CN114623990B - Monitoring and leakage positioning method, device, boiler, system and storage medium - Google Patents
Monitoring and leakage positioning method, device, boiler, system and storage medium Download PDFInfo
- Publication number
- CN114623990B CN114623990B CN202011475800.0A CN202011475800A CN114623990B CN 114623990 B CN114623990 B CN 114623990B CN 202011475800 A CN202011475800 A CN 202011475800A CN 114623990 B CN114623990 B CN 114623990B
- Authority
- CN
- China
- Prior art keywords
- smoke pressure
- smoke
- boiler
- time
- pressure measuring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 137
- 238000000034 method Methods 0.000 title claims abstract description 89
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 239000007788 liquid Substances 0.000 claims abstract description 437
- 238000001514 detection method Methods 0.000 claims abstract description 170
- 230000036541 health Effects 0.000 claims abstract description 42
- 230000004044 response Effects 0.000 claims abstract description 12
- 239000000779 smoke Substances 0.000 claims description 854
- 230000008859 change Effects 0.000 claims description 207
- 230000002159 abnormal effect Effects 0.000 claims description 95
- 238000009530 blood pressure measurement Methods 0.000 claims description 89
- 230000005856 abnormality Effects 0.000 claims description 57
- 238000005070 sampling Methods 0.000 claims description 53
- 238000004364 calculation method Methods 0.000 claims description 47
- 238000004422 calculation algorithm Methods 0.000 claims description 37
- 238000012423 maintenance Methods 0.000 claims description 34
- 238000009499 grossing Methods 0.000 claims description 31
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 27
- 230000006870 function Effects 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 15
- 230000003862 health status Effects 0.000 claims description 10
- 230000005855 radiation Effects 0.000 claims description 8
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 239000013589 supplement Substances 0.000 claims description 4
- 230000008439 repair process Effects 0.000 claims description 3
- 230000001502 supplementing effect Effects 0.000 claims description 3
- 241000208125 Nicotiana Species 0.000 claims 8
- 235000002637 Nicotiana tabacum Nutrition 0.000 claims 8
- 230000035945 sensitivity Effects 0.000 abstract description 20
- 238000011897 real-time detection Methods 0.000 abstract description 10
- 238000007619 statistical method Methods 0.000 description 24
- 238000010586 diagram Methods 0.000 description 22
- 230000008569 process Effects 0.000 description 19
- 238000004891 communication Methods 0.000 description 15
- 238000003062 neural network model Methods 0.000 description 15
- 238000005516 engineering process Methods 0.000 description 11
- 238000012545 processing Methods 0.000 description 10
- 230000009286 beneficial effect Effects 0.000 description 9
- 238000005260 corrosion Methods 0.000 description 5
- 238000009826 distribution Methods 0.000 description 5
- 238000004880 explosion Methods 0.000 description 5
- 230000007797 corrosion Effects 0.000 description 4
- 238000010438 heat treatment Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 229920006395 saturated elastomer Polymers 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 239000000446 fuel Substances 0.000 description 2
- 239000007789 gas Substances 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 239000002918 waste heat Substances 0.000 description 1
- 238000004056 waste incineration Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
- G01M3/26—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors
- G01M3/32—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors for containers, e.g. radiators
- G01M3/3236—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors for containers, e.g. radiators by monitoring the interior space of the containers
- G01M3/3254—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors for containers, e.g. radiators by monitoring the interior space of the containers using a flow detector
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
- G01M3/26—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors
- G01M3/32—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors for containers, e.g. radiators
- G01M3/3236—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors for containers, e.g. radiators by monitoring the interior space of the containers
- G01M3/3272—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors for containers, e.g. radiators by monitoring the interior space of the containers for verifying the internal pressure of closed containers
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Examining Or Testing Airtightness (AREA)
Abstract
The embodiment of the application provides a monitoring and leakage positioning method, equipment, a boiler, a system and a storage medium. In the embodiment of the application, the historical liquid loss and the real-time liquid loss of the boiler, which are acquired by the existing flowmeter of the boiler, are subjected to variable point detection, the health condition of the current boiler is determined according to the variable point detection result, the real-time monitoring of boiler leakage is realized, the variable point detection is carried out by utilizing the liquid loss, the response speed is higher, the variable point can be detected without accumulating a large number of points, the timely detection of boiler leakage is facilitated, and the sensitivity of the real-time detection of boiler leakage is improved.
Description
Technical Field
The present application relates to the field of industrial monitoring technologies, and in particular, to a method, an apparatus, a boiler, a system, and a storage medium for monitoring and positioning leakage.
Background
The boiler is an energy conversion device, the energy input to the boiler is chemical energy and electric energy in fuel, and the boiler outputs steam, high temperature water or organic heat carrier with certain heat energy. The hot water or steam generated in the boiler can directly provide heat energy required by industrial production and people living, and can also be converted into mechanical energy through a steam power device or converted into electric energy through a generator.
At present, the boiler steam leakage accident is a main reason for influencing the safe and stable operation of the boiler, is a main factor for reducing the efficiency of a power plant, and is also a main reason for stopping the boiler. Practice has shown that most leaks develop from tiny leaks, and when the worker is able to perceive the leak, the damage caused by the leak is quite serious and often causes a significant loss. Therefore, the method for predicting the leakage of the steam pipeline of the boiler in real time has great significance in ensuring personal safety of workers, reducing economic loss and reasonably arranging maintenance.
Disclosure of Invention
Aspects of the present application provide a monitoring and leak location method, apparatus, boiler, system and storage medium for improving the sensitivity of real-time monitoring of boiler steam leaks.
An embodiment of the present application provides a monitoring system, including: monitoring nodes, a boiler and a flowmeter arranged in the boiler;
the flowmeter is used for collecting real-time total liquid flow and real-time steam flow of the boiler;
The monitoring node is used for determining the real-time liquid loss of the boiler according to the real-time total liquid flow and the real-time steam flow; performing variable point detection on the historical liquid loss and the real-time liquid loss of the boiler; and determining the health condition of the current boiler according to the change point detection result.
The embodiment of the application also provides a monitoring method, which comprises the following steps: acquiring real-time total liquid flow and real-time steam flow of a boiler; determining the real-time liquid loss of the boiler according to the real-time total liquid flow and the real-time steam flow; performing variable point detection on the historical liquid loss and the real-time liquid loss of the boiler; and determining the health condition of the current boiler according to the change point detection result.
The embodiment of the application also provides a leakage positioning method, which comprises the following steps:
under the condition that liquid leakage exists in the boiler, acquiring a smoke pressure sequence acquired by a pressure gauge of a plurality of smoke pressure measuring points distributed in the boiler before the boiler is maintained; the smoke pressure sequence that the manometer of a plurality of smoke pressure measurement stations gathered includes: the pressure gauges of the smoke pressure measuring points collect smoke pressure data before and after liquid leakage exists in the boiler;
respectively detecting the smoke pressure sequences acquired by the pressure gauges of the smoke pressure measuring points to determine smoke pressure change points in the smoke pressure sequences acquired by the pressure gauges of each smoke pressure measuring point;
Determining a normal sample interval and an abnormal sample interval of a smoke pressure sequence corresponding to each smoke pressure measuring point based on smoke pressure change points in the smoke pressure sequence acquired by a pressure gauge of each smoke pressure measuring point;
Calculating an abnormality index of each smoke pressure measuring point by using the smoke pressure in the normal sample interval and the smoke pressure in the abnormal sample interval corresponding to each smoke pressure measuring point;
and determining the risk sequence of leakage of the plurality of smoke pressure measuring points according to the magnitude of the abnormality indexes of the plurality of smoke pressure measuring points, so that maintenance personnel can position the smoke pressure measuring points with leakage based on the risk sequence.
The embodiment of the application also provides a boiler, which comprises: a flowmeter and a monitoring module installed in the boiler;
the flowmeter is used for collecting real-time total liquid flow and real-time steam flow of the boiler;
the monitoring module is used for determining the real-time liquid loss of the boiler according to the real-time total liquid flow and the real-time steam flow; performing variable point detection on the historical liquid loss and the real-time liquid loss of the boiler; and determining the health condition of the current boiler according to the change point detection result.
The embodiment of the application also provides a computer device, which comprises: a memory and a processor; wherein the memory is used for storing a computer program;
The processor is coupled to the memory for executing the computer program for performing the steps of the methods described above.
Embodiments of the present application also provide a computer-readable storage medium storing computer instructions that, when executed by one or more processors, cause the one or more processors to perform the steps in the methods described above.
In the embodiment of the application, the historical liquid loss and the real-time liquid loss of the boiler, which are acquired by the existing flowmeter of the boiler, are subjected to variable point detection, the health condition of the current boiler is determined according to the variable point detection result, the real-time monitoring of boiler leakage is realized, the variable point detection is carried out by utilizing the liquid loss, the response speed is higher, the variable point can be detected without accumulating a large number of points, the timely detection of boiler leakage is facilitated, and the sensitivity of the real-time detection of boiler leakage is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
Fig. 1a and fig. 1b are schematic structural diagrams of a monitoring system according to an embodiment of the present application;
FIG. 1c is a schematic diagram of a data billboard reflecting boiler health conditions according to an embodiment of the present application;
FIG. 1d is a schematic diagram of another monitoring system according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of a monitoring method according to an embodiment of the present application;
FIG. 3 is a schematic flow chart of a leak location method according to an embodiment of the present application;
Fig. 4 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The boiler of the power station is in a high-temperature, high-pressure and high-corrosion environment for a long time, and is easy to leak and even burst a steam pipeline. The boiler steam leakage accident is a main reason for influencing the safe and stable operation of the boiler, is a main factor for reducing the efficiency of a power plant, and is also a main reason for stopping the boiler. The current method for detecting boiler steam leakage mainly comprises the following two modes:
Mode 1: the temperature sensor module is used for measuring temperature data, the infrared thermal imaging module is used for acquiring image data, and then the temperature data and the image data are analyzed to realize the positioning of the position of high-temperature steam in the high-temperature steam pipeline.
Mode 2: and the acoustic wave sensor and the acoustic wave transmitter are arranged on the boiler pipeline in parallel, and the position of the pipe explosion is positioned by analyzing acoustic wave data.
The precondition of the implementation of the two modes is that a large number of sensors are additionally installed so as to achieve the function of positioning the position of the tube explosion, and the detection cost is high. On the other hand, in the above-mentioned mode 1, since the hysteresis of the temperature is strong and the response speed is slow, when the temperature change amplitude exceeds a certain threshold value, the leakage tends to develop to a relatively serious stage, the leakage detection sensitivity is low, and the leakage early warning effect of the temperature sensor is greatly reduced.
With respect to the above-described mode 2, for a waste incineration power station boiler, the positions where leakage and tube explosion most often occur are mainly distributed in the vicinity of the first radiation passage of the boiler, which is the largest part of the boiler. If the acoustic wave sensor is installed on the outer wall of the first radiation of the boiler, it is difficult to detect the acoustic wave signal due to the thicker wall thickness of the first radiation channel. If the acoustic wave sensor is directly arranged on the steam pipeline, the acoustic wave sensor is directly contacted with high-temperature high-pressure high-corrosiveness smoke, and is extremely easy to damage and extremely high in cost.
In order to realize real-time prediction of leakage of a boiler steam pipeline and improve leakage detection sensitivity, in some embodiments of the application, a probability statistical method is utilized to perform variable point detection on the historical liquid loss and the real-time liquid loss of a boiler, which are acquired by the existing flowmeter of the boiler, and the health condition of the current boiler is determined according to the variable point detection result, so that real-time monitoring of boiler leakage is realized, the variable point detection is performed by utilizing the liquid loss, the response speed is higher, the variable point can be detected without accumulating a large number of points, the boiler leakage can be detected in time, and the sensitivity of real-time detection of boiler leakage is improved.
On the other hand, as the flowmeter is an infrastructure of the boiler, the boiler is subjected to leakage detection by utilizing flow data acquired by the existing flowmeter of the boiler, and a sensor is not required to be additionally installed, so that the detection cost is saved.
The following describes in detail the technical solutions provided by the embodiments of the present application with reference to the accompanying drawings.
It should be noted that: like reference numerals denote like objects in the following figures and embodiments, and thus once an object is defined in one figure or embodiment, further discussion thereof is not necessary in the subsequent figures and embodiments.
Fig. 1a is a schematic structural diagram of a monitoring system according to an embodiment of the present application. As shown in fig. 1a, the system mainly comprises: boiler 11, flowmeter 12 installed in boiler 11, and monitoring node 13.
The boiler 11 includes: a boiler and a furnace. The upper part for storing liquid is a boiler, the lower heating part is a furnace, and the integrated design of the boiler and the furnace is called a boiler. The boiler is an energy converter, which is a device for heating working medium water or other liquid to a certain parameter by using heat energy released by fuel combustion or other heat energy.
In the present embodiment, a plurality of flow meters 12 are installed in the boiler 11. The plural means 2 or more than 2. The plurality of flow meters 12 are used to collect real-time total liquid flow and real-time steam flow, respectively, of the boiler 11. The flowmeter for collecting the real-time total liquid flow of the boiler 11 can be arranged on the inner wall or the outer wall of the boiler barrel 18 and at the water supply inlet. A flow meter 12 for collecting real-time steam flow of the boiler 11 may be installed at a steam outlet of the boiler 11. In the present embodiment, the plurality of flow meters 12 may periodically collect the real-time total liquid flow rate and the real-time steam flow rate of the boiler 11 according to the set sampling period T 1. The sampling periods of the plurality of flowmeters 11 may be the same or different. Preferably, the sampling periods of the plurality of flow meters 11 are the same. In the present embodiment, the specific values of the sampling periods T 1 of the plurality of flowmeters 11 are not limited. In order to improve the sensitivity of safety monitoring, the health condition of the boiler 11 is conveniently found in time. The sampling period T 1 of the plurality of flow meters 11 is preferably not too large, and may be of the order of seconds. For example, the sampling period T 1 of the plurality of flowmeters 11 may be 5s, 10s, 15s, or the like, but is not limited thereto.
In this embodiment, the monitoring node 13 refers to an apparatus, a module or a computer device having data processing capability. The computer device may be a terminal device or a server device. The terminal equipment can be a smart phone, a tablet personal computer, a wearable device and the like. The server device may be a single server device, a cloud server array, or a Virtual Machine (VM) running in the cloud server array. In addition, the server device may also refer to other computing devices having corresponding service capabilities, for example, a terminal device (running a service program) such as a computer, and the like. In this embodiment, the monitoring node 13 may be located in a machine room of the boiler 11 and in communication with the flow meter 12.
In this embodiment, the monitoring node 13 may obtain the real-time total liquid flow and the real-time steam flow collected by the flowmeter 12; and determining the real-time liquid loss of the boiler according to the real-time total liquid flow and the real-time steam flow. Further, the monitoring node 13 may also obtain a historical liquid loss of the boiler. The historical liquid loss of the boiler 11 refers to the liquid loss before the current time, that is, the liquid loss of the boiler 11 acquired by the monitoring node 13 before the real-time liquid loss is determined. In the embodiment of the present application, the historical liquid loss amount of the boiler 11 is the liquid loss amount in the period of time nearest to the acquisition time of the real-time liquid loss amount. In this embodiment, the specific value of the collection period of the historical liquid loss amount is not limited. For example, the period of time of acquisition of the historical liquid loss may be a period of time of 1 day, 2 days, one week, half month, 1 month, 2 months, etc. prior to the current time.
Further, the monitoring node 13 may perform a variable point detection of the historical liquid loss amount and the real-time liquid loss amount of the boiler. In the embodiment of the application, the specific implementation mode of performing the variable point detection on the historical liquid loss amount and the real-time liquid loss amount of the boiler is not limited.
In some embodiments, the monitoring node 13 may utilize a neural network model to perform variable point detection on the historical liquid loss amount and the real-time liquid loss amount of the boiler. However, because the abnormal conditions such as leakage and the like of the boiler are small probability events, and a large number of abnormal samples are needed by the neural network model in the training stage, the abnormal liquid loss amount sample may be insufficient when the neural network model is trained, and the trained neural network model has low accuracy in variable point detection. On the other hand, because the neural network model has a complex structure and large calculation amount, the variable point detection efficiency is low, and the boiler leakage real-time detection sensitivity is low.
To address the above, in some embodiments, the monitoring node 13 may employ a probabilistic statistical method to perform variable point detection on the historical liquid loss and the real-time liquid loss of the boiler. Specifically, the monitoring node 13 may employ a probability statistical method to perform a variable point detection on the historical liquid loss and the real-time liquid loss of the boiler, so as to determine whether the real-time liquid loss is a variable point. The method comprises the steps of detecting the change point of the historical liquid loss and the real-time liquid loss of the boiler by using a probability statistical method, and is beneficial to improving the accuracy of the change point detection without a large number of abnormal samples. On the other hand, the probability statistical method is used for detecting the variable points, a large number of variable point interfaces do not need to be accumulated for detecting the variable points, the boiler leakage can be detected timely, and the sensitivity of the real-time detection of the boiler leakage is improved.
Alternatively, a Bayesian variable point detection algorithm can be employed to perform variable point detection on the historical liquid loss amount and the real-time liquid loss amount of the boiler. Accordingly, the monitoring node 13 may utilize a bayesian variable point detection model to perform variable point detection on the historical liquid loss amount and the real-time liquid loss amount of the boiler 11.
The principle of the Bayesian online variable point detection algorithm is as follows: bayesian change point detection assumes that the change points are generated by a random process, and that the data between the change points is independently co-distributed. The algorithm may output the probability that each data point is a change point. Assuming the time series data is y 1:n=(y1,y2,…,yn), the algorithm output is the probability series p 1:n=(p1,p2,…,pn). Y i is considered a change point when a certain data point p i > θ. Where θ is a set threshold. In the embodiment of the present application, θ=0.5. This is because the variation points of the liquid loss amount are independently and uniformly distributed, and the probability of being the variation point and not being the variation point is 0.5 for the liquid loss amount at a certain time. Thus, θ=0.5 can be set.
The current methods for leakage warning mostly rely on the selection of threshold values, such as setting a temperature threshold value in the above-mentioned mode 1 and setting a sound wave threshold value in the mode 2. The threshold value is selected to be too small, the leakage of the boiler can be found after the boiler leaks and accumulates for a period of time, the leakage is easy, and the proper overhaul time can be missed; and too large a threshold value is easy to generate false alarms, and too many false alarms can lose the value of the early warning. And the selection of the threshold depends on engineering experience, different thresholds are set according to different equipment requirements, and the early warning system is difficult to obtain better generalization capability and difficult to use in different scenes, so that the popularization of the technology is limited.
The Bayesian variable point detection algorithm is based on the characteristic that data among variable points are independent and distributed, and a probability threshold value is set, so that different thresholds are not required to be set for different equipment, the Bayesian variable point detection algorithm can be applied to various boiler scenes, and the technical popularization of an early warning method is facilitated. On the other hand, the Bayesian variable point detection algorithm can accurately detect the variable point only by accumulating a small number of sample points after the variable point actually appears in the boiler 11, thereby being beneficial to improving the timeliness and the sensitivity of boiler leakage detection and playing a role in early warning. Moreover, the algorithm can detect other types of inflection points except for the step, and can capture small changes of water loss data distribution tens of days before pipe explosion.
Accordingly, the monitoring node 13 may input the historical liquid loss amount and the real-time liquid loss amount of the boiler 11 into the bayesian variable point detection model; in the Bayesian variable point detection model, the historical liquid loss amount and the real-time liquid loss amount of the boiler 11 can be utilized to calculate the probability that the real-time liquid loss amount is a variable point; and determining whether the real-time liquid loss is the change point according to the probability that the real-time liquid loss is the change point. Optionally, if the probability that the real-time liquid loss amount is the change point is greater than the set probability threshold θ, determining that the real-time liquid loss amount is the change point.
Optionally, in the bayesian variable point detection model, the prior condition and the posterior condition which can be set initially detect that the first liquid loss in the time sequence formed by the historical liquid loss and the real-time liquid loss is the probability of the variable point, and if the probability is smaller than the set probability threshold value θ, it is determined that the acquisition time corresponding to the first liquid loss is before the variable point. And then, according to the determined probability that the acquisition time corresponding to the first liquid loss is before the change point, adjusting the prior condition and the posterior condition, and then calculating the probability that the second liquid loss in the time sequence formed by the historical liquid loss and the real-time liquid loss is the change point by using the adjusted prior condition and the posterior condition, and if the probability is smaller than a set probability threshold value theta, determining that the acquisition time corresponding to the second liquid loss is before the change point. And the like, iteratively detecting the probability that each liquid loss amount in a time sequence formed by the historical liquid loss amount and the real-time liquid loss amount is a variable point according to the sequence of the acquisition time, and determining that the liquid loss amount is the variable point if the probability that the liquid loss amount is the variable point is larger than the set probability threshold value theta in the iteration process. For the real-time liquid loss in the time sequence formed by the historical liquid loss and the real-time liquid loss, the prior condition and the posterior condition can be adjusted by utilizing the detection result of the previous liquid loss; calculating the probability that the real-time liquid loss is a variable point by using the adjusted priori condition and posterior condition; further, if the probability is greater than the set probability threshold θ, the real-time liquid loss amount is determined to be a change point.
In some embodiments, the sampling period of the flow meter 12 is shorter and the corresponding time span of the historical fluid loss is longer, resulting in a greater data volume for the historical fluid loss. To improve the efficiency of the change point detection, the historical liquid loss may be downsampled. Accordingly, the monitoring node 13 may downsample the historical liquid loss of the boiler according to the set sampling period T 2. For ease of description and distinction, in the embodiment of the present application, the sampling period of the flow meter 12 is defined as a first sampling period T 1, and the sampling period employed for downsampling is defined as a second sampling period T 2. Wherein the second sampling period T 2 is greater than the first sampling period T 1,T2>T1. In the embodiment of the present application, the specific value of the second sampling period T 2 is not limited. The second sampling period T 2 can be flexibly set according to the variable point detection efficiency and the variable point detection accuracy. For example, the second sampling period T 2 may be 10min, 20min, 30min, etc.
The liquid loss sequence formed by the down-sampled historical liquid loss and the real-time liquid loss can be expressed as: g (t 1∶tn)={g(t1),g(t2),...g(tn) }, wherein the time interval between two adjacent liquid loss amounts of the downsampled liquid loss sequence is: t i-ti-1=T2; wherein i is more than 1 and less than or equal to n. Alternatively, g (t 1) may be the amount of fluid loss corresponding to the first point in time t 1 after the last shutdown repair in the historical fluid loss data. g (t n) may be the amount of liquid loss corresponding to the current time t n.
Further, the monitoring node 13 may perform variable point detection on the down-sampled historical liquid loss and the real-time liquid loss by using a probability statistical method. Optionally, to avoid noise interference in the fluid loss amount, the downsampled historical fluid loss amount and the real-time fluid loss amount may be smoothed to obtain the smoothed historical fluid loss amount and the smoothed real-time fluid loss amount.
Alternatively, the downsampled historical fluid loss and real-time fluid loss may be smoothed using an exponentially weighted moving window function. The formula for smoothing an exponentially weighted moving window function can be expressed as:
Wherein g (t i) represents an observed value at time t i, namely a liquid loss value before smoothing at time t i; The predicted value of the exponential weighting at time t i is shown, that is, the liquid loss after the smoothing treatment at time t i. Alpha is a smoothing coefficient. Alternatively, α=0.2.
Further, the monitoring node 13 may perform the variable point detection on the smoothed historical liquid loss and the smoothed real-time liquid loss by using a probability statistical method. Optionally, a bayesian variable point detection algorithm may be used to perform variable point detection on the historical liquid loss after the smoothing process and the real-time liquid loss after the smoothing process, and in the specific embodiment, reference may be made to the above related content of performing variable point detection on the historical liquid loss and the real-time liquid loss by using a bayesian variable point detection model, which is not described herein again.
Further, the monitoring node 13 may determine the current health status of the boiler according to the change point detection result. Optionally, if the change point detection result is that the real-time liquid loss amount is the change point, determining that the liquid leakage occurs in the current boiler.
Further, in order for the technician to intuitively understand the health of the boiler, the monitoring system may also be provided with a display node 14, as shown in fig. 1 b. The display node 14 refers to a module, an apparatus or a device having an imaging function. Wherein the display node 14 may be configured with a screen. The screen may be a display screen, curtain, or the like. Alternatively, the display node 14 may have only a screen with an imaging function, such as a display screen, a curtain, or the like. Or the display node 14 may be a computer device configured with a display screen. For example, the display node 14 may be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart television, or the like.
In this embodiment, the display node 14 and the monitoring node 13 may be located in the same physical machine or may be located in different physical machines. And communication connection between different physical machines. The different physical machines may be connected wirelessly or by wire. Alternatively, different physical machines may be connected through mobile network communication, and accordingly, the network system of the mobile network may be any one of 2G (GSM), 2.5G (GPRS), 3G (WCDMA, TD-SCDMA, CDMA2000, UTMS), 4G (LTE), 4g+ (lte+), 5G, wiMax, and so on. Alternatively, the different physical machines may be communicatively connected by bluetooth, wiFi, infrared, or the like.
Accordingly, the monitoring node 13 may provide the current boiler health status to the display node 14. The display node 14 may display the current health of the boiler. In embodiments of the present application, the specific format and information of the current boiler health status displayed by the display node 14 is not limited. In one embodiment, as shown in FIG. 1b, the display node 14 may display a data billboard reflecting a relationship of the health of the boiler over time. Alternatively, the data sign reflecting the relationship of the health of the boiler over time may be expressed as: and a data signboard reflecting the change relation of the real-time liquid loss quantity of the boiler with time, and displaying the change point in the data signboard in a set display format under the condition that the change point exists. As shown in fig. 1b, for the change point, the change point may be displayed by a connection line between the time corresponding to the change point and the liquid loss amount; and/or displaying the moment corresponding to the change point on the data billboard. The data signboard reflecting the change relation of the real-time liquid loss of the boiler along with time can be a graphical signboard or a list signboard. The graphical board can be at least one of a scatter diagram board, a graph board, a line diagram board, a histogram board, a bullet diagram board, an area diagram board and a waterfall diagram board. Fig. 1b is illustrated only in the form of a graphic billboard, but is not limiting.
In other embodiments, the data sign reflecting the change in the health of the boiler over time may be a graphical sign or a list sign (shown in FIG. 1 c), or the like. The graphical board can be at least one of a scatter diagram board, a graph board, a line diagram board, a histogram board, a bullet diagram board, an area diagram board and a waterfall diagram board.
In still other embodiments, the monitoring node 13 may also output leakage alarm information in case of leakage of the current boiler. In the present embodiment, the specific embodiment in which the monitoring node 13 outputs the leakage alarm information is not limited. In some embodiments, the monitoring node 13 may provide leakage alarm information to the display node 14 in case of leakage of the current boiler. Accordingly, display node 14 may display leak alert information. In this embodiment, the leakage alarm information may be text information, picture information, animation information, or the like.
In other embodiments, the monitoring node 13 may voice report the leak alert information. In this embodiment, the leakage alarm information is implemented as a voice message.
In still other embodiments, the monitoring node 13 may control a buzzer or the like to sound in the event of leakage of the current boiler as the leakage alarm information.
In other embodiments, the monitoring node 13 may control the indicator lamp to be turned on or flash, etc. as the leakage alarm information in case of leakage of the current boiler.
In some embodiments, the monitoring node 13 may also calculate the loss rate of the real-time liquid loss amount of the boiler 11; and provides the loss rate of the real-time liquid loss amount of the boiler 11 to the display node 14. Accordingly, the display node 14 can display the loss speed of the real-time liquid loss of the boiler, so that a technician can intuitively know the loss speed of the real-time liquid loss of the boiler, and can provide reference information for the technician to judge whether the boiler leaks or not.
In other embodiments, the monitoring system may further comprise: a level gauge (not shown in fig. 1 a) disposed within the boiler 11; the level gauge may be used to collect the liquid level of the boiler 11.
For the monitoring node 13, the water inlet of the boiler 11 can be controlled to be opened under the condition that the liquid level of the boiler 11 is lower than a set first liquid level threshold value; and controlling the water inlet of the boiler 11 to be closed under the condition that the liquid level of the boiler 12 reaches a set second liquid level threshold value; wherein the second liquid level threshold is greater than the first liquid level threshold.
And/or, the monitoring node 13 can output water shortage prompt information to prompt a manager of the boiler to supplement water under the condition that the liquid level of the boiler is lower than a set first liquid level threshold value; and outputting full liquid level prompt information to prompt a manager of the boiler to stop water replenishment under the condition that the liquid level of the boiler 11 reaches a set second liquid level threshold value; etc.
In the embodiment of the application, the display node 14 displays the real-time health condition of the boiler, so that technicians can intuitively know the real-time health condition of the boiler, and the timeliness of overhaul is improved. Alternatively, the technician may decide on downtime for maintenance based on the amount of real-time fluid loss.
In order to improve maintenance efficiency, the monitoring system provided by the embodiment of the application can also be used for positioning leakage. In an embodiment of the present application, to reduce the cost of leak location, a plurality of pressure gauges (not shown in fig. 1a and 1 b) existing within the boiler may be used for leak location. The plural means 2 or more than 2. In an embodiment of the present application, a plurality of pressure gauges may be installed at a plurality of smoke pressure measuring points of the boiler 11 for detecting smoke pressures at the corresponding smoke pressure measuring points. The smoke pressure refers to the pressure of smoke in the flue. In the embodiment of the application, at least one pressure gauge is arranged at each smoke pressure measuring point.
In an embodiment of the present application, a plurality of smoke pressure measurement points includes: at least two of the inlet and outlet of the radiation passage 15 of the boiler, the inlet and outlet of the superheater 16, and the inlet and outlet of the economizer 17. The superheater 16 may include: at least one of the high temperature superheater 16a, the medium temperature superheater 16b and the low temperature superheater 16 c. In the present embodiment, the high-temperature superheater 16a, the medium-temperature superheater 16b and the low-temperature superheater 16c are not limited to the description of the relationship between the temperatures of the three types of steam, i.e., the temperature of the steam passing through the high-temperature superheater 16a is higher than that of the medium-temperature superheater 16b; the temperature of the steam passing through the medium-temperature superheater 16b is greater than that of the low-temperature superheater 16c, and the specific temperatures of the steam passing through the high-temperature superheater 16a, the medium-temperature superheater 16b, and the low-temperature superheater 16c are not limited. Optionally, the smoke pressure measurement points include the following 12: the device comprises a first radiation channel outlet left side, a first radiation channel outlet right side, a high-temperature superheater inlet left side, a high-temperature superheater inlet right side, a medium-temperature superheater inlet left side, a medium-temperature superheater inlet right side, a low-temperature superheater inlet left side, a low-temperature superheater inlet right side, an economizer inlet left side, an economizer inlet right side, an economizer outlet left side and an economizer outlet right side.
The superheater 16 is an auxiliary heating surface of the boiler, and can lead out saturated steam from the boiler drum 19 under the condition of unchanged pressure, evaporate moisture in the wet saturated steam through heating to become dry saturated steam, and continuously heat to raise the temperature to become superheated steam.
The economizer 17 is a heat exchanger which is arranged in a tail flue of the boiler and utilizes the exhaust gas waste heat to increase the water supply temperature, so that the liquid temperature is increased, the exhaust gas loss is reduced, and the heat efficiency of the boiler is improved.
In an embodiment of the present application, the monitoring node 13 may acquire a sequence of smoke pressures acquired by a pressure gauge for a plurality of smoke pressure measurement points before the boiler 11 is maintained in case of liquid leakage of the boiler 11. Alternatively, the monitoring node 13 may determine that there is a liquid leak in the boiler 11 in the case of the above-described monitoring of the change point. The monitoring node 13 can acquire a smoke pressure sequence acquired by a pressure gauge of a plurality of smoke pressure measuring points in a set time period before the current moment under the condition that the liquid leakage occurs in the boiler 11. The current time is any time before shutdown maintenance. The sequence of smoke pressures over the set time period may include: the smoke pressure data before the liquid leakage of the boiler 11 and the smoke pressure data after the liquid leakage of the boiler 11. The set time period can be flexibly determined according to the time interval of the liquid leakage from the boiler 11 at the present moment. For example, the monitoring node 13 may acquire a sequence of smoke pressures acquired by pressure gauges at a plurality of smoke pressure points within 10 hours (10 hours) before the current time in the case where liquid leakage occurs in the boiler 11. In the present embodiment, the sampling period of the pressure gauge is not limited. The sampling period of the pressure gauge may be the same as the sampling period of the flow meter. In order to improve the safety of the boiler, the sampling period of the pressure gauge is not suitable to be too long. Alternatively, the sampling period of the manometer may be 5s, 10s, etc.
Alternatively, as shown in FIG. 1d, the monitoring node 13 may deploy a real-time leak early warning model and a leak location model. The historical production database of FIG. 1d may store data collected by the data collection device. In the embodiment of the application, the data acquisition equipment mainly comprises the flowmeter and the pressure gauge. Accordingly, the historical production database stores the historical total liquid flow and the historical steam flow collected by the flowmeter and the smoke pressure sequence collected by the pressure gauge. The front-end interface is disposed on the display node 14, and is used for displaying the real-time health status of the boiler 11. In fig. 1d, the real-time leakage early warning model is used to realize the real-time monitoring of the boiler health status, and in case that the leakage of the boiler is detected, the leakage positioning model is triggered to operate so as to define the leakage position of the boiler 11. In some embodiments, since the downtime and maintenance time is determined by a technician according to the liquid loss, in order to improve the accuracy of the leakage positioning, for the leakage positioning model, a sequence of the pressures collected by the pressure gauges of the plurality of pressure measurement points in real time can be periodically scheduled according to a set scheduling period, and the leakage positioning is performed until the downtime and maintenance is performed by using the sequence of the pressures scheduled by the current scheduling period. The smoke pressure sequence scheduled by the leakage positioning model in each scheduling period can comprise: the pressure gauges of the smoke pressure measuring points collect smoke pressure sequences in the current dispatching cycle and set smoke pressure sequences in a time period before the current dispatching cycle. In the embodiment of the application, the specific value of the scheduling period is not limited. Alternatively, the scheduling period is greater than the sampling period of the pressure gauge, which may be on the order of minutes, e.g., 3 minutes, 5 minutes, 8 minutes, etc.
Further, the monitoring node 13 may perform a change point detection on the smoke pressure sequences collected by the pressure gauges of the scheduled smoke pressure measurement points, so as to determine smoke pressure change points in the smoke pressure sequences collected by the pressure gauges of each smoke pressure measurement point.
The monitoring node 13 performs the same manner of detecting the change point of the smoke pressure sequence corresponding to each smoke pressure measuring point. An exemplary explanation will be made below taking the jth smoke pressure measurement point in the monitoring node 13 as an example. Where j=1, 2,..k, k represents the total number of smoke pressure points. The j-th smoke pressure measuring point is any smoke pressure measuring point in the plurality of smoke pressure measuring points.
For the jth smoke pressure measuring point, the monitoring node 13 can utilize a PELT (Pruned Exact LINEAR TIME) algorithm to detect the smoke pressure sequence of the jth smoke pressure measuring point scheduled by the current calling period so as to determine the smoke pressure change point in the smoke pressure sequence corresponding to the jth smoke pressure measuring point. The smoke pressure measuring point is any smoke pressure measuring point in the plurality of smoke pressure measuring points. The smoke pressure sequence corresponding to the jth smoke pressure measuring point can be the smoke pressure sequence acquired by a pressure gauge installed at the jth smoke pressure measuring point in the current scheduling period. The principle of the PELT algorithm is described below:
For any time series y 1:n=(y1,y2,…,yn), assume its point of change is τ 1:m=(τ1,τ2,…,τm);
the algorithm aims at minimizing:
Where C represents the loss function and β represents the penalty factor to prevent overfitting. Wherein the loss function can be expressed as:
Wherein f (y i |θ) represents the density function of the independent same distribution.
For time series y 1:s, let the set of change points be T s={τ:0=τ0<τ1<…<τm<τm+1 =s }:
Thus, minimizing the loss of y 1:s can be solved by minimizing the loss of y 1:t by recursive calculation, where t < s, s=1, 2, … n. Finally, a series of variators in the time series y 1:n=(y1,y2,…,yn) can be found. In this embodiment, y 1:n=(y1,y2,…,yn) is the smoke pressure sequence of the smoke pressure measurement points.
In the embodiment of the application, in order to reduce the calculated amount and improve the positioning efficiency, the smoke pressure data in the current calling period can be downsampled. Optionally, the smoke pressure sequence corresponding to each smoke pressure measuring point in the current scheduling period may be downsampled according to the third sampling period T 3. In this embodiment, the third sampling period is smaller than the sampling period of the pressure gauge, and the specific value of the third sampling period T 3 is not limited. Alternatively, the third sampling period T 3 may be 30s, 1min, 2min, and so on.
Further, in order to avoid noise interference in the downsampled smoke pressure sequence, the downsampled smoke pressure sequence may be smoothed to obtain a smoothed smoke pressure sequence. The smoothed smoke pressure sequence can be expressed as:
fj(tl:tstop)={fj(tl),fj(tl+1),...fj(ti),fj(ti+1),...fj(tstop)} (5)
In the formula (5), t i+1-ti=T3, 1 is less than or equal to j is less than or equal to k, k is the total number of the smoke pressure measuring points, and j represents the j-th smoke pressure measuring point, namely the number of the smoke pressure measuring point. In the equation (5), only the current time is taken as the shutdown maintenance time t stop as an example, and t l is the acquisition time of the set period of time from t stop.
It should be noted that, the following smoke pressure sequences corresponding to the smoke pressure measuring points may be smoke pressure sequences after the downsampling and smoothing process, or may be smoke pressure sequences without the downsampling and smoothing process.
Further, the monitoring node 13 may determine a normal sample interval and an abnormal sample interval of the smoke pressure sequence corresponding to each smoke pressure measurement point based on the smoke pressure change point in the smoke pressure sequence acquired by the pressure gauge of the smoke pressure measurement point. In the following, a specific embodiment of determining a normal sample section and an abnormal sample section of a smoke pressure sequence will be described by taking a j-th smoke pressure measurement point as an example.
Optionally, a peak may be found for the smoke pressure sequence corresponding to the jth smoke pressure measurement point, so as to determine a smoke pressure peak in the smoke pressure sequence corresponding to the jth smoke pressure measurement point. Wherein, the time corresponding to the smoke pressure peak value is respectively: h j represents the total number of smoke pressure peaks existing in the smoke pressure sequence corresponding to the j-th smoke pressure measuring point.
Further, the maximum smoke pressure peak value can be determined from the smoke pressure peak value in the smoke pressure sequence corresponding to the j-th smoke pressure measuring point, and the first smoke pressure changing point and the second smoke pressure changing point, the acquisition time of which is adjacent to the acquisition time corresponding to the maximum smoke pressure peak value, are acquired from the smoke pressure changing points in the smoke pressure sequence corresponding to the j-th smoke pressure measuring point. The acquisition time of the maximum smoke pressure peak value is p j; the acquisition time of the first smoke pressure change point and the second smoke pressure change point is respectively as follows: And/> WhereinAnd is also provided with
Further, the smoke pressure collected in the collection time period from the first smoke pressure change point to the second smoke pressure change point can be obtained from the smoke pressure sequence corresponding to the j-th smoke pressure measurement point and used as an abnormal sample section of the smoke pressure sequence corresponding to the j-th smoke pressure measurement point, namelyThe corresponding smoke pressure sequence is an abnormal sample interval.
Further, from the smoke pressure sequence corresponding to the j-th smoke pressure measuring point, first smoke pressure data, the acquisition time of which is located before the first smoke pressure changing point and the time interval between the acquisition time and the first smoke pressure changing point is set as the time interval delta T, can be obtained from the smoke pressure sequence corresponding to the j-th smoke pressure measuring point. Alternatively, the set time interval may be 30min, 40min, 1h, 1.5h, etc., but is not limited thereto. The acquisition time corresponding to the first smoke pressure data can be expressed as follows:
Further, a smoke pressure sequence with the acquisition time in the acquisition time period of the specified smoke pressure data and the first smoke pressure data can be selected from the smoke pressure sequence corresponding to the j-th smoke pressure measuring point to be used as a normal sample interval of the smoke pressure sequence corresponding to the j-th smoke pressure measuring point; the acquisition time of the specified smoke pressure data is located before the first smoke pressure data. Optionally, the specified smoke pressure data may be the earliest smoke pressure data collected in the smoke pressure sequence corresponding to the j-th smoke pressure measuring point, that is, the smoke pressure data corresponding to the collection time lower bound t l. Correspondingly, the normal sample interval is a smoke pressure sequence with the acquisition time being in [ t l,te ].
In the embodiment of the application, the normal sample interval and the abnormal sample interval of the smoke pressure sequence corresponding to each smoke pressure measuring point are divided, an off-line variable point detection algorithm is adopted, no manual experience is relied, the accuracy of sample interval division is improved, and the accuracy of subsequent leakage positioning based on smoke pressure data in the normal sample interval and the abnormal sample interval is further facilitated.
Further, the monitoring node 13 may calculate the abnormality index of each smoke pressure measurement point by using the smoke pressure in the normal sample section and the smoke pressure in the abnormal sample section corresponding to the smoke pressure measurement point.
Optionally, for the jth smoke pressure measuring point, the monitoring node 13 may calculate at least one characteristic parameter value of the jth smoke pressure measuring point by using the smoke pressure in the normal sample interval and the smoke pressure in the abnormal sample interval corresponding to the jth smoke pressure measuring point; and carrying out weighted summation on at least one characteristic parameter value of the jth smoke pressure measuring point to obtain an abnormality index of the jth smoke pressure measuring point.
In the embodiment of the application, the monitoring node calculates at least one characteristic parameter value of the jth smoke pressure measuring point by executing at least one of the following calculation modes:
calculation mode 1: and calculating the relative change proportion of the root mean square of the smoke pressure of the normal sample interval corresponding to the j smoke pressure measuring point and the smoke pressure of the abnormal sample interval.
The data length of an abnormal sample interval of the jth smoke pressure measuring point is assumed to be M; the normal sample interval length is N. The mean value of the abnormal samples of the j-th smoke pressure measuring point is as follows:
The mean value of the normal samples is:
further, the relative variation ratio of the root mean square of the smoke pressure of the normal sample section and the smoke pressure of the abnormal sample section corresponding to the jth smoke pressure measuring point can be expressed as:
Calculation mode 2: and calculating the standard deviation variation of the smoke pressure of the normal sample interval and the smoke pressure of the abnormal sample interval corresponding to the j-th smoke pressure measuring point. Wherein, the standard deviation variation can be calculated using the following formula (11):
calculation method 3: and calculating the dynamic time warping (DYNAMIC TIME WARPING, DTW) distance between the smoke pressure of the normal sample interval corresponding to the j-th smoke pressure measuring point and the smoke pressure of the abnormal sample interval.
The calculation principle of the DTW distance is as follows:
Two time sequences q= [ Q 1,q2,…,qn ] and c= [ C 1,c2,…,cm ], the lengths of which are n and m, respectively; the DTW distance is calculated as follows:
1) The first step: a matrix D of size n x m is constructed, matrix element D ij=dist(qi,cj), where dist represents the distance calculation function, typically using euclidean distance.
2) And a second step of: the shortest path from D 11 to D nm is searched in matrix D by dynamic programming, and the path searching direction can be upward, rightward or obliquely upward and rightward at D ij.
3) And a third step of: the shortest path from D 11 to D nm is searched in matrix D as the similarity of the Q and C sequences.
4) The general calculation formula is as follows:
D(i,j)=dist(i,j)+min[D(i-1,j),D(i,j-1),D(i-1,k-1)] (12)
In the embodiment of the application, Q and C respectively represent the smoke pressure sequence in a normal sample interval and the smoke pressure sequence in an abnormal sample. The DTW distance between the normal sample interval and the abnormal sample interval can be calculated by the DTW distance calculation method
Calculation mode 4: and searching the smoke pressure of the abnormal sample section corresponding to the j smoke pressure measuring point to determine the smoke pressure trough of the abnormal sample section corresponding to the j smoke pressure measuring point. Wherein, the acquisition time mark corresponding to the smoke pressure wave valley is v j, and v j satisfies the following formula:
If there is no characteristic valley v j satisfying the constraint of the above formula (13), v j is defined as the f j (t) interval The position of the inner minimum:
Further, the relative variation of the maximum smoke pressure peak value and the smoke pressure trough in the abnormal sample interval corresponding to the j-th smoke pressure measuring point can be calculated. The calculation formula can be expressed as:
calculation mode 5: and determining the smoke pressure of the boiler after the acquisition time is in leakage from the smoke pressure sequence corresponding to the jth smoke pressure measuring point, wherein the smoke pressure exceeds the target smoke pressure of the smoke pressure average value set proportion of the normal sample interval corresponding to the jth smoke pressure measuring point. The set ratio may be 90%, 100%, or the like, but is not limited thereto. Further, the time interval between the acquisition time of the minimum value of the target smoke pressure and the occurrence of leakage of the boiler can be calculated and used as the response time of the j-th smoke pressure measuring point to the leakage of the boiler. The calculation formula can be expressed as:
The expression (16) is shown as 100% only, but is not limited thereto.
Calculation mode 6: calculating the time interval between the leakage of the smoke pressure sequence corresponding to the jth smoke pressure measuring point from the boiler to the maximum smoke pressure peak value in the abnormal sample interval corresponding to the jth smoke pressure measuring point, wherein the calculation formula can be expressed as follows:
wherein mu 1 represents the time when the boiler leaks.
In the calculation mode 6, the acquisition time of the change point detected by the monitoring node 13 on line for the first time before the shutdown maintenance can be used as the boiler leakage time. Or the monitoring node 13 can also acquire a liquid loss amount sequence which is in the same acquisition time period as a smoke pressure sequence acquired by a pressure gauge of a plurality of smoke pressure measuring points. Optionally, the liquid loss sequence may be downsampled and smoothed, where the downsampling and smoothing process may be described in the context of the above embodiments and is not described herein. Wherein the sequence of liquid loss after the downsampling and smoothing process can be expressed as:
g(tl:tstop)={g(tl),g(tl+1),...g(ti),g(ti+1),...g(tstop)} (18)
In the equation (18), the present time is only taken as an example of the boiler shutdown maintenance time, but the present invention is not limited thereto.
Further, the liquid loss sequence may be subjected to a change point detection to determine a change point in the liquid loss sequence, where the change point in the liquid loss sequence is: mu 1:m=(μ1,μ2,…μm). Where m represents the total number of change points in the fluid loss sequence. Alternatively, a PELT algorithm may be used to perform a change point detection on the fluid loss sequence to determine a change point in the fluid loss sequence. In this embodiment, the time series y 1:n in the above formulas (2), (3) and (4) is a liquid loss series. The change point detection is performed by the PELT algorithm as off-line change point detection, so that the accuracy of the change point detection is improved.
Further, the acquisition time of the variable point with the earliest acquisition time among the variable points in the liquid loss sequence can be used as the time for the boiler to leak.
Further, the abnormality index of the at least one characteristic parameter value of the jth smoke pressure measurement point may be determined according to a ranking of the at least one characteristic parameter value of the jth smoke pressure measurement point among the characteristic parameters of the same attribute of the plurality of smoke pressure measurement points. For example, for the characteristic parameter values of the smoke pressure measurement points calculated in the calculation modes 1 to 4 J=1, 2, … k, k represents the total number of smoke pressure points, for these 4 characteristic parameters, the larger the characteristic parameter value of the same attribute, the higher the abnormality index. Correspondingly, for any characteristic parameter value in the calculation of the calculation modes 1-4, the characteristic parameter values of the k smoke pressure measuring points can be sequenced from small to large, and the occupation of the smoke pressure measuring points in the sequencing is used as the abnormality index of the smoke pressure measuring points. For example, the abnormality index of the characteristic parameter value of the smoke pressure measurement point having the largest characteristic parameter value may be assigned k, the abnormality index of the characteristic parameter value of the smoke pressure measurement point having the smallest characteristic parameter value may be assigned 1, and so on. For example, the characteristic parameter value/>, calculated for the smoke pressure measurement point in calculation mode 1According toThe size of the (2) is used for sequencing k smoke pressure measuring points, wherein the smoke pressure measuring points areThe bigger the rank is, the earlier is the/>, of the smoke pressure measuring pointThe greater the abnormality index. According to the above mode, the characteristic parameter value/>, calculated in the calculation modes 1-4, of the j-th smoke pressure measuring point is obtainedThe anomaly indexes of (2) are expressed as:
for another example, the characteristic parameter values of the smoke pressure measurement points calculated in the calculation modes 5 and 6 J=1, 2, … k, k represents the total number of smoke pressure points, for these 2 characteristic parameters, the larger the characteristic parameter value of the same attribute, the lower the abnormality index. Accordingly, for any characteristic parameter value in the calculation of the calculation modes 5 and 6, the characteristic parameter values of the k smoke pressure measuring points can be ranked in order from large to small, and the occupation of the smoke pressure measuring points in the ranking is used as the abnormality index of the smoke pressure measuring points. For example, the abnormality index of the characteristic parameter value of the smoke pressure measurement point having the largest characteristic parameter value may be assigned to 1, the abnormality index of the characteristic parameter value of the smoke pressure measurement point having the smallest characteristic parameter value may be assigned to k, and so on. In the above way, the characteristic parameter value/>, calculated in the calculation modes 5 and 6, of the j-th smoke pressure measuring point is obtainedThe anomaly indexes of (2) are expressed as: /(I)
Further, the abnormality index of at least one characteristic parameter value of the jth smoke pressure measuring point may be weighted and summed to obtain the abnormality index of the jth smoke pressure measuring point. The calculation formula can be expressed as:
In the embodiment of the application, the weight of each characteristic parameter can be flexibly set according to the actual situation. Optionally, ω i =1, i=1, 2, …,6. The greater the abnormality index of the smoke pressure measuring point is, the higher the risk of leakage of the smoke pressure measuring point is.
Further, according to the magnitude of the abnormality indexes of the plurality of smoke pressure measuring points, the risk sequence of leakage of the plurality of smoke pressure measuring points is determined, so that maintenance personnel can position the smoke pressure measuring points with leakage based on the risk sequence of leakage of the plurality of smoke pressure measuring points. Optionally, the monitoring node 13 may sort the plurality of smoke pressure measurement points in order from the large to the small of the abnormality indexes of the plurality of smoke pressure measurement points, so as to obtain a risk sequence of leakage of the plurality of smoke pressure measurement points.
The calculation mode of the abnormal indexes of the smoke pressure measuring points compares the smoke pressure data before and after the boiler 11 leaks, namely compares the smoke pressure data during normal operation of the boiler 11 with the smoke pressure data after the leakage occurs, makes full use of characteristic information contained in historical data, and can improve the accuracy of calculating the abnormal indexes. On the other hand, various characteristic parameters are adopted to determine the possibility of leakage of the smoke pressure measuring point, and the robustness of a leakage positioning method is improved.
Further, the monitoring node 13 may also provide the display node 14 with a risk sequence of leakage at a plurality of smoke pressure measurement points. Display node 14 may display a plurality of smoke pressure stations in the order of risk of leakage at the plurality of smoke pressure stations. The risk sequence of leakage of the smoke pressure measuring points which are arranged at the front is higher, so that maintenance staff overhauls the smoke pressure measuring points according to the risk sequence to rapidly locate the smoke pressure measuring points which are leaked.
In the embodiment of the application, the existing pressure gauge of the boiler is utilized to carry out leakage positioning on the boiler, and no additional sensor is needed, thereby being beneficial to reducing the leakage positioning cost. On the other hand, as the response time of the smoke pressure data is shorter, the characteristic parameters of the smoke pressure measuring point can be timely obtained, and the timeliness and the time sensitivity of leakage positioning can be improved.
The embodiment of the application provides a boiler besides a monitoring system. The boiler provided by the embodiment of the application is exemplified below.
The boiler provided by the embodiment comprises: a flowmeter and a monitoring module installed in the boiler. In this embodiment, a plurality of flow meters are installed in the boiler. The plural means 2 or more than 2. The plurality of flowmeters are respectively used for collecting real-time total liquid flow and real-time steam flow of the boiler. The setting position of the flowmeter and the data collecting manner can be referred to the relevant content of the above embodiment, and will not be described herein.
In this embodiment, the implementation manner of the monitoring module may be referred to the relevant content of the above system embodiment, which is not described herein. In this embodiment, the monitoring module may be provided on the boiler. In order to prevent the damage to the monitoring module caused by the environments such as high temperature and high corrosion of the boiler, the boiler can be further provided with a protection device for preventing high temperature and corrosion of the monitoring module. In this embodiment, the monitoring module is in communication with the flow meter.
In this embodiment, the monitoring module may obtain the real-time total liquid flow and the real-time steam flow collected by the flowmeter; and determining the real-time liquid loss of the boiler according to the real-time total liquid flow and the real-time steam flow. Further, the monitoring module may also obtain a historical liquid loss of the boiler. The historical liquid loss of the boiler refers to the liquid loss before the current moment, namely the liquid loss of the boiler acquired by the monitoring module before the real-time liquid loss is determined. In the embodiment of the application, the historical liquid loss of the boiler is the liquid loss in a period of time closest to the acquisition time of the real-time liquid loss.
Further, the monitoring module may perform variable point detection on the historical liquid loss and the real-time liquid loss of the boiler. In the embodiment of the application, the specific implementation mode of performing the variable point detection on the historical liquid loss amount and the real-time liquid loss amount of the boiler is not limited.
In some embodiments the monitoring module may utilize a neural network model to perform variable point detection on the historical liquid loss and the real-time liquid loss of the boiler. However, because the abnormal conditions such as leakage and the like of the boiler are small probability events, and a large number of abnormal samples are needed by the neural network model in the training stage, the abnormal liquid loss amount sample may be insufficient when the neural network model is trained, and the trained neural network model has low accuracy in variable point detection. On the other hand, because the neural network model has a complex structure and large calculation amount, the variable point detection efficiency is low, and the boiler leakage real-time detection sensitivity is low.
To address the above, in some embodiments, the monitoring module may employ probabilistic statistical methods for spot-changing detection of historical and real-time liquid loss amounts from the boiler. Specifically, the monitoring module can adopt a probability statistical method to detect the change point of the historical liquid loss amount and the real-time liquid loss amount of the boiler so as to judge whether the real-time liquid loss amount is the change point or not. The method comprises the steps of detecting the change point of the historical liquid loss and the real-time liquid loss of the boiler by using a probability statistical method, and is beneficial to improving the accuracy of the change point detection without a large number of abnormal samples. On the other hand, the probability statistical method is used for detecting the variable points, a large number of variable point interfaces do not need to be accumulated for detecting the variable points, the boiler leakage can be detected timely, and the sensitivity of the real-time detection of the boiler leakage is improved.
Alternatively, a Bayesian variable point detection algorithm can be employed to perform variable point detection on the historical liquid loss amount and the real-time liquid loss amount of the boiler. Accordingly, the monitoring module can utilize a Bayesian variable point detection model to perform variable point detection on the historical liquid loss and the real-time liquid loss of the monitoring module. Regarding the principle of the bayesian variable point detection algorithm and the specific implementation manner of performing variable point detection on the historical liquid loss and the real-time liquid loss of the monitoring module by using the bayesian variable point detection model, reference may be made to the relevant content of the above system embodiment, which is not described herein again.
In some embodiments, the sampling period of the flow meter is shorter and the corresponding time span of the historical fluid loss is longer, resulting in a greater data volume for the historical fluid loss. To improve the efficiency of the change point detection, the historical liquid loss may be downsampled. Accordingly, the monitoring module may downsample the historical liquid loss of the boiler according to the set second sampling period T 2. Wherein the second sampling period T 2 is greater than the first sampling period T 1,T2>T1. The value of the second sampling period T 2 can be referred to the related content of the above embodiment, and will not be described again.
Further, the monitoring module can adopt a probability statistical method to detect the change points of the historical liquid loss and the real-time liquid loss after the downsampling. Optionally, to avoid noise interference in the fluid loss amount, the downsampled historical fluid loss amount and the real-time fluid loss amount may be smoothed to obtain the smoothed historical fluid loss amount and the smoothed real-time fluid loss amount.
Alternatively, the downsampled historical fluid loss and real-time fluid loss may be smoothed using an exponentially weighted moving window function. For specific calculation formulas, reference may be made to the system embodiments described above.
Further, the monitoring module can adopt a probability statistical method to detect the change point of the historical liquid loss after the smoothing treatment and the real-time liquid loss after the smoothing treatment. Optionally, a bayesian variable point detection algorithm may be used to perform variable point detection on the historical liquid loss after the smoothing process and the real-time liquid loss after the smoothing process, and in the specific embodiment, reference may be made to the above related content of performing variable point detection on the historical liquid loss and the real-time liquid loss by using a bayesian variable point detection model, which is not described herein again.
Further, the monitoring module can determine the health condition of the current boiler according to the variable point detection result. Optionally, if the change point detection result is that the real-time liquid loss amount is the change point, determining that the liquid leakage occurs in the current boiler.
Furthermore, in order to enable the technician to intuitively know the health condition of the boiler, a display module can be further arranged on the boiler. For the implementation manner of the display module, refer to the relevant content of the display node in the above system embodiment, which is not described herein again. In order to prevent the damage to the monitoring module caused by the environments such as high temperature and high corrosion of the boiler, the boiler can be further provided with a protection device for preventing the monitoring module from high temperature, corrosion and dust.
In this embodiment, the display module and the monitoring module may be located in the same physical machine or may be located in different physical machines. The communication manner between the physical machines can be referred to the relevant content of the above system embodiment, and will not be described herein.
Accordingly, the monitoring module may provide the current health of the boiler to the display module. The display module can display the current health status of the boiler. For the specific implementation of the display module displaying the current health status of the boiler, reference may be made to the relevant content of the above system embodiment, which is not described herein.
In still other embodiments, the monitoring module may also output leakage alarm information in the event of a leak in the current boiler. For a specific implementation manner of outputting the leakage alarm information by the monitoring module, reference may be made to the relevant content of the above system embodiment, which is not described herein.
In some embodiments, the monitoring module may also calculate a loss rate of the real-time liquid loss amount of the boiler; and provides the loss rate of the real-time liquid loss amount of the boiler to the display module. Accordingly, the display module can display the loss speed of the real-time liquid loss amount of the boiler, so that technicians can intuitively know the loss speed of the real-time liquid loss amount of the boiler, and reference information can be provided for the technicians to judge whether the boiler leaks or not.
In other embodiments, the boiler may further include: a liquid level gauge disposed within the boiler; the level gauge may be used to collect the level of the boiler.
Aiming at the monitoring module, the water inlet of the boiler can be controlled to be opened under the condition that the liquid level of the boiler is lower than a set first liquid level threshold value; and controlling the water inlet of the boiler to be closed under the condition that the liquid level of the boiler reaches a set second liquid level threshold value; wherein the second liquid level threshold is greater than the first liquid level threshold.
And/or the monitoring module can output water shortage prompt information under the condition that the liquid level of the boiler is lower than a set first liquid level threshold value so as to prompt a manager of the boiler to supplement water; outputting full liquid level prompt information to prompt a manager of the boiler to stop water supplementing under the condition that the liquid level of the boiler reaches a set second liquid level threshold value; etc.
In the embodiment of the application, the display module displays the real-time health condition of the boiler, so that technicians can intuitively know the real-time health condition of the boiler, and the timeliness of overhaul is improved. Alternatively, the technician may decide on downtime for maintenance based on the amount of real-time fluid loss.
In order to improve maintenance efficiency, the monitoring system provided by the embodiment of the application can also be used for positioning leakage. In the embodiment of the application, in order to reduce the leakage positioning cost, a plurality of existing pressure gauges in the boiler can be used for leakage positioning. The plural means 2 or more than 2. For a description of the distribution positions of the plurality of pressure gauges, reference may be made to the relevant content of the above system embodiments, and the description thereof will not be repeated here.
In the embodiment of the application, the monitoring module can acquire the smoke pressure sequence acquired by the pressure gauges of a plurality of smoke pressure measuring points before the boiler is maintained under the condition that the liquid leakage occurs in the boiler. Alternatively, the monitoring module may determine that there is a liquid leak from the boiler if the change point is monitored as described above. The monitoring module can acquire the smoke pressure sequences acquired by the pressure gauges of a plurality of smoke pressure measuring points in a set time period before the current moment under the condition that liquid leakage occurs in the boiler. The current time is any time before shutdown maintenance. The sequence of smoke pressures over the set time period may include: the smoke pressure data before the liquid leakage of the boiler and the smoke pressure data after the liquid leakage of the boiler occur. The set time period can be flexibly determined according to the time interval of the liquid leakage from the boiler at the current moment.
Optionally, the monitoring module may periodically schedule the smoke pressure sequences collected in real time by the pressure gauges of the smoke pressure measuring points according to a set scheduling period, and perform leakage positioning by using the smoke pressure sequences scheduled by the current scheduling period until the machine is stopped for maintenance. The smoke pressure sequence scheduled by the leakage positioning model in each scheduling period can comprise: the pressure gauges of the smoke pressure measuring points collect smoke pressure sequences in the current dispatching cycle and set smoke pressure sequences in a time period before the current dispatching cycle.
Further, the monitoring module can respectively detect the change points of the smoke pressure sequences acquired by the pressure gauges of the scheduled smoke pressure measuring points so as to determine the smoke pressure change points in the smoke pressure sequences acquired by the pressure gauges of each smoke pressure measuring point. For a specific implementation manner of performing variable point detection on the smoke pressure sequences acquired by the pressure gauges of the scheduled multiple smoke pressure measurement points, reference may be made to the relevant content of the above system embodiment, which is not described herein again.
Further, the monitoring module can determine a normal sample interval and an abnormal sample interval of the smoke pressure sequence corresponding to each smoke pressure measuring point based on smoke pressure change points in the smoke pressure sequence acquired by the pressure gauge of the smoke pressure measuring point. For the specific implementation of determining the normal sample interval and the abnormal sample interval of the smoke pressure sequence, reference may be made to the relevant content of the above system embodiment, which is not described herein.
In the embodiment of the application, the normal sample interval and the abnormal sample interval of the smoke pressure sequence corresponding to each smoke pressure measuring point are divided, an off-line variable point detection algorithm is adopted, no manual experience is relied, the accuracy of sample interval division is improved, and the accuracy of subsequent leakage positioning based on smoke pressure data in the normal sample interval and the abnormal sample interval is further facilitated.
Further, the monitoring module can calculate the abnormality index of each smoke pressure measuring point by using the smoke pressure in the normal sample interval and the smoke pressure in the abnormal sample interval corresponding to each smoke pressure measuring point.
Optionally, for the jth smoke pressure measuring point, the monitoring module may calculate at least one characteristic parameter value of the jth smoke pressure measuring point by using the smoke pressure in the normal sample interval and the smoke pressure in the abnormal sample interval corresponding to the jth smoke pressure measuring point; and carrying out weighted summation on at least one characteristic parameter value of the jth smoke pressure measuring point to obtain an abnormality index of the jth smoke pressure measuring point.
In the embodiment of the present application, the specific implementation manner of the monitoring module in calculating the at least one characteristic parameter value of the jth smoke pressure measuring point may be referred to the above calculation manners 1-6, which are not described herein again.
Further, the liquid loss sequence may be subjected to a change point detection to determine a change point in the liquid loss sequence, where the change point in the liquid loss sequence is: mu 1:m=(μ1,μ2,…μm). Where m represents the total number of change points in the fluid loss sequence. Alternatively, a PELT algorithm may be used to perform a change point detection on the fluid loss sequence to determine a change point in the fluid loss sequence. The change point detection is performed by the PELT algorithm as off-line change point detection, so that the accuracy of the change point detection is improved.
Further, the acquisition time of the variable point with the earliest acquisition time among the variable points in the liquid loss sequence can be used as the time for the boiler to leak.
Further, the abnormality index of the at least one characteristic parameter value of the jth smoke pressure measurement point may be determined according to a ranking of the at least one characteristic parameter value of the jth smoke pressure measurement point among the characteristic parameters of the same attribute of the plurality of smoke pressure measurement points. Further, the abnormality index of at least one characteristic parameter value of the jth smoke pressure measuring point may be weighted and summed to obtain the abnormality index of the jth smoke pressure measuring point. In the embodiment of the application, the weight of each characteristic parameter can be flexibly set according to the actual situation. The greater the abnormality index of the smoke pressure measuring point is, the higher the risk of leakage of the smoke pressure measuring point is.
Further, according to the magnitude of the abnormality indexes of the plurality of smoke pressure measuring points, the risk sequence of leakage of the plurality of smoke pressure measuring points can be determined, so that maintenance personnel can position the smoke pressure measuring points with leakage based on the risk sequence of leakage of the plurality of smoke pressure measuring points. Optionally, the monitoring module may sort the plurality of smoke pressure measurement points according to the order of the abnormality indexes of the plurality of smoke pressure measurement points from large to small, so as to obtain a risk order of leakage of the plurality of smoke pressure measurement points.
The calculation mode of the abnormal indexes of the smoke pressure measuring points compares the smoke pressure data before and after boiler leakage, namely compares the smoke pressure data during normal operation of the boiler with the smoke pressure data after leakage, fully utilizes the characteristic information contained in the historical data, and can improve the accuracy of abnormal index calculation. On the other hand, various characteristic parameters are adopted to determine the possibility of leakage of the smoke pressure measuring point, and the robustness of a leakage positioning method is improved.
Further, the monitoring module can also provide the risk sequence of leakage of a plurality of smoke pressure measuring points to the display module. The display module can display the plurality of smoke pressure measuring points according to the risk sequence of leakage of the plurality of smoke pressure measuring points. The risk sequence of leakage of the smoke pressure measuring points which are arranged at the front is higher, so that maintenance staff overhauls the smoke pressure measuring points according to the risk sequence to rapidly locate the smoke pressure measuring points which are leaked.
In the embodiment of the application, the existing pressure gauge of the boiler is utilized to carry out leakage positioning on the boiler, and no additional sensor is needed, thereby being beneficial to reducing the leakage positioning cost. On the other hand, as the response time of the smoke pressure data is shorter, the characteristic parameters of the smoke pressure measuring point can be timely obtained, and the timeliness and the time sensitivity of leakage positioning can be improved.
In addition to the monitoring system and boiler described above, embodiments of the present application provide a monitoring method and a leak location method, which are exemplified below in connection with specific embodiments.
Fig. 2 is a schematic flow chart of a monitoring method according to an embodiment of the present application. As shown in fig. 2, the method includes:
201. and acquiring the real-time total liquid flow and the real-time steam flow of the boiler.
202. And determining the real-time liquid loss of the boiler according to the real-time total liquid flow and the real-time steam flow.
203. And detecting the change point of the historical liquid loss and the real-time liquid loss of the boiler.
204. And determining the health condition of the current boiler according to the change point detection result.
In the present embodiment, a plurality of flow meters are installed in the boiler. The plural means 2 or more than 2. The plurality of flowmeters are respectively used for collecting real-time total liquid flow and real-time steam flow of the boiler. Alternatively, the plurality of flow meters may periodically collect the real-time total liquid flow and the real-time steam flow of the boiler at a set sampling period T 1. For T 1, reference may be made to relevant contents of the system embodiment, and details are not repeated here. Accordingly, for the monitoring device, in step 201, a real-time total liquid flow and a real-time steam flow of the boiler may be acquired.
In step 202, a real-time liquid loss amount of the boiler may be determined based on the real-time total liquid flow and the real-time steam flow. Further, the historical liquid loss of the boiler may also be obtained. For a description of the historical liquid loss, reference may be made to the relevant content of the above system embodiment, and the description thereof will not be repeated here.
Further, in step 203, a change point detection may be performed on the historical liquid loss amount and the real-time liquid loss amount of the boiler. In the present embodiment, the specific embodiment of performing the change point detection of the historic liquid loss amount and the real-time liquid loss amount of the boiler is not limited.
Optionally, an alternative embodiment of step 203 is: the neural network model can be utilized to detect the change points of the historical liquid loss and the real-time liquid loss of the boiler. However, because the abnormal conditions such as leakage and the like of the boiler are small probability events, and a large number of abnormal samples are needed by the neural network model in the training stage, the abnormal liquid loss amount sample may be insufficient when the neural network model is trained, and the trained neural network model has low accuracy in variable point detection. On the other hand, because the neural network model has a complex structure and large calculation amount, the variable point detection efficiency is low, and the boiler leakage real-time detection sensitivity is low.
To address the above, in some embodiments, a probabilistic statistical method may be employed to perform variable point detection on the historical and real-time liquid loss amounts of the boiler. Specifically, the probability statistical method can be adopted to detect the change point of the historical liquid loss amount and the real-time liquid loss amount of the boiler so as to judge whether the real-time liquid loss amount is the change point. The method comprises the steps of detecting the change point of the historical liquid loss and the real-time liquid loss of the boiler by using a probability statistical method, and is beneficial to improving the accuracy of the change point detection without a large number of abnormal samples. On the other hand, the probability statistical method is used for detecting the variable points, a large number of variable point interfaces do not need to be accumulated for detecting the variable points, the boiler leakage can be detected timely, and the sensitivity of the real-time detection of the boiler leakage is improved.
Alternatively, a Bayesian variable point detection algorithm can be employed to perform variable point detection on the historical liquid loss amount and the real-time liquid loss amount of the boiler. Accordingly, a Bayesian variable point detection model can be utilized to perform variable point detection on the historical liquid loss amount and the real-time liquid loss amount of the boiler. The principle of bayesian variational point detection can be referred to in the related content of the above system embodiment, and will not be described herein.
The current methods for leakage warning mostly rely on the selection of threshold values, such as setting a temperature threshold value in the above-mentioned mode 1 and setting a sound wave threshold value in the mode 2. The threshold value is selected to be too small, the leakage of the boiler can be found after the boiler leaks and accumulates for a period of time, the leakage is easy, and the proper overhaul time can be missed; and too large a threshold value is easy to generate false alarms, and too many false alarms can lose the value of the early warning. And the selection of the threshold depends on engineering experience, different thresholds are set according to different equipment requirements, and the early warning system is difficult to obtain better generalization capability and difficult to use in different scenes, so that the popularization of the technology is limited.
The Bayesian variable point detection algorithm is based on the characteristic that data among variable points are independent and distributed, and a probability threshold value is set, so that different thresholds are not required to be set for different equipment, the Bayesian variable point detection algorithm can be applied to various boiler scenes, and the technical popularization of an early warning method is facilitated. On the other hand, the Bayesian variable point detection algorithm can accurately detect the variable point only by accumulating a small number of sample points after the variable point actually appears in the boiler, thereby being beneficial to improving the timeliness and the sensitivity of boiler leakage detection and playing a role in early warning. Moreover, the algorithm can detect other types of inflection points except for the step, and can capture small changes of water loss data distribution tens of days before pipe explosion.
Accordingly, the historical liquid loss and the real-time liquid loss of the boiler can be input into a Bayesian variable point detection model; in the Bayesian variable point detection model, the historical liquid loss and the real-time liquid loss of the boiler can be utilized to calculate the probability that the real-time liquid loss is a variable point; and determining whether the real-time liquid loss is the change point according to the probability that the real-time liquid loss is the change point. Optionally, if the probability that the real-time liquid loss amount is the change point is greater than the set probability threshold θ, determining that the real-time liquid loss amount is the change point.
In some embodiments, the sampling period of the flow meter is shorter and the corresponding time span of the historical fluid loss is longer, resulting in a greater data volume for the historical fluid loss. To improve the efficiency of the change point detection, the historical liquid loss may be downsampled. Accordingly, the historical liquid loss amount of the boiler can be downsampled according to the set sampling period T 2. For convenience of description and distinction, in the embodiment of the present application, a sampling period of the flow meter is defined as a first sampling period T 1, and a sampling period employed for downsampling is defined as a second sampling period T 2. Wherein the second sampling period T 2 is greater than the first sampling period T 1,T2>T1. The value of the second sampling period T 2 can be referred to the related content of the above embodiment, and will not be described again.
Further, a probability statistical method can be adopted to detect the change points of the historical liquid loss and the real-time liquid loss after the downsampling. Optionally, to avoid noise interference in the fluid loss amount, the downsampled historical fluid loss amount and the real-time fluid loss amount may be smoothed to obtain the smoothed historical fluid loss amount and the smoothed real-time fluid loss amount.
Alternatively, the downsampled historical fluid loss and real-time fluid loss may be smoothed using an exponentially weighted moving window function. For specific calculation formulas, reference may be made to the system embodiments described above.
Further, the probability statistical method can be adopted to detect the change point of the historical liquid loss after the smoothing treatment and the real-time liquid loss after the smoothing treatment. Optionally, a bayesian variable point detection algorithm may be used to perform variable point detection on the historical liquid loss after the smoothing process and the real-time liquid loss after the smoothing process, and in the specific embodiment, reference may be made to the above related content of performing variable point detection on the historical liquid loss and the real-time liquid loss by using a bayesian variable point detection model, which is not described herein again.
Further, in step 204, the current boiler health may be determined based on the change point detection. Optionally, if the change point detection result is that the real-time liquid loss amount is the change point, determining that the liquid leakage occurs in the current boiler.
Further, in order for the technician to intuitively understand the health status of the boiler, the current health status of the boiler may also be displayed. In the embodiment of the application, the specific format and information for displaying the health condition of the current boiler are not limited. In one embodiment, a data sign reflecting the change in the health of the boiler over time may be displayed. Alternatively, the data sign reflecting the relationship of the health of the boiler over time may be expressed as: and a data signboard reflecting the change relation of the real-time liquid loss quantity of the boiler with time, and displaying the change point in the data signboard in a set display format under the condition that the change point exists. In other embodiments, the data signs reflecting the changing relationship of the health condition of the boiler over time may be graphical signs or list signs, or the like.
Or the health condition of the current boiler can be provided for the corresponding display node of the boiler for display. The display node displays the description of the current health condition of the boiler, which can be referred to the relevant content of the system embodiment, and will not be described herein.
In still other embodiments, a leak alert message may also be output in the event of a leak in the current boiler. For the specific implementation of outputting the leakage alarm information, reference may be made to the relevant content of the foregoing embodiments, which are not repeated here.
In some embodiments, the loss rate of the real-time liquid loss amount of the boiler may also be calculated; and the loss speed of the real-time liquid loss of the boiler is displayed, so that a technician can intuitively know the loss speed of the real-time liquid loss of the boiler, and can provide reference information for the technician to judge whether the boiler leaks or not.
In other embodiments, the boiler may further include: a liquid level gauge disposed within the boiler; the level gauge may be used to collect the level of the boiler. Correspondingly, the water inlet of the boiler can be controlled to be opened under the condition that the liquid level of the boiler is lower than a set first liquid level threshold value; and controlling the water inlet of the boiler to be closed under the condition that the liquid level of the boiler reaches a set second liquid level threshold value; wherein the second liquid level threshold is greater than the first liquid level threshold.
And/or outputting water shortage prompt information to prompt a manager of the boiler to supplement water under the condition that the liquid level of the boiler is lower than a set first liquid level threshold value; outputting full liquid level prompt information to prompt a manager of the boiler to stop water supplementing under the condition that the liquid level of the boiler reaches a set second liquid level threshold value; etc.
In the embodiment of the application, the real-time health condition of the boiler can be displayed, so that technicians can intuitively know the real-time health condition of the boiler, and the timeliness of overhaul is improved. Alternatively, the technician may decide on downtime for maintenance based on the amount of real-time fluid loss.
In order to improve maintenance efficiency, the monitoring system provided by the embodiment of the application can also be used for positioning leakage. In the embodiment of the application, in order to reduce the leakage positioning cost, a plurality of existing pressure gauges in the boiler can be used for leakage positioning. The plural means 2 or more than 2. For a description of the distribution positions of the plurality of pressure gauges, reference may be made to the relevant content of the above system embodiments, and the description thereof will not be repeated here. The leak locating method provided by the embodiment of the application is exemplified below.
Fig. 3 is a flow chart of a leak positioning method according to an embodiment of the present application. As shown in fig. 3, the method includes:
301. In the case of a liquid leak in the boiler, a sequence of smoke pressures acquired by a pressure gauge distributed over a plurality of smoke pressure stations within the boiler prior to boiler repair is acquired.
The smoke pressure sequence that the manometer of a plurality of smoke pressure measurement stations gathered includes: and the smoke pressure data before and after the liquid leakage of the boiler are collected by the pressure gauges of the smoke pressure measuring points.
302. And respectively performing variable point detection on the smoke pressure sequences acquired by the pressure gauges of the smoke pressure measuring points so as to determine smoke pressure variable points in the smoke pressure sequences acquired by the pressure gauges of each smoke pressure measuring point.
303. And determining a normal sample interval and an abnormal sample interval of the smoke pressure sequence corresponding to each smoke pressure measuring point based on the smoke pressure change point in the smoke pressure sequence acquired by the pressure gauge of each smoke pressure measuring point.
304. And calculating the abnormality index of each smoke pressure measuring point by using the smoke pressure in the normal sample interval and the smoke pressure in the abnormal sample interval corresponding to each smoke pressure measuring point.
305. And determining the risk sequence of leakage of the plurality of smoke pressure measuring points according to the magnitude of the abnormality indexes of the plurality of smoke pressure measuring points so as to enable maintenance personnel to perform leakage positioning based on the risk sequence.
In the embodiment of the present application, in step 301, in the case of a liquid leakage of the boiler, a sequence of smoke pressures acquired by a pressure gauge for a plurality of smoke pressure measuring points before the boiler is maintained may be acquired. The smoke pressure sequence that the manometer of a plurality of smoke pressure measurement stations gathered includes: and the smoke pressure data before and after the liquid leakage of the boiler are collected by the pressure gauges of the smoke pressure measuring points.
Alternatively, it may be determined that there is a liquid leak in the boiler in the case where the change point is monitored as described above. Under the condition that liquid leakage occurs in the boiler, a smoke pressure sequence acquired by a pressure gauge with a plurality of smoke pressure measuring points in a set time period before the current moment can be acquired. The current time is any time before shutdown maintenance. The sequence of smoke pressures over the set time period may include: the smoke pressure data before the liquid leakage of the boiler and the smoke pressure data after the liquid leakage of the boiler occur. The set time period can be flexibly determined according to the time interval of the liquid leakage from the boiler at the current moment.
Optionally, according to a set scheduling period, periodically scheduling a smoke pressure sequence acquired by the pressure gauges of a plurality of smoke pressure measuring points in real time, and performing leakage positioning by utilizing the smoke pressure sequence scheduled by the current scheduling period until the machine is stopped for maintenance. The smoke pressure sequence scheduled by the leakage positioning model in each scheduling period can comprise: the pressure gauges of the smoke pressure measuring points collect smoke pressure sequences in the current dispatching cycle and set smoke pressure sequences in a time period before the current dispatching cycle. Further, in step 302, a pressure sequence collected by pressure gauges of the scheduled plurality of pressure measurement points may be separately subjected to a change point detection to determine a pressure change point in the pressure sequence collected by pressure gauges of each pressure measurement point.
The method for detecting the change point of the smoke pressure sequence corresponding to each smoke pressure measuring point is the same. The j-th smoke pressure measuring point is taken as an example and is exemplified below. Where j=1, 2,..k, k represents the total number of smoke pressure points. The j-th smoke pressure measuring point is any smoke pressure measuring point in the plurality of smoke pressure measuring points.
And aiming at the jth smoke pressure measuring point, detecting the smoke pressure sequence of the jth smoke pressure measuring point which is scheduled by the current calling period by using a PELT algorithm so as to determine the smoke pressure change point of the jth smoke pressure measuring point corresponding to the smoke pressure sequence. The smoke pressure measuring point is any smoke pressure measuring point in a plurality of smoke pressure measuring points. The smoke pressure sequence corresponding to the jth smoke pressure measuring point can be the smoke pressure sequence acquired by a pressure gauge installed at the jth smoke pressure measuring point in the current scheduling period. See above for relevant aspects of system embodiments for the principles of the PELT algorithm.
In the embodiment of the application, in order to reduce the calculated amount and improve the positioning efficiency, the smoke pressure data in the current calling period can be downsampled. Optionally, the smoke pressure sequence corresponding to each smoke pressure measuring point in the current scheduling period may be downsampled according to the third sampling period T 3. In this embodiment, the third sampling period is less than the sampling period of the pressure gauge. Optionally, further, to avoid noise interference in the downsampled smoke pressure sequence, the downsampled smoke pressure sequence may be smoothed to obtain a smoothed smoke pressure sequence. It should be noted that, the following smoke pressure sequences corresponding to the smoke pressure measuring points may be smoke pressure sequences after the downsampling and smoothing process, or may be smoke pressure sequences without the downsampling and smoothing process.
Further, in step 303, a normal sample interval and an abnormal sample interval of the smoke pressure sequence corresponding to each smoke pressure measurement point may be determined based on the smoke pressure change point in the smoke pressure sequence acquired by the pressure gauge of the smoke pressure measurement point. In the following, a specific embodiment of determining a normal sample section and an abnormal sample section of a smoke pressure sequence will be described by taking a j-th smoke pressure measurement point as an example.
Optionally, a peak may be found for the smoke pressure sequence corresponding to the jth smoke pressure measurement point, so as to determine a smoke pressure peak in the smoke pressure sequence corresponding to the jth smoke pressure measurement point. Further, the maximum smoke pressure peak value can be determined from the smoke pressure peak value in the smoke pressure sequence corresponding to the j-th smoke pressure measuring point, and the first smoke pressure changing point and the second smoke pressure changing point, the acquisition time of which is adjacent to the acquisition time corresponding to the maximum smoke pressure peak value, are acquired from the smoke pressure changing points in the smoke pressure sequence corresponding to the j-th smoke pressure measuring point. Further, the smoke pressure collected in the collection time period from the first smoke pressure change point to the second smoke pressure change point can be obtained from the smoke pressure sequence corresponding to the j-th smoke pressure measurement point and used as an abnormal sample section of the smoke pressure sequence corresponding to the j-th smoke pressure measurement point. Further, from the smoke pressure sequence corresponding to the j-th smoke pressure measuring point, first smoke pressure data, the acquisition time of which is located before the first smoke pressure changing point and the time interval between the acquisition time and the first smoke pressure changing point is set as the time interval delta T, can be obtained from the smoke pressure sequence corresponding to the j-th smoke pressure measuring point. Further, a smoke pressure sequence with the acquisition time in the acquisition time period of the specified smoke pressure data and the first smoke pressure data can be selected from the smoke pressure sequence corresponding to the j-th smoke pressure measuring point to be used as a normal sample interval of the smoke pressure sequence corresponding to the j-th smoke pressure measuring point; the acquisition time of the specified smoke pressure data is located before the first smoke pressure data. Optionally, the specified smoke pressure data may be the earliest smoke pressure data collected in the smoke pressure sequence corresponding to the j-th smoke pressure measuring point, that is, the smoke pressure data corresponding to the collection time lower bound t l. Correspondingly, the normal sample interval is a smoke pressure sequence with the acquisition time being in [ t l,te ].
In the embodiment of the application, the normal sample interval and the abnormal sample interval of the smoke pressure sequence corresponding to each smoke pressure measuring point are divided, an off-line variable point detection algorithm is adopted, no manual experience is relied, the accuracy of sample interval division is improved, and the accuracy of subsequent leakage positioning based on smoke pressure data in the normal sample interval and the abnormal sample interval is further facilitated.
Further, in step 304, the abnormal index of each smoke pressure measurement point may be calculated by using the smoke pressure in the normal sample interval and the smoke pressure in the abnormal sample interval corresponding to the smoke pressure measurement point.
Optionally, for the jth smoke pressure measuring point, calculating at least one characteristic parameter value of the jth smoke pressure measuring point by using the smoke pressure in the normal sample interval corresponding to the jth smoke pressure measuring point and the smoke pressure in the abnormal sample interval; and carrying out weighted summation on at least one characteristic parameter value of the jth smoke pressure measuring point to obtain an abnormality index of the jth smoke pressure measuring point.
In an embodiment of the present application, calculating the at least one characteristic parameter value of the jth smoke pressure measurement point includes performing at least one of the following calculation modes:
calculation mode 1: and calculating the relative change proportion of the root mean square of the smoke pressure of the normal sample interval corresponding to the j smoke pressure measuring point and the smoke pressure of the abnormal sample interval.
Calculation mode 2: and calculating the standard deviation variation of the smoke pressure of the normal sample interval and the smoke pressure of the abnormal sample interval corresponding to the j-th smoke pressure measuring point.
Calculation method 3: and calculating the dynamic time warping (DYNAMIC TIME WARPING, DTW) distance between the smoke pressure of the normal sample interval corresponding to the j-th smoke pressure measuring point and the smoke pressure of the abnormal sample interval.
Calculation mode 4: searching the smoke pressure of the abnormal sample section corresponding to the j-th smoke pressure measuring point to determine the smoke pressure trough of the abnormal sample section corresponding to the j-th smoke pressure measuring point; and calculating the relative variation of the maximum smoke pressure peak value and the smoke pressure trough in the abnormal sample interval corresponding to the j-th smoke pressure measuring point.
Calculation mode 5: and determining the smoke pressure of the boiler after the acquisition time is in leakage from the smoke pressure sequence corresponding to the jth smoke pressure measuring point, wherein the smoke pressure exceeds the target smoke pressure of the smoke pressure average value set proportion of the normal sample interval corresponding to the jth smoke pressure measuring point. The set ratio may be 90%, 100%, or the like, but is not limited thereto. Further, the time interval between the acquisition time of the minimum value of the target smoke pressure and the occurrence of leakage of the boiler can be calculated and used as the response time of the j-th smoke pressure measuring point to the leakage of the boiler.
Calculation mode 6: and calculating the time interval between the leakage of the smoke pressure sequence corresponding to the jth smoke pressure measuring point from the boiler and the reaching of the maximum smoke pressure peak value in the abnormal sample interval corresponding to the jth smoke pressure measuring point.
In the calculation mode 6, the acquisition time of the first online detected change point before the shutdown maintenance can be used as the boiler leakage time. Or the liquid loss sequence which is in the same acquisition time period with the smoke pressure sequence acquired by the pressure gauges of a plurality of smoke pressure measuring points can also be acquired. Optionally, the liquid loss sequence may be downsampled and smoothed, where the downsampling and smoothing process may be described in the context of the above embodiments and is not described herein.
Further, the liquid loss sequence may be subjected to a change point detection to determine a change point in the liquid loss sequence, where the change point in the liquid loss sequence is: mu 1:m=(μ1,μ2,…μm). Where m represents the total number of change points in the fluid loss sequence. Alternatively, a PELT algorithm may be used to perform a change point detection on the fluid loss sequence to determine a change point in the fluid loss sequence. In this embodiment, the time series y 1:n in the above formulas (2), (3) and (4) is a liquid loss series. The change point detection is performed by the PELT algorithm as off-line change point detection, so that the accuracy of the change point detection is improved.
Further, the acquisition time of the variable point with the earliest acquisition time among the variable points in the liquid loss sequence can be used as the time for the boiler to leak.
Further, according to the sequence of at least one characteristic parameter value of the jth smoke pressure measuring point in the characteristic parameters of the same attribute of the smoke pressure measuring points, determining an abnormality index of at least one characteristic parameter value of the jth smoke pressure measuring point; and carrying out weighted summation on the abnormality indexes of at least one characteristic parameter value of the jth smoke pressure measuring point to obtain the abnormality index of the jth smoke pressure measuring point.
In the embodiment of the application, the weight of each characteristic parameter can be flexibly set according to the actual situation. The greater the abnormality index of the smoke pressure measuring point is, the higher the risk of leakage of the smoke pressure measuring point is.
Further, in step 305, the risk sequence of the leakage of the plurality of smoke pressure measurement points may be determined according to the magnitude of the abnormality indexes of the plurality of smoke pressure measurement points, so that the maintenance personnel can position the smoke pressure measurement point with the leakage based on the risk sequence of the leakage of the plurality of smoke pressure measurement points. Optionally, the plurality of smoke pressure measurement points may be ordered according to the order of the abnormality indexes of the plurality of smoke pressure measurement points from large to small, so as to obtain the risk order of leakage of the plurality of smoke pressure measurement points.
The calculation mode of the abnormal indexes of the smoke pressure measuring points compares the smoke pressure data before and after boiler leakage, namely compares the smoke pressure data during normal operation of the boiler with the smoke pressure data after leakage, fully utilizes the characteristic information contained in the historical data, and can improve the accuracy of abnormal index calculation. On the other hand, various characteristic parameters are adopted to determine the possibility of leakage of the smoke pressure measuring point, and the robustness of a leakage positioning method is improved.
Further, the plurality of smoke pressure measuring points can be displayed according to the risk sequence of leakage of the plurality of smoke pressure measuring points. The risk sequence of leakage of the smoke pressure measuring points which are arranged at the front is higher, so that maintenance staff overhauls the smoke pressure measuring points according to the risk sequence to rapidly locate the smoke pressure measuring points which are leaked.
In the embodiment of the application, the existing pressure gauge of the boiler is utilized to carry out leakage positioning on the boiler, and no additional sensor is needed, thereby being beneficial to reducing the leakage positioning cost. On the other hand, as the response time of the smoke pressure data is shorter, the characteristic parameters of the smoke pressure measuring point can be timely obtained, and the timeliness and the time sensitivity of leakage positioning can be improved.
It should be noted that the above-mentioned monitoring method and leak locating method may be implemented separately or in combination. For the computer equipment, only the monitoring method or the leakage positioning method can be deployed, and two methods of the monitoring method and the leakage positioning method can also be deployed.
It should be noted that, the execution subjects of each step of the method provided in the above embodiment may be the same device, or the method may also be executed by different devices. For example, the execution subject of steps 301 and 302 may be device a; for another example, the execution body of step 301 may be device a, and the execution body of step 302 may be device B; etc.
In addition, in some of the flows described in the above embodiments and the drawings, a plurality of operations appearing in a specific order are included, but it should be clearly understood that the operations may be performed out of the order in which they appear herein or performed in parallel, the sequence numbers of the operations such as 301, 302, etc. are merely used to distinguish between the various operations, and the sequence numbers themselves do not represent any order of execution. In addition, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel.
Accordingly, embodiments of the present application also provide a computer-readable storage medium storing computer instructions that, when executed by one or more processors, cause the one or more processors to perform the steps in the above-described monitoring method and/or leak location method.
Fig. 4 is a schematic structural diagram of a computer device according to an embodiment of the present application. As shown in fig. 4, the computer device includes: a memory 40a and a processor 40b; wherein the memory 40a is used for storing a computer program.
The processor 40b is coupled to the memory 40a for executing a computer program for: acquiring real-time total liquid flow and real-time steam flow of a boiler; determining the real-time liquid loss of the boiler according to the real-time total liquid flow and the real-time steam flow; performing variable point detection on the historical liquid loss and the real-time liquid loss of the boiler by adopting a probability statistical method; and determining the health condition of the current boiler according to the change point detection result.
In some embodiments, the processor 40b is specifically configured to, when performing the variable point detection of the historical liquid loss amount and the real-time liquid loss amount of the boiler: and performing variable point detection on the historical liquid loss and the real-time liquid loss of the boiler by using a Bayesian variable point detection model.
Further, the processor 40b is specifically configured to, when performing the variable point detection on the historical liquid loss amount and the real-time liquid loss amount of the boiler: inputting the historical liquid loss and the real-time liquid loss of the boiler into a Bayesian variable point detection model; in a Bayesian variable point detection model, calculating the probability that the real-time liquid loss is a variable point by utilizing the historical liquid loss and the real-time liquid loss of the boiler; and determining whether the real-time liquid loss is the change point according to the probability that the real-time liquid loss is the change point.
Optionally, when determining whether the sampling time corresponding to the real-time liquid loss is a variable point, the processor 40b is specifically configured to: and if the probability that the real-time liquid loss is the change point is larger than the set probability threshold, determining that the real-time liquid loss is the change point.
Optionally, the processor 40b is specifically configured to, when determining the current health of the boiler: and if the change point detection result is that the real-time liquid loss amount is the change point, determining that the liquid leakage occurs in the current boiler.
In other embodiments, the processor 40b is further configured to: before the change point detection is carried out on the historical liquid loss of the boiler and the real-time liquid loss, the historical liquid loss of the boiler is downsampled according to a first sampling period so as to obtain the downsampled historical liquid loss; the first sampling period is greater than the sampling period of the flowmeter in the boiler; and performing variable point detection on the down-sampled historical liquid loss and the down-sampled real-time liquid loss by adopting a probability statistical method.
Optionally, the processor 40b is specifically configured to, when performing the variable-point detection on the downsampled historical liquid loss amount and the real-time liquid loss amount: smoothing the downsampled historical liquid loss and the real-time liquid loss to obtain smoothed historical liquid loss and smoothed real-time liquid loss; and detecting the change point of the historical liquid loss after the smoothing treatment and the real-time liquid loss after the smoothing treatment by adopting a probability statistical method.
Optionally, the processor 40b is specifically configured to, when performing the smoothing processing on the downsampled historical liquid loss amount and the real-time liquid loss amount: and smoothing the down-sampled historical liquid loss and the down-sampled real-time liquid loss by adopting an exponentially weighted moving window function.
In some embodiments, the computer device further comprises: a display screen 40c; the processor 40b is also configured to: the current boiler health is displayed on the display screen 40 c.
In other embodiments, the computer device further comprises: a communication component 40d. The processor 40b is also configured to: the health of the current boiler is provided to the corresponding display node of the boiler for display via the communication component 40d.
Optionally, the processor 40b is further configured to: displaying a data signboard reflecting a change relation of the real-time liquid loss amount of the boiler with time on the display screen 40 c; and displaying the change point in the data billboard in a set display format when the change point exists.
The computer equipment provided by the embodiment can utilize the probability statistical method to detect the change points of the historical liquid loss and the real-time liquid loss of the boiler acquired by the existing flowmeter of the boiler, and determine the health condition of the current boiler according to the change point detection result, so that the real-time monitoring of boiler leakage is realized, the probability statistical method is utilized to detect the change points, a large number of points are not required to be accumulated, the detection of the boiler leakage is facilitated in time, and the sensitivity of the real-time detection of the boiler leakage is improved.
In an embodiment of the present application, the processor 40b may be further configured to: under the condition that liquid leakage exists in the boiler, acquiring a smoke pressure sequence acquired by a pressure gauge of a plurality of smoke pressure measuring points distributed in the boiler before the boiler is maintained; the smoke pressure sequence that the manometer of a plurality of smoke pressure measurement points gathered includes: smoke pressure data before and after liquid leakage exists in a boiler, which are collected by pressure gauges of a plurality of smoke pressure measuring points; respectively performing variable point detection on the smoke pressure sequences acquired by the pressure gauges of the smoke pressure measuring points to determine smoke pressure variable points in the smoke pressure sequences acquired by the pressure gauges of each smoke pressure measuring point; determining a normal sample interval and an abnormal sample interval of a smoke pressure sequence corresponding to each smoke pressure measuring point based on smoke pressure change points in the smoke pressure sequence acquired by a pressure gauge of each smoke pressure measuring point; calculating an abnormality index of each smoke pressure measuring point by using the smoke pressure in the normal sample interval and the smoke pressure in the abnormal sample interval corresponding to each smoke pressure measuring point; and determining the risk sequence of leakage of the plurality of smoke pressure measuring points according to the magnitude of the abnormality indexes of the plurality of smoke pressure measuring points, so that maintenance personnel can perform leakage positioning based on the risk sequence.
In some embodiments, the processor 40b is further configured to: the plurality of smoke pressure measuring points are displayed on the display screen 40c according to the risk sequence of leakage of the plurality of smoke pressure measuring points, so that maintenance staff can maintain the plurality of smoke pressure measuring points according to the risk sequence.
Optionally, the processor 40b is specifically configured to, when determining a risk sequence of leakage at a plurality of smoke pressure measurement points: and sequencing the plurality of smoke pressure measuring points according to the sequence from the large to the small of the abnormality indexes of the plurality of smoke pressure measuring points so as to obtain the risk sequence of leakage of the plurality of smoke pressure measuring points.
In some embodiments, the processor 40b is specifically configured to, when performing the variable point detection on the smoke pressure sequences acquired by the pressure gauges of the plurality of smoke pressure measurement points, respectively: aiming at the first smoke pressure measuring point, detecting a smoke pressure sequence of the first smoke pressure measuring point by using a PELT algorithm to determine a smoke pressure change point in the smoke pressure sequence corresponding to the first smoke pressure measuring point; the first smoke pressure measuring point is any smoke pressure measuring point in a plurality of smoke pressure measuring points.
Optionally, the processor 40b is specifically configured to, when determining a normal sample interval and an abnormal sample interval of the smoke pressure sequence corresponding to the smoke pressure measurement point: peak searching is carried out on the smoke pressure sequence corresponding to the first smoke pressure measuring point aiming at the first smoke pressure measuring point so as to determine the smoke pressure peak value in the smoke pressure sequence corresponding to the first smoke pressure measuring point; determining a maximum smoke pressure peak value from smoke pressure peak values in a smoke pressure sequence corresponding to the first smoke pressure measuring point; acquiring a first smoke pressure change point and a second smoke pressure change point, which are adjacent to each other in acquisition time and correspond to the maximum smoke pressure peak value, from smoke pressure change points in a smoke pressure sequence corresponding to the first smoke pressure measurement point; and acquiring the smoke pressure acquired in the acquisition time period from the first smoke pressure change point to the second smoke pressure change point from the smoke pressure sequence corresponding to the first smoke pressure measurement point, and taking the smoke pressure as an abnormal sample interval of the smoke pressure sequence corresponding to the first smoke pressure measurement point; acquiring first smoke pressure data, the acquisition time of which is positioned before the first smoke pressure change point and the time interval between the first smoke pressure data and the first smoke pressure change point is a set time interval, from a smoke pressure sequence corresponding to the first smoke pressure measurement point; and selecting a smoke pressure sequence with acquisition time in an acquisition time period of the specified smoke pressure data and the first smoke pressure data from the smoke pressure sequence corresponding to the first smoke pressure measuring point as a normal sample interval of the smoke pressure sequence corresponding to the first smoke pressure measuring point; the acquisition time of the specified smoke pressure data is located before the first smoke pressure data.
Optionally, the processor 40b is specifically configured to, when calculating the abnormality index of the smoke pressure measurement point: calculating at least one characteristic parameter value of the first smoke pressure measuring point by using the smoke pressure in the normal sample interval and the smoke pressure in the abnormal sample interval corresponding to the first smoke pressure measuring point aiming at the first smoke pressure measuring point; determining an abnormality index of at least one characteristic parameter value of the first smoke pressure measuring point according to the sequence of the at least one characteristic parameter value of the first smoke pressure measuring point in the characteristic parameters of the same attribute of the plurality of smoke pressure measuring points; and carrying out weighted summation on the abnormality indexes of at least one characteristic parameter value of the first smoke pressure measuring point to obtain the abnormality indexes of the first smoke pressure measuring point.
Optionally, the processor 40b is specifically configured to perform at least one of the following calculation modes when calculating the at least one characteristic parameter value of the first smoke pressure measurement point:
Calculating the relative change proportion of the root mean square of the smoke pressure of the normal sample interval corresponding to the first smoke pressure measuring point and the smoke pressure of the abnormal sample interval;
calculating the standard deviation variation of the smoke pressure of the normal sample interval and the smoke pressure of the abnormal sample interval corresponding to the first smoke pressure measuring point;
Calculating a dynamic time warping distance between the smoke pressure of the normal sample interval corresponding to the first smoke pressure measuring point and the smoke pressure of the abnormal sample interval;
Searching a valley of the smoke pressure of the abnormal sample section corresponding to the first smoke pressure measuring point to determine a smoke pressure valley of the abnormal sample section corresponding to the first smoke pressure measuring point; calculating the relative variation of the maximum smoke pressure peak value and the smoke pressure wave valley in the abnormal sample interval corresponding to the first smoke pressure measuring point;
Determining the target smoke pressure of which the acquisition time is after the boiler leaks and exceeds the smoke pressure average value set proportion of the normal sample interval corresponding to the first smoke pressure measuring point from the smoke pressure sequence corresponding to the first smoke pressure measuring point; calculating the time interval between the acquisition time of the minimum value of the target smoke pressure and the leakage of the boiler, and taking the time interval as the response time of the first smoke pressure measuring point to the leakage of the boiler;
and calculating the time interval between the leakage of the smoke pressure sequence corresponding to the first smoke pressure measuring point from the boiler and the reaching of the maximum smoke pressure peak value in the abnormal sample interval corresponding to the first smoke pressure measuring point.
In some embodiments, the processor 40b is further configured to: acquiring a liquid loss sequence which is in the same acquisition time period with a smoke pressure sequence acquired by a pressure gauge of a plurality of smoke pressure measuring points; performing variable point detection on the liquid loss sequence to determine a variable point in the liquid loss sequence; and the acquisition time of the variable point with the earliest acquisition time in the variable points in the liquid loss sequence is used as the time of leakage of the boiler.
Optionally, the processor 40b is specifically configured to, when performing the variable point detection on the liquid loss amount sequence: and detecting the change points of the liquid loss sequence by using a PELT algorithm to determine the change points in the liquid loss sequence.
The computer equipment provided by the embodiment can utilize the existing pressure gauge of the boiler to perform leakage positioning on the boiler, does not need to add an additional sensor, and is beneficial to reducing the leakage positioning cost. On the other hand, as the response time of the smoke pressure data is shorter, the characteristic parameters of the smoke pressure measuring point can be timely obtained, and the timeliness and the time sensitivity of leakage positioning can be improved.
In some alternative embodiments, as shown in fig. 4, the computer device may further include: optional components such as a power component 40e, an audio component 40f, and the like. The illustration of only a few components in fig. 4 is not intended to imply that the computer device must contain all of the components shown in fig. 4 nor that the computer device can only contain the components shown in fig. 4.
In an embodiment of the present application, the memory is used to store a computer program and may be configured to store various other data to support operations on the device on which it resides. Wherein the processor may execute a computer program stored in the memory to implement the corresponding control logic. The memory may be implemented by any type of volatile or nonvolatile memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.
In an embodiment of the present application, the processor may be any hardware processing device that may execute the above-described method logic. Alternatively, the processor may be a central processing unit (Central Processing Unit, CPU), a graphics processor (Graphics Processing Unit, GPU) or a micro-control unit (Microcontroller Unit, MCU); programmable devices such as Field-Programmable gate arrays (Field-Programmable GATE ARRAY, FPGA), programmable array Logic devices (Programmable Array Logic, PAL), general-purpose array Logic devices (GENERAL ARRAY Logic, GAL), complex Programmable Logic devices (Complex Programmable Logic Device, CPLD), and the like; or an advanced Reduced Instruction Set (RISC) processor (ADVANCED RISC MACHINES, ARM) or a System On Chip (SOC), etc., but is not limited thereto.
In an embodiment of the application, the communication component is configured to facilitate wired or wireless communication between the device in which it is located and other devices. The device in which the communication component is located may access a wireless network based on a communication standard, such as WiFi,2G or 3G,4G,5G or a combination thereof. In one exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component may also be implemented based on Near Field Communication (NFC) technology, radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, or other technologies.
In an embodiment of the present application, the display screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the display screen includes a touch panel, the display screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation.
In an embodiment of the application, the power supply assembly is configured to provide power to the various components of the device in which it is located. The power components may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the devices in which the power components are located.
In embodiments of the application, the audio component may be configured to output and/or input audio signals. For example, the audio component includes a Microphone (MIC) configured to receive external audio signals when the device in which the audio component is located is in an operational mode, such as a call mode, a recording mode, and a speech recognition mode. The received audio signal may be further stored in a memory or transmitted via a communication component. In some embodiments, the audio assembly further comprises a speaker for outputting audio signals. For example, for a device with language interaction functionality, voice interaction with a user, etc., may be accomplished through an audio component.
It should be noted that, the descriptions of "first" and "second" herein are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, and are not limited to the "first" and the "second" being different types.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.
Claims (31)
1. A monitoring system, comprising: monitoring nodes, a boiler and a flowmeter arranged in the boiler;
the flowmeter is used for collecting real-time total liquid flow and real-time steam flow of the boiler;
The monitoring node is used for determining the real-time liquid loss of the boiler according to the real-time total liquid flow and the real-time steam flow; performing variable point detection on the historical liquid loss and the real-time liquid loss of the boiler by using a Bayesian variable point detection model, wherein in the Bayesian variable point detection model, the probability that the real-time liquid loss is a variable point is calculated by using the historical liquid loss and the real-time liquid loss of the boiler; determining a change point detection result according to the probability that the real-time liquid loss is a change point, wherein the change point detection result represents whether the real-time liquid loss is the change point or not; and determining the health condition of the current boiler according to the change point detection result.
2. The system of claim 1, further comprising: displaying the nodes; the monitoring node is further configured to: providing the current health status of the boiler to the display node;
And the display node is used for displaying the current health condition of the boiler.
3. The system of claim 2, wherein the display node is further configured to: displaying a data billboard reflecting the change relation of the real-time liquid loss quantity of the boiler with time; and displaying the change point in the data billboard in a set display format when the change point exists.
4. The system of claim 2, wherein the monitoring node is further configured to:
Calculating the loss speed of the real-time liquid loss amount of the boiler; providing a loss rate of a real-time liquid loss amount of the boiler to the display node;
The display node is used for displaying the loss speed of the real-time liquid loss quantity of the boiler.
5. The system of claim 1, wherein the monitoring node is further configured to:
and outputting leakage alarm information under the condition that the current boiler leaks.
6. The system of claim 1, further comprising: a level gauge disposed within the boiler; the liquid level meter is used for collecting the liquid level of the boiler;
the monitoring node is used for controlling the water inlet of the boiler to be opened under the condition that the liquid level of the boiler is lower than a set first liquid level threshold value; and controlling a water inlet of the boiler to be closed under the condition that the liquid level of the boiler reaches a set second liquid level threshold value;
And/or the monitoring node is used for outputting water shortage prompt information to prompt a manager of the boiler to supplement water under the condition that the liquid level of the boiler is lower than a set first liquid level threshold value; outputting full liquid level prompt information to prompt a manager of the boiler to stop water supplementing under the condition that the liquid level of the boiler reaches a set second liquid level threshold value;
Wherein the second liquid level threshold is greater than the first liquid level threshold.
7. The system of any one of claims 1-6, further comprising: a plurality of pressure gauges mounted to a plurality of smoke pressure measurement points of the boiler; the pressure gauges are used for monitoring the smoke pressure at the corresponding smoke pressure measuring points;
the plurality of smoke pressure measurement points includes: at least two of an inlet and an outlet of a radiation channel of the boiler, an inlet and an outlet of the superheater and an inlet and an outlet of the economizer; the superheater includes: at least one of a high temperature superheater, a medium temperature superheater and a low temperature superheater;
The monitoring node is further configured to: under the condition that liquid leakage occurs in the boiler, acquiring a smoke pressure sequence acquired by a pressure gauge of the smoke pressure measuring points before the boiler is maintained; the smoke pressure sequence acquired by the pressure gauges of the smoke pressure measuring points comprises: smoke pressure data before and after liquid leakage occurs in the boiler; respectively detecting the smoke pressure sequences acquired by the pressure gauges of the smoke pressure measuring points to determine smoke pressure change points in the smoke pressure sequences acquired by the pressure gauges of each smoke pressure measuring point; determining a normal sample interval and an abnormal sample interval of a smoke pressure sequence corresponding to each smoke pressure measuring point based on smoke pressure change points in the smoke pressure sequence acquired by a pressure gauge of each smoke pressure measuring point; calculating an abnormality index of each smoke pressure measuring point by using the smoke pressure in the normal sample interval and the smoke pressure in the abnormal sample interval corresponding to each smoke pressure measuring point; and determining the risk sequence of leakage of the smoke pressure measuring points according to the magnitude of the abnormality indexes of the smoke pressure measuring points, so that maintenance personnel can perform leakage positioning based on the risk sequence.
8. The system of claim 7, further comprising: displaying the nodes; the monitoring node is further configured to increase the risk sequence of leakage at the plurality of smoke pressure measurement points to the display node;
The display node is used for: and displaying the plurality of smoke pressure measuring points according to the risk sequence of leakage of the plurality of smoke pressure measuring points, so that maintenance personnel can maintain the plurality of smoke pressure measuring points according to the risk sequence.
9. The system of claim 7, wherein the detecting the change point of the sequence of smoke pressures collected by the pressure gauges of the plurality of smoke pressure measurement points to determine the change point of smoke pressure in the sequence of smoke pressures collected by the pressure gauges of each smoke pressure measurement point comprises:
For a first smoke pressure measuring point, detecting a smoke pressure sequence of the first smoke pressure measuring point by using a PELT algorithm to determine a smoke pressure change point in the smoke pressure sequence corresponding to the first smoke pressure measuring point; the first smoke pressure measuring point is any smoke pressure measuring point in the plurality of smoke pressure measuring points.
10. A method of monitoring, comprising:
Acquiring real-time total liquid flow and real-time steam flow of a boiler;
determining the real-time liquid loss of the boiler according to the real-time total liquid flow and the real-time steam flow;
Performing variable point detection on the historical liquid loss and the real-time liquid loss of the boiler by using a Bayesian variable point detection model, wherein in the Bayesian variable point detection model, the probability that the real-time liquid loss is a variable point is calculated by using the historical liquid loss and the real-time liquid loss of the boiler; determining a change point detection result according to the probability that the real-time liquid loss is a change point, wherein the change point detection result represents whether the real-time liquid loss is the change point or not;
and determining the health condition of the current boiler according to the change point detection result.
11. The method of claim 10, wherein determining whether the real-time liquid loss amount is a change point based on the probability that the real-time liquid loss amount is a change point comprises:
And if the probability that the real-time liquid loss is the change point is larger than the set probability threshold, determining that the real-time liquid loss is the change point.
12. The method of claim 10, wherein determining the current boiler health based on the change point detection comprises:
And if the change point detection result is that the real-time liquid loss amount is the change point, determining that the liquid leakage occurs in the current boiler.
13. The method according to any one of claims 10-12, further comprising, prior to performing the varipoint detection of the historical and real-time liquid loss amounts of the boiler using a bayesian varipoint detection model:
Downsampling the historical liquid loss of the boiler according to a first sampling period to obtain the downsampled historical liquid loss; the first sampling period is greater than the sampling period of the flowmeter in the boiler;
and performing variable point detection on the downsampled historical liquid loss and the real-time liquid loss by adopting a Bayesian variable point detection model.
14. The method of claim 13, wherein performing the varipoint detection on the downsampled historical liquid loss amount and the real-time liquid loss amount using a bayesian varipoint detection model comprises:
smoothing the downsampled historical liquid loss and the real-time liquid loss to obtain smoothed historical liquid loss and smoothed real-time liquid loss;
and detecting the change point of the historical liquid loss after the smoothing treatment and the real-time liquid loss after the smoothing treatment by adopting a Bayesian change point detection model.
15. The method of claim 14, wherein smoothing the downsampled historical fluid loss amount and the real-time fluid loss amount comprises:
and smoothing the downsampled historical liquid loss and the real-time liquid loss by adopting an exponentially weighted moving window function.
16. The method as recited in claim 10, further comprising:
And displaying the health condition of the current boiler, or providing the health condition of the current boiler to a display node corresponding to the boiler for display.
17. The method as recited in claim 16, further comprising:
displaying a data billboard reflecting the change relation of the real-time liquid loss quantity of the boiler with time; and displaying the change point in the data billboard in a set display format when the change point exists.
18. The method according to any one of claims 10-12, further comprising:
under the condition that liquid leakage exists in the boiler, acquiring a smoke pressure sequence acquired by a pressure gauge of a plurality of smoke pressure measuring points distributed in the boiler before the boiler is maintained; the smoke pressure sequence that the manometer of a plurality of smoke pressure measurement stations gathered includes: the pressure gauges of the smoke pressure measuring points collect smoke pressure data before and after liquid leakage exists in the boiler;
respectively detecting the smoke pressure sequences acquired by the pressure gauges of the smoke pressure measuring points to determine smoke pressure change points in the smoke pressure sequences acquired by the pressure gauges of each smoke pressure measuring point;
Determining a normal sample interval and an abnormal sample interval of a smoke pressure sequence corresponding to each smoke pressure measuring point based on smoke pressure change points in the smoke pressure sequence acquired by a pressure gauge of each smoke pressure measuring point;
Calculating an abnormality index of each smoke pressure measuring point by using the smoke pressure in the normal sample interval and the smoke pressure in the abnormal sample interval corresponding to each smoke pressure measuring point;
and determining the risk sequence of leakage of the smoke pressure measuring points according to the magnitude of the abnormality indexes of the smoke pressure measuring points, so that maintenance personnel can perform leakage positioning based on the risk sequence.
19. The method as recited in claim 18, further comprising:
And displaying the plurality of smoke pressure measuring points according to the risk sequence of leakage of the plurality of smoke pressure measuring points, so that maintenance personnel can maintain the plurality of smoke pressure measuring points according to the risk sequence.
20. The method of claim 18, wherein determining the order of risk of leakage at the plurality of smoke pressure points based on the magnitude of the abnormality index for the plurality of smoke pressure points comprises:
and sequencing the plurality of smoke pressure measuring points according to the sequence from the large to the small of the abnormality indexes of the plurality of smoke pressure measuring points so as to obtain the risk sequence of leakage of the plurality of smoke pressure measuring points.
21. The method of claim 18, wherein the detecting the change point of the sequence of smoke pressures collected by the pressure gauges of the plurality of smoke pressure measurement points to determine the change point of smoke pressure in the sequence of smoke pressures collected by the pressure gauges of each smoke pressure measurement point comprises:
For a first smoke pressure measuring point, detecting a smoke pressure sequence of the first smoke pressure measuring point by using a PELT algorithm to determine a smoke pressure change point in the smoke pressure sequence corresponding to the first smoke pressure measuring point; the first smoke pressure measuring point is any smoke pressure measuring point in the plurality of smoke pressure measuring points.
22. The method according to claim 18, wherein determining the normal sample interval and the abnormal sample interval of the smoke pressure sequence corresponding to the smoke pressure measuring point based on the smoke pressure change point in the smoke pressure sequence acquired by the pressure gauge of each smoke pressure measuring point comprises:
For a first smoke pressure measuring point, peak searching is carried out on a smoke pressure sequence corresponding to the first smoke pressure measuring point so as to determine a smoke pressure peak value in the smoke pressure sequence corresponding to the first smoke pressure measuring point;
Determining a maximum smoke pressure peak value from smoke pressure peak values in a smoke pressure sequence corresponding to the first smoke pressure measuring point;
acquiring a first smoke pressure change point and a second smoke pressure change point, the acquisition time of which is adjacent to the acquisition time corresponding to the maximum smoke pressure peak value, from smoke pressure change points in a smoke pressure sequence corresponding to the first smoke pressure measurement point;
Acquiring the smoke pressure acquired in the acquisition time period from the first smoke pressure change point to the second smoke pressure change point from the smoke pressure sequence corresponding to the first smoke pressure measurement point, and taking the smoke pressure as an abnormal sample interval of the smoke pressure sequence corresponding to the first smoke pressure measurement point;
Acquiring first smoke pressure data, the acquisition time of which is positioned before the first smoke pressure change point and the time interval between the acquisition time and the first smoke pressure change point is a set time interval, from a smoke pressure sequence corresponding to the first smoke pressure measurement point;
Selecting a tobacco pressure sequence with acquisition time in an acquisition time period of specified tobacco pressure data and the first tobacco pressure data from the tobacco pressure sequence corresponding to the first tobacco pressure measuring point, and taking the tobacco pressure sequence as a normal sample interval of the tobacco pressure sequence corresponding to the first tobacco pressure measuring point;
the acquisition time of the specified smoke pressure data is located before the first smoke pressure data.
23. The method of claim 18, wherein calculating the abnormality index of each smoke pressure measurement point using the smoke pressure in the normal sample interval and the smoke pressure in the abnormal sample interval corresponding to the smoke pressure measurement point comprises:
For a first smoke pressure measuring point, calculating at least one characteristic parameter value of the first smoke pressure measuring point by using the smoke pressure in a normal sample interval and the smoke pressure in an abnormal sample interval corresponding to the first smoke pressure measuring point;
Determining an abnormality index of at least one characteristic parameter value of the first smoke pressure measuring point according to the sequence of the at least one characteristic parameter value of the first smoke pressure measuring point in the characteristic parameters of the same attribute of the plurality of smoke pressure measuring points;
And carrying out weighted summation on the abnormality indexes of at least one characteristic parameter value of the first smoke pressure measuring point to obtain the abnormality indexes of the first smoke pressure measuring point.
24. The method of claim 23, wherein calculating the at least one characteristic parameter value of the first smoke pressure measurement point using the smoke pressure of the normal sample interval and the smoke pressure of the abnormal sample interval corresponding to the first smoke pressure measurement point comprises performing at least one of the following calculation modes:
calculating the relative change proportion of the root mean square of the smoke pressure of the normal sample interval corresponding to the first smoke pressure measuring point and the smoke pressure of the abnormal sample interval;
calculating the standard deviation variation of the smoke pressure of the normal sample interval and the smoke pressure of the abnormal sample interval corresponding to the first smoke pressure measuring point;
Calculating a dynamic time warping distance between the smoke pressure of the normal sample interval corresponding to the first smoke pressure measuring point and the smoke pressure of the abnormal sample interval;
Searching a valley of the smoke pressure of the abnormal sample interval corresponding to the first smoke pressure measuring point to determine a smoke pressure valley of the abnormal sample interval corresponding to the first smoke pressure measuring point; calculating the relative variation of the maximum smoke pressure peak value and the smoke pressure trough in the abnormal sample interval corresponding to the first smoke pressure measuring point;
Determining the smoke pressure of the boiler after leakage from a smoke pressure sequence corresponding to the first smoke pressure measuring point, wherein the acquisition time of the smoke pressure exceeds the target smoke pressure of the smoke pressure average value set proportion of a normal sample interval corresponding to the first smoke pressure measuring point; calculating the time interval between the acquisition time of the minimum value of the target smoke pressure and the leakage of the boiler, and taking the time interval as the response time of the first smoke pressure measuring point to the leakage of the boiler;
And calculating the time interval between the leakage of the smoke pressure sequence corresponding to the first smoke pressure measuring point from the boiler to the maximum smoke pressure peak value in the abnormal sample interval corresponding to the first smoke pressure measuring point.
25. The method as recited in claim 24, further comprising:
acquiring a liquid loss sequence which is in the same acquisition time period with a smoke pressure sequence acquired by a pressure gauge of the smoke pressure measuring points;
Performing variable point detection on the liquid loss sequence to determine a variable point in the liquid loss sequence;
and taking the acquisition time of the variable point with the earliest acquisition time among the variable points in the liquid loss sequence as the time of leakage of the boiler.
26. The method of claim 25, wherein the performing a change point detection on the sequence of fluid loss amounts to determine a change point in the sequence of fluid loss amounts comprises:
and detecting the change point of the liquid loss sequence by using a PELT algorithm to determine the change point in the liquid loss sequence.
27. A leak location method, comprising:
In the case of determining that there is a liquid leak in a boiler using the method of any one of claims 10-15, acquiring a sequence of smoke pressures acquired by pressure gauges distributed over a plurality of smoke pressure points within the boiler prior to boiler repair; the smoke pressure sequence that the manometer of a plurality of smoke pressure measurement stations gathered includes: the pressure gauges of the smoke pressure measuring points collect smoke pressure data before and after liquid leakage exists in the boiler;
respectively detecting the smoke pressure sequences acquired by the pressure gauges of the smoke pressure measuring points to determine smoke pressure change points in the smoke pressure sequences acquired by the pressure gauges of each smoke pressure measuring point;
Determining a normal sample interval and an abnormal sample interval of a smoke pressure sequence corresponding to each smoke pressure measuring point based on smoke pressure change points in the smoke pressure sequence acquired by a pressure gauge of each smoke pressure measuring point;
Calculating an abnormality index of each smoke pressure measuring point by using the smoke pressure in the normal sample interval and the smoke pressure in the abnormal sample interval corresponding to each smoke pressure measuring point;
and determining the risk sequence of leakage of the plurality of smoke pressure measuring points according to the magnitude of the abnormality indexes of the plurality of smoke pressure measuring points, so that maintenance personnel can position the smoke pressure measuring points with leakage based on the risk sequence.
28. A boiler, comprising: a flowmeter and a monitoring module installed in the boiler;
the flowmeter is used for collecting real-time total liquid flow and real-time steam flow of the boiler;
The monitoring module is used for determining the real-time liquid loss of the boiler according to the real-time total liquid flow and the real-time steam flow; performing variable point detection on the historical liquid loss and the real-time liquid loss of the boiler by using a Bayesian variable point detection model, wherein in the Bayesian variable point detection model, the probability that the real-time liquid loss is a variable point is calculated by using the historical liquid loss and the real-time liquid loss of the boiler; determining a change point detection result according to the probability that the real-time liquid loss is a change point, wherein the change point detection result represents whether the real-time liquid loss is the change point or not; and determining the health condition of the current boiler according to the change point detection result.
29. The boiler according to claim 28, further comprising: a plurality of pressure gauges mounted to a plurality of smoke pressure measurement points of the boiler; the pressure gauges are used for monitoring the smoke pressure at the corresponding smoke pressure measuring points;
the plurality of smoke pressure measurement points includes: at least two of an inlet and an outlet of a radiation channel of the boiler, an inlet and an outlet of the superheater and an inlet and an outlet of the economizer; the superheater includes: at least one of a high temperature superheater, a medium temperature superheater and a low temperature superheater;
the monitoring module is further used for: under the condition that liquid leakage occurs in the boiler, acquiring a smoke pressure sequence acquired by a pressure gauge of the smoke pressure measuring points before the boiler is maintained; the smoke pressure sequence acquired by the pressure gauges of the smoke pressure measuring points comprises: smoke pressure data before and after liquid leakage occurs in the boiler; respectively detecting the smoke pressure sequences acquired by the pressure gauges of the smoke pressure measuring points to determine smoke pressure change points in the smoke pressure sequences acquired by the pressure gauges of each smoke pressure measuring point; determining a normal sample interval and an abnormal sample interval of a smoke pressure sequence corresponding to each smoke pressure measuring point based on smoke pressure change points in the smoke pressure sequence acquired by a pressure gauge of each smoke pressure measuring point; calculating an abnormality index of each smoke pressure measuring point by using the smoke pressure in the normal sample interval and the smoke pressure in the abnormal sample interval corresponding to each smoke pressure measuring point; and determining the risk sequence of leakage of the smoke pressure measuring points according to the magnitude of the abnormality indexes of the smoke pressure measuring points, so that maintenance personnel can perform leakage positioning based on the risk sequence.
30. A computer device, comprising: a memory and a processor; wherein the memory is used for storing a computer program;
The processor is coupled to the memory for executing the computer program for performing the steps in the method of any of claims 10-27.
31. A computer-readable storage medium storing computer instructions that, when executed by one or more processors, cause the one or more processors to perform the steps in the method of any of claims 10-27.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011475800.0A CN114623990B (en) | 2020-12-14 | 2020-12-14 | Monitoring and leakage positioning method, device, boiler, system and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011475800.0A CN114623990B (en) | 2020-12-14 | 2020-12-14 | Monitoring and leakage positioning method, device, boiler, system and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114623990A CN114623990A (en) | 2022-06-14 |
CN114623990B true CN114623990B (en) | 2024-06-25 |
Family
ID=81897588
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011475800.0A Active CN114623990B (en) | 2020-12-14 | 2020-12-14 | Monitoring and leakage positioning method, device, boiler, system and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114623990B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116498908B (en) * | 2023-06-26 | 2023-08-25 | 成都秦川物联网科技股份有限公司 | Intelligent gas pipe network monitoring method based on ultrasonic flowmeter and Internet of things system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101839795A (en) * | 2010-05-10 | 2010-09-22 | 任振伟 | The leak diagnostic systems of pressure-bearing pipe of boiler and method |
CN106918033A (en) * | 2017-03-21 | 2017-07-04 | 山东中实易通集团有限公司 | Three impulses leakage of boiler tubes alarm control system and method |
CN111626360A (en) * | 2020-05-28 | 2020-09-04 | 新智数字科技有限公司 | Method, device, equipment and storage medium for detecting fault type of boiler |
Family Cites Families (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH06292839A (en) * | 1993-04-12 | 1994-10-21 | Mitsubishi Heavy Ind Ltd | Method for controlling smoke concentration of boiler |
CN102734785B (en) * | 2012-07-04 | 2014-11-26 | 攀钢集团攀枝花钢钒有限公司 | Leakage judging method for boiler economizer in power plant |
CN105718717A (en) * | 2016-01-12 | 2016-06-29 | 叶翔 | Method and device for establishing boiler combustion process model by utilizing Bayesian network algorithm |
WO2019006474A1 (en) * | 2017-06-30 | 2019-01-03 | The Johns Hopkins University | Hardware architecture and processing units for exact bayesian inference with on-line learning and methods for same |
CN208061002U (en) * | 2018-03-20 | 2018-11-06 | 沈阳日上机电工程技术有限公司 | A kind of boiler room equipment energy consumption monitoring system |
CN108764745B (en) * | 2018-06-05 | 2020-05-15 | 中国石油大学(北京) | Method and device for evaluating leakage risk of dangerous liquid pipeline |
CN110222351A (en) * | 2018-12-17 | 2019-09-10 | 江苏海事职业技术学院 | Gas mixed burning boiler as-fired coal gas calorific value and boiler thermal efficiency on-line monitoring method |
CN109469896B (en) * | 2018-12-28 | 2020-06-09 | 佛山科学技术学院 | Industrial boiler fault diagnosis method and system based on time series analysis |
CN109813400B (en) * | 2019-03-23 | 2024-02-06 | 重庆市计量质量检测研究院 | Boiler main steam flowmeter online checking and testing system based on internet of things technology |
CN111667009B (en) * | 2020-06-08 | 2023-04-04 | 长安大学 | Time sequence mutation detection method based on sample entropy and Bayes |
CN111927574B (en) * | 2020-06-18 | 2022-06-07 | 华电电力科学研究院有限公司 | Test device for indirectly testing steam leakage amount of steam seal |
-
2020
- 2020-12-14 CN CN202011475800.0A patent/CN114623990B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101839795A (en) * | 2010-05-10 | 2010-09-22 | 任振伟 | The leak diagnostic systems of pressure-bearing pipe of boiler and method |
CN106918033A (en) * | 2017-03-21 | 2017-07-04 | 山东中实易通集团有限公司 | Three impulses leakage of boiler tubes alarm control system and method |
CN111626360A (en) * | 2020-05-28 | 2020-09-04 | 新智数字科技有限公司 | Method, device, equipment and storage medium for detecting fault type of boiler |
Also Published As
Publication number | Publication date |
---|---|
CN114623990A (en) | 2022-06-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109325692B (en) | Real-time data analysis method and device for water pipe network | |
US20180224831A1 (en) | Event analyzing device, event analyzing system, event analyzing method, and non-transitory computer readable storage medium | |
JP6605357B2 (en) | Anomaly detection apparatus, anomaly detection system and method | |
CN111898691A (en) | River sudden water pollution early warning tracing method, system, terminal and medium | |
CN107949812A (en) | Combined method for detecting anomalies in a water distribution system | |
CN101025093B (en) | Method for determining limit exceedance | |
CN103953098A (en) | Pipe network loss monitoring method | |
CN111597223A (en) | Fault early warning processing method, device and system | |
CN114623990B (en) | Monitoring and leakage positioning method, device, boiler, system and storage medium | |
US20210054825A1 (en) | Wind turbine control method and device, controller, and control system | |
CN112966374A (en) | Intelligent power grid power line safety real-time online prediction early warning management system | |
CN117192042A (en) | Intelligent mine gas inspection system and method | |
CN104359590A (en) | Reduction box operation temperature monitoring method and device | |
CN116226263A (en) | Renewable energy source visual intelligent pipe control method and system | |
KR102560572B1 (en) | System and Method for detecting tube leakage using state signal of power generation plant | |
CN117370818B (en) | Intelligent diagnosis method and intelligent environment-friendly system for water supply and drainage pipe network based on artificial intelligence | |
US11375677B2 (en) | Fluid conservation system and methods of use | |
CN118328004A (en) | Static pressure resetting variable frequency control method of centralized flue system | |
KR102545240B1 (en) | Apparatus and method for predicting of the tube wall thinning | |
CN117189309A (en) | Noise reduction method and device for intelligent computation center diesel generator set | |
CN110503254A (en) | One kind leaking method for early warning based on markovian nonmetal pipeline | |
CN115310681A (en) | Boiler operation safety prediction method, device, medium and electronic equipment | |
CN116320824A (en) | Thing allies oneself with electric energy meter of electrified energy quality module | |
Wang et al. | Research on water supply network pressure prediction using PSO-BP neural network algorithm | |
CN117763429A (en) | Method, system, storage medium and equipment for identifying operation condition of finished oil pipeline |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |