CN118243378B - Fault diagnosis method and system for cutting speed reducer of cantilever type heading machine - Google Patents
Fault diagnosis method and system for cutting speed reducer of cantilever type heading machine Download PDFInfo
- Publication number
- CN118243378B CN118243378B CN202410666954.XA CN202410666954A CN118243378B CN 118243378 B CN118243378 B CN 118243378B CN 202410666954 A CN202410666954 A CN 202410666954A CN 118243378 B CN118243378 B CN 118243378B
- Authority
- CN
- China
- Prior art keywords
- speed reducer
- real
- normal
- fault
- data
- 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
- 239000003638 chemical reducing agent Substances 0.000 title claims abstract description 554
- 238000005520 cutting process Methods 0.000 title claims abstract description 104
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000003745 diagnosis Methods 0.000 title claims abstract description 50
- 239000013598 vector Substances 0.000 claims abstract description 134
- 239000002131 composite material Substances 0.000 claims abstract description 80
- 238000012423 maintenance Methods 0.000 claims abstract description 39
- 238000012544 monitoring process Methods 0.000 claims abstract description 15
- 230000003213 activating effect Effects 0.000 claims abstract description 11
- 150000001875 compounds Chemical class 0.000 claims abstract description 6
- 230000005856 abnormality Effects 0.000 claims description 78
- 238000005461 lubrication Methods 0.000 claims description 71
- 230000008447 perception Effects 0.000 claims description 53
- 238000004364 calculation method Methods 0.000 claims description 36
- 230000002159 abnormal effect Effects 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 21
- 238000001514 detection method Methods 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 15
- 238000012937 correction Methods 0.000 claims description 15
- 230000004927 fusion Effects 0.000 claims description 15
- 238000010276 construction Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 10
- 230000008569 process Effects 0.000 description 12
- 238000004422 calculation algorithm Methods 0.000 description 9
- 238000010801 machine learning Methods 0.000 description 6
- 239000000306 component Substances 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 239000003245 coal Substances 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000005641 tunneling Effects 0.000 description 2
- 238000012952 Resampling Methods 0.000 description 1
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000013021 overheating Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification 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
- G01M13/00—Testing of machine parts
- G01M13/02—Gearings; Transmission mechanisms
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a fault diagnosis method and a system of a cutting speed reducer of a cantilever type heading machine, and relates to the field of mechanical fault diagnosis and maintenance, wherein the method comprises the following steps: real-time monitoring is carried out on the target cutting speed reducer according to a speed reducer sensing array which is arranged in advance, and a real-time speed reducer sensing data source is obtained; constructing a normal deviation vector set of the speed reducer; activating a multi-element speed reducer fault sensing channel to obtain a speed reducer compound fault sensing result; loading a real-time operation data stream of a target cutting speed reducer, correcting a composite fault sensing result of the speed reducer, and generating a speed reducer fault sensing report; and carrying out fault operation and maintenance on the target cutting speed reducer by combining the speed reducer fault operation and maintenance library. The technical problems of low diagnosis precision, high false alarm rate and inaccurate fault positioning existing in the fault diagnosis of the cutting speed reducer of the existing cantilever type heading machine are solved, the technical effects of improving the diagnosis precision, reducing the false alarm rate and realizing accurate fault positioning are achieved.
Description
Technical Field
The application relates to the field of mechanical fault diagnosis and maintenance, in particular to a fault diagnosis method and system for a cutting speed reducer of a cantilever type heading machine.
Background
The cantilever type heading machine is widely applied to the engineering fields of coal mines, tunnels and the like, is mainly used for the tunneling operation of the roadways, and the cutting speed reducer is a core component of the cantilever type heading machine and is responsible for transmitting the torque of a cutting motor to a cutting head so as to drive the cutting head to cut. Due to the complexity and variability of the working environment of the heading machine, the cutting speed reducer can suffer from various impacts and vibrations during operation, so that the performance of the cutting speed reducer is reduced or the cutting speed reducer fails, and therefore, the fault diagnosis of the cutting speed reducer of the cantilever type heading machine is very important. In the fault diagnosis of the existing cantilever type heading machine cutting speed reducer, the traditional sensor monitoring and data analysis methods are generally relied on, and although the methods can realize the state monitoring and fault diagnosis of the speed reducer, the existing methods often only rely on single sensor data for fault diagnosis, the comprehensive analysis and utilization of multi-source data are lacked, so that the diagnosis precision is limited, and due to the complexity and the variability of working condition environments, the existing methods are easy to misjudge when abnormal data are processed, the misinformation rate is higher, the difficulty and the cost of fault processing are increased, meanwhile, the existing methods often only can provide a rough fault range in terms of fault positioning, and specific fault components or positions cannot be accurately obtained, so that the efficiency and the accuracy of fault processing are affected.
In the related art at the present stage, the fault diagnosis of the cutting speed reducer of the cantilever type heading machine has the technical problems of low diagnosis precision, high false alarm rate and inaccurate fault positioning.
Disclosure of Invention
The application provides the fault diagnosis method and the fault diagnosis system for the cutting speed reducer of the cantilever type heading machine, and the technical effects of improving the diagnosis precision, reducing the false alarm rate, and realizing accurate fault positioning are achieved by comprehensively utilizing the technical means of multi-source sensing data, constructing a normal deviation vector set, activating a multi-element fault sensing channel and the like.
The application provides a fault diagnosis method of a cutting speed reducer of a cantilever type heading machine, which comprises the following steps:
Real-time monitoring is carried out on a target cutting speed reducer according to a speed reducer sensing array which is arranged in advance, so that a real-time speed reducer sensing data source is obtained, wherein the real-time speed reducer sensing data source comprises a speed reducer vibration sensing data stream, a speed reducer lubrication sensing data stream and a speed reducer temperature sensing data stream, and the real-time speed reducer sensing data source has real-time working condition characteristic data and real-time working environment characteristic data which correspond to the marks;
Constructing a normal deviation vector set of the speed reducer, wherein the real-time speed reducer perceived data source is subjected to multi-element normal deviation calculation through the real-time working condition characteristic data and the real-time working environment characteristic data to obtain the normal deviation vector set of the speed reducer, and the normal deviation vector set of the speed reducer comprises a vibration normal deviation vector, a lubrication normal deviation vector and a temperature normal deviation vector;
activating a multi-element speed reducer fault sensing channel based on the real-time working condition characteristic data, the real-time working environment characteristic data and the normal deviation vector set of the speed reducer to obtain a speed reducer compound fault sensing result;
loading a real-time operation data stream of the target cutting speed reducer, correcting a composite fault sensing result of the speed reducer based on the real-time operation data stream, and generating a speed reducer fault sensing report;
And carrying out fault operation and maintenance on the target cutting speed reducer by combining a speed reducer fault operation and maintenance library based on the speed reducer fault perception report.
In a possible implementation, a real-time retarder aware data source is obtained, the following processing is performed:
the state source data of sensing equipment corresponding to each data flow in the sensing data source of the real-time speed reducer is called;
Carrying out depth abnormality recognition based on the state source data of the sensing equipment to obtain a sensing equipment abnormality recognition result and an equipment abnormality depth index;
judging whether the equipment abnormality depth index is smaller than an equipment abnormality depth threshold value or not;
if the equipment abnormality depth index is larger than or equal to the equipment abnormality depth threshold, performing sensing compensation based on the sensing equipment abnormality identification result to obtain abnormality sensing compensation data;
and carrying out mapping correction on the real-time speed reducer perception data source based on the abnormal perception compensation data.
In a possible implementation manner, a normal deviation vector set of the speed reducer is constructed, wherein the real-time speed reducer sensing data source is subjected to multi-element normal deviation calculation through the real-time working condition characteristic data and the real-time working environment characteristic data to obtain the normal deviation vector set of the speed reducer, the normal deviation vector set of the speed reducer comprises a vibration normal deviation vector, a lubrication normal deviation vector and a temperature normal deviation vector, and the following processing is performed:
Performing normal record registration of the speed reducer according to the real-time working condition characteristic data and the real-time working environment characteristic data to obtain a registration speed reducer normal record set;
performing multi-element normal deviation calculation on the vibration sensing data flow of the speed reducer based on the registration speed reducer normal record set, and constructing the vibration normal deviation vector;
performing multi-element normal deviation calculation on the lubrication sensing data flow of the speed reducer based on the registration speed reducer normal record set, and constructing the lubrication normal deviation vector;
and carrying out multi-element normal deviation calculation on the temperature sensing data flow of the speed reducer based on the registration speed reducer normal record set, and constructing the temperature normal deviation vector.
In a possible implementation manner, the normal recording registration of the speed reducer is performed according to the real-time working condition characteristic data and the real-time working environment characteristic data, a registration speed reducer normal recording set is obtained, and the following processing is performed:
Performing normal sample global retrieval based on big data to obtain a plurality of groups of normal perception records of the speed reducer;
Traversing the plurality of groups of normal sensing records of the speed reducers, and extracting a first group of normal sensing records of the speed reducers, wherein the first group of normal sensing records of the speed reducers comprise a first normal vibration data record of the speed reducers, a first normal lubrication data record of the speed reducers and a first normal temperature data record of the speed reducers, and first historical working condition characteristic data and first historical working environment characteristic data corresponding to the first normal vibration data record of the speed reducers, the first normal lubrication data record of the speed reducers and the first normal temperature data record of the speed reducers;
Based on the real-time working condition characteristic data and the real-time working environment characteristic data, carrying out registration analysis on the first historical working condition characteristic data and the first historical working environment characteristic data respectively to obtain a first working condition characteristic registration coefficient and a first environment characteristic registration coefficient;
Weighting calculation is carried out on the first working condition characteristic registration coefficient and the first environment characteristic registration coefficient based on a preset normal registration weight condition, and a first characteristic composite registration coefficient is obtained;
Judging whether the first characteristic composite registration coefficient meets a preset composite registration constraint;
And if the first characteristic composite registration coefficient meets the preset composite registration constraint, adding the first speed reducer normal vibration data record, the first speed reducer normal lubrication data record and the first speed reducer normal temperature data record to the registration speed reducer normal record set.
In a possible implementation manner, the registration reducer normal record set is used for carrying out multi-element normal deviation calculation on the reducer vibration sensing data flow, constructing the vibration normal deviation vector, and executing the following processing:
Classifying the registration reducer normal record set to obtain a registration normal vibration record set, a registration normal lubrication record set and a registration normal temperature record set;
Evaluating the concentrated value according to the registration normal vibration record set to obtain registration normal vibration concentrated quantity;
And carrying out multi-feature deviation calculation on the vibration sensing data flow of the speed reducer based on the registration normal vibration concentration quantity, and generating the vibration normal deviation vector.
In a possible implementation manner, based on the real-time working condition characteristic data, the real-time working environment characteristic data and the normal deviation vector set of the speed reducer, activating a multi-speed reducer fault sensing channel to obtain a speed reducer composite fault sensing result, and executing the following processing:
The multi-speed reducer fault sensing channel comprises a first speed reducer fault sensing channel, a second speed reducer fault sensing channel and a third speed reducer fault sensing channel;
inputting the real-time working condition characteristic data, the real-time working environment characteristic data and the vibration normal deviation vector into the first speed reducer fault sensing channel to generate a first speed reducer fault sensing result;
inputting the real-time working condition characteristic data, the real-time working environment characteristic data and the lubrication normal deviation vector into the second speed reducer fault sensing channel to obtain a second speed reducer fault sensing result;
Inputting the real-time working condition characteristic data, the real-time working environment characteristic data and the temperature normal deviation vector into the third speed reducer fault sensing channel to obtain a third speed reducer fault sensing result;
And performing fault fusion according to the first speed reducer fault sensing result, the second speed reducer fault sensing result and the third speed reducer fault sensing result to generate a speed reducer compound fault sensing result.
In a possible implementation manner, correcting the composite fault sensing result of the speed reducer based on the real-time job data stream, generating a speed reducer fault sensing report, and performing the following processing:
Performing abnormality detection according to the real-time operation data stream to obtain an operation abnormality detection result;
performing fault prediction on the target cutting speed reducer based on the operation abnormality detection result to generate an operation abnormality fault prediction result;
and carrying out fault fusion on the composite fault sensing result of the speed reducer based on the operation abnormal fault prediction result to obtain the speed reducer fault sensing report.
The application also provides a fault diagnosis system of the cutting speed reducer of the cantilever type heading machine, which comprises the following steps:
The real-time speed reducer perception data source acquisition module is used for monitoring the target cutting speed reducer in real time according to a speed reducer sensing array which is arranged in advance to obtain a real-time speed reducer perception data source, wherein the real-time speed reducer perception data source comprises a speed reducer vibration perception data stream, a speed reducer lubrication perception data stream and a speed reducer temperature perception data stream, and the real-time speed reducer perception data source is provided with real-time working condition characteristic data and real-time working environment characteristic data which correspond to the marks;
The speed reducer normal deviation vector set construction module is used for constructing a speed reducer normal deviation vector set, wherein the real-time speed reducer perceived data source is subjected to multi-element normal deviation calculation through the real-time working condition characteristic data and the real-time working environment characteristic data to obtain the speed reducer normal deviation vector set, and the speed reducer normal deviation vector set comprises a vibration normal deviation vector, a lubrication normal deviation vector and a temperature normal deviation vector;
The speed reducer composite fault sensing result acquisition module is used for activating a multi-speed reducer fault sensing channel based on the real-time working condition characteristic data, the real-time working environment characteristic data and the speed reducer normal deviation vector set to acquire a speed reducer composite fault sensing result;
The speed reducer composite fault sensing result correction module is used for loading a real-time operation data stream of the target cutting speed reducer, correcting the speed reducer composite fault sensing result based on the real-time operation data stream and generating a speed reducer fault sensing report;
The target cutting speed reducer fault operation and maintenance module is used for carrying out fault operation and maintenance on the target cutting speed reducer by combining a speed reducer fault operation and maintenance library based on the speed reducer fault perception report.
According to the fault diagnosis method and system for the cantilever type heading machine cutting speed reducer, firstly, a target cutting speed reducer is monitored in real time according to a speed reducer sensing array which is arranged in advance, a real-time speed reducer sensing data source is obtained, wherein the real-time speed reducer sensing data source comprises speed reducer vibration sensing data flow, speed reducer lubrication sensing data flow and speed reducer temperature sensing data flow, the real-time speed reducer sensing data source is provided with real-time working condition characteristic data and real-time working environment characteristic data which are correspondingly identified, a speed reducer normal deviation vector set is built, the real-time speed reducer sensing data source is subjected to multi-element normal deviation calculation through the real-time working condition characteristic data and the real-time working environment characteristic data, the speed reducer normal deviation vector set comprises vibration normal deviation vector, lubrication normal deviation vector and temperature normal deviation vector, then a multi-component speed reducer fault sensing channel is activated based on the real-time working condition characteristic data flow, the speed reducer composite fault sensing result is obtained, the real-time working condition characteristic data flow of the target cutting speed reducer is loaded, the speed reducer fault sensing result is accurately reported based on the speed reducer normal deviation vector, and the speed reducer normal deviation is accurately sensed, and the fault is accurately sensed by the speed reducer is accurately reported based on the speed reducer operation fault sensing device.
Drawings
In order to more clearly illustrate the technical solution of the embodiments of the present application, the following description will briefly refer to the accompanying drawings of the embodiments of the present application, in which flowcharts are used to illustrate operations performed by systems according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Fig. 1 is a schematic flow chart of a fault diagnosis method for a cutting speed reducer of a cantilever type heading machine according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a fault diagnosis system of a cutting speed reducer of a cantilever type heading machine according to an embodiment of the present application.
Detailed Description
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described in further detail with reference to the accompanying drawings, and the described embodiments should not be construed as limiting the present application, and all other embodiments obtained by those skilled in the art without making any inventive effort are within the scope of the present application.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict, the term "first\second" being referred to merely as distinguishing between similar objects and not representing a particular ordering for the objects. The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements that are expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or modules that may not be expressly listed or inherent to such process, method, article, or apparatus, and unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used herein is for the purpose of describing embodiments of the application only.
The embodiment of the application provides a fault diagnosis method of a cutting speed reducer of a cantilever type heading machine, as shown in fig. 1, the method comprises the following steps:
Step S100, monitoring a target cutting speed reducer in real time according to a speed reducer sensing array which is arranged in advance to obtain a real-time speed reducer sensing data source, wherein the real-time speed reducer sensing data source comprises a speed reducer vibration sensing data stream, a speed reducer lubrication sensing data stream and a speed reducer temperature sensing data stream, and the real-time speed reducer sensing data source has real-time working condition characteristic data and real-time working environment characteristic data which correspond to the identification. Specifically, the target cutting speed reducer refers to a specific cutting speed reducer which needs fault diagnosis and monitoring, in the cantilever type heading machine, the cutting speed reducer is a mechanical component and is responsible for transmitting power and adjusting the rotating speed of a cutting head so as to meet cutting requirements under different working conditions, a speed reducer sensing array which is arranged on the target cutting speed reducer in advance is started, the speed reducer sensing array is activated and checked, the sensors are ensured to be in a normal working state, and the measuring precision and the response speed meet the requirements of fault diagnosis. Vibration, lubrication and temperature of the target cutting speed reducer are monitored in real time respectively by using a vibration sensor, a lubrication sensor and a temperature sensor in the speed reducer sensing array, wherein the vibration sensor records vibration characteristic data such as vibration frequency, vibration amplitude and the like of the target cutting speed reducer, the lubrication sensor monitors lubrication state data such as lubrication oil quantity, oil pressure, oil quality and oil temperature and the like of the target cutting speed reducer, and the temperature sensor measures key part temperatures of the target cutting speed reducer, such as bearing temperature, gear box temperature and the like. And transmitting the acquired vibration, lubrication and temperature data in real time in a data stream form to obtain a speed reducer vibration sensing data stream, a speed reducer lubrication sensing data stream and a speed reducer temperature sensing data stream, wherein the three data streams are combined together to form a real-time speed reducer sensing data source. And extracting characteristics of the vibration sensing data stream of the speed reducer, the lubrication sensing data stream of the speed reducer and the temperature sensing data stream of the speed reducer, and extracting characteristic data capable of reflecting the real-time working condition and the real-time working environment of the target cutting speed reducer, wherein the characteristic data of the real-time working condition comprise real-time working condition attribute parameters of the target cutting speed reducer. Illustratively, the real-time operating condition attribute parameter may be a continuous tunneling condition, an impact load condition, a variable speed cutting condition, or the like. The real-time operation environment characteristic data comprise coal rock hardness, environment temperature, humidity, dust concentration and the like, and corresponding identifiers are added for each characteristic data for subsequent data processing and analysis.
In one possible implementation, the step S100 further includes a step S110 of obtaining a real-time retarder perception data source, and retrieving sensing device status source data corresponding to each data flow in the real-time retarder perception data source. Specifically, according to the organization structure of the real-time speed reducer sensing data source, the corresponding relation between each data stream and a specific sensor is identified, state source data of the sensing devices are called from the sensors or a data acquisition system connected with the sensors, the state source data of the sensing devices comprise the running time, the calibration state, the signal strength, the error code, the environment information and the like of the sensors, and the state source data of the sensing devices reflect the health condition and the working state of the sensors. And step S120, carrying out depth abnormality recognition based on the state source data of the sensing equipment to obtain a sensing equipment abnormality recognition result and an equipment abnormality depth index. Specifically, preprocessing sensor state source data, including data cleaning, denoising, normalization and other operations, eliminating abnormal values and interference in the data, extracting key features including response time, signal stability, error rate and the like of a sensor from the preprocessed sensor state source data, wherein the features reflect the performance and working state of the sensor, establishing a sensor abnormality recognition model based on historical data and expert knowledge by using a machine learning or deep learning algorithm, judging whether the sensor is in an abnormal state according to the extracted features, inputting the sensor state source data acquired in real time into the sensor abnormality recognition model, the sensor abnormality recognition model evaluates the state of each sensor and outputs a sensing device abnormality recognition result, which may be expressed in the form of two categories (normal/abnormal) or multiple categories (different abnormality types). Meanwhile, according to the abnormal recognition result of the sensing equipment, calculating an equipment abnormal depth index, wherein the equipment abnormal depth index is obtained by setting different weights and thresholds and comprehensively calculating according to a plurality of factors such as the occurrence frequency, duration time, influence range and the like of the abnormality, and is used for quantifying the severity of the abnormal condition of the sensor. Step S130, judging whether the equipment abnormality depth index is smaller than an equipment abnormality depth threshold. Specifically, the device abnormality depth threshold is a preset value, and is used for judging whether the sensor abnormality reaches the degree of intervention, and the device abnormality depth threshold is set based on performance requirements, historical data, expert experience, industry standards and the like of the system. And comparing the equipment abnormality depth index with an equipment abnormality depth threshold, and if the equipment abnormality depth index is smaller than the equipment abnormality depth threshold, indicating that the abnormality degree of the sensor does not reach the level of intervention, and continuing normal operation. And step S140, if the equipment abnormality depth index is larger than or equal to the equipment abnormality depth threshold, performing sensing compensation based on the sensing equipment abnormality identification result to obtain abnormality sensing compensation data. Specifically, if the device abnormality depth index is greater than or equal to the device abnormality depth threshold, indicating that there is a relatively serious abnormality in the sensor, in which case further measures need to be taken to obtain, for each of the identified abnormality sensing devices, corresponding sensing device abnormality recognition results that provide detailed information about the type, extent and possible cause of the abnormality from step S120, select an appropriate perceptual compensation method (filtering, interpolation, calibration, model correction, etc.) based on the sensing device abnormality recognition results, process the output data of the abnormality sensing device, The method comprises the steps of correcting, replacing or reconstructing original data, eliminating the influence of abnormality on sensing data, generating abnormal sensing compensation data after sensing compensation processing, wherein the abnormal sensing compensation data reflects the actual state of a target cutting speed reducer. And step S150, carrying out mapping correction on the real-time speed reducer perception data source based on the abnormal perception compensation data. Namely, the abnormal sensing compensation data is updated to the real-time speed reducer sensing data source to replace or supplement the original abnormal data, so that the real-time speed reducer sensing data source which is more accurate and reliable is formed. By finding and processing the sensor abnormality, the realization method obtains a more accurate and reliable real-time speed reducer sensing data source, achieves the technical effects of improving the accuracy and the reliability of data and avoiding the subsequent erroneous judgment or missed judgment caused by the sensor abnormality.
Step 200, a normal deviation vector set of the speed reducer is constructed, wherein the real-time speed reducer perceived data source is subjected to multi-element normal deviation calculation through the real-time working condition characteristic data and the real-time working environment characteristic data to obtain the normal deviation vector set of the speed reducer, and the normal deviation vector set of the speed reducer comprises a vibration normal deviation vector, a lubrication normal deviation vector and a temperature normal deviation vector. Specifically, the real-time working condition characteristic data and the real-time working environment characteristic data are matched with data in a preset normal working state, deviation values between the real-time data and the normal data in a sensing data source of the real-time speed reducer are calculated according to the matching result, the deviation values comprise vibration deviation, lubrication deviation and temperature deviation, the calculated deviation values are subjected to normalization processing, differences between different data types and dimensions are eliminated, normal deviation values are obtained, the deviation degree of the real-time data and the normal state is reflected by the normal deviation values, potential faults or anomalies are identified, the normal deviation values are combined into vectors according to corresponding categories (vibration, lubrication and temperature), and a vibration normal deviation vector, a lubrication normal deviation vector and a temperature normal deviation vector are formed together to form a speed reducer normal deviation vector set.
In a possible implementation manner, step S200 further includes step S210, performing normal record registration of the speed reducer according to the real-time working condition feature data and the real-time working environment feature data, to obtain a registered normal record set of the speed reducer. Specifically, key features capable of reflecting the operation state and the operation environment of the target cutting speed reducer are extracted from the real-time working condition feature data and the real-time operation environment feature data through methods such as statistical analysis, a machine learning algorithm or expert knowledge, a registration algorithm (registration based on features, registration based on transformation and the like) is applied according to the extracted features, the real-time data and the known speed reducer records in a normal state are aligned or calibrated by minimizing differences or maximizing similarity between the two, the deviation or differences between the two are eliminated, and a group of registered speed reducer records in the normal state corresponding to the real-time data is obtained after the registration is completed, and the records form a registration speed reducer normal record set. And step S220, performing multi-element normal deviation calculation on the vibration sensing data flow of the speed reducer based on the registration speed reducer normal record set, and constructing the vibration normal deviation vector. Specifically, the vibration sensing data stream of the speed reducer is aligned with vibration data in a registration speed reducer normal record set through methods of timestamp matching, interpolation or resampling and the like, so that consistency of time sequences is ensured. And calculating the normal deviation between the vibration sensing data flow of the speed reducer and the vibration data in the registration speed reducer normal record set by calculating the deviation value of each time point or data point by using a multivariate statistical analysis method, and organizing the calculated vibration normal deviation values into a vector form according to a time sequence or other proper sequences to form a vibration normal deviation vector. Step S230, performing multi-element normal deviation calculation on the lubrication sensing data flow of the speed reducer based on the registration speed reducer normal record set, and constructing the lubrication normal deviation vector; and step S240, performing multi-element normal deviation calculation on the temperature sensing data flow of the speed reducer based on the registration speed reducer normal record set, and constructing the temperature normal deviation vector. Specifically, the same processing method as that used for calculating the vibration normal deviation vector is adopted to respectively construct the lubrication normal deviation vector and the temperature normal deviation vector, and finally the normal deviation vector set of the speed reducer comprising the vibration normal deviation vector, the lubrication normal deviation vector and the temperature normal deviation vector is obtained. According to the implementation mode, through accurately analyzing and processing various perceived data streams of the target cutting speed reducer, a set of normal deviation vector sets capable of reflecting the running state of the target cutting speed reducer is constructed, and therefore the technical effects of effectively monitoring and maintaining the target cutting speed reducer are achieved.
In a possible implementation manner, step S210 further includes step S211, performing a normal sample global search based on big data, to obtain multiple sets of normal sensing records of the speed reducer. Specifically, the big data storage library is connected, search conditions are defined, the search conditions comprise the model number, the working environment, the working time period and the like of the speed reducer, global search is executed, a plurality of groups of normal perception records of the speed reducer are screened out from the big data storage library according to the search conditions, the normal perception records of the speed reducer are a series of data records which are perceived by the speed reducer of the target cutting speed reducer or the speed reducer of the same type as the target cutting speed reducer in a normal operation state, and the data are acquired under the normal working condition and the working environment of the speed reducer of the same type as the target cutting speed reducer. Step S212, traversing the plurality of groups of normal sensing records of the speed reducers, and extracting a first group of normal sensing records of the speed reducers, wherein the first group of normal sensing records of the speed reducers comprise a first normal vibration data record of the speed reducers, a first normal lubrication data record of the speed reducers and a first normal temperature data record of the speed reducers, and first history working condition characteristic data and first history working environment characteristic data corresponding to the first normal vibration data record of the speed reducers, the first normal lubrication data record of the speed reducers and the first normal temperature data record of the speed reducers. Specifically, a traversing pointer is initialized to point to the starting position of a plurality of groups of normal sensing records of the speed reducer, each group of records in the plurality of groups of normal sensing records of the speed reducer is traversed circularly, in each cycle, the normal sensing record of the speed reducer pointed by the current pointer, corresponding working condition characteristic data and operation environment characteristic data are extracted, a first group of normal sensing records of the speed reducer are extracted from the traversing process, and the first group of normal sensing records of the speed reducer are any group of normal sensing records of the plurality of groups of normal sensing records of the speed reducer, and comprise normal data records of vibration, lubrication and temperature, and meanwhile, historical working condition characteristic data and historical operation environment characteristic data corresponding to the group of normal data are extracted. step S213, based on the real-time working condition characteristic data and the real-time working environment characteristic data, performing registration analysis on the first historical working condition characteristic data and the first historical working environment characteristic data respectively to obtain a first working condition characteristic registration coefficient and a first environment characteristic registration coefficient. Specifically, according to the characteristics and the monitoring requirements of the target cutting speed reducer, key characteristics with the same meaning and unit are extracted from the real-time working condition characteristic data and the first historical working condition characteristic data, and key characteristics with the same meaning and unit, such as temperature and the like, are extracted from the real-time working environment characteristic data and the first historical working environment characteristic data. For each feature, similarity measures (e.g., euclidean distance, correlation coefficients, dynamic time warping, etc.) are used to calculate the similarity between the real-time data and the historical data. According to the similarity calculation result, calculating a registration coefficient for each feature, wherein the registration coefficient can be a numerical value between 0 and 1, and the higher the numerical value is, the better the matching degree is; the lower the numerical value is, the larger the representation difference is, and for the working condition characteristic data, a first working condition characteristic registration coefficient is obtained; and obtaining a first environmental characteristic registration coefficient for the operation environmental characteristic data. And step S214, carrying out weighted calculation on the first working condition characteristic registration coefficient and the first environment characteristic registration coefficient based on a preset normal registration weight condition to obtain a first characteristic composite registration coefficient. Specifically, the preset normal registration weight condition is obtained based on actual experience, test data or theoretical analysis, the relative importance of each of the working condition features and the working environment features in the registration process is reflected, corresponding weights are respectively distributed to the first working condition feature registration coefficient and the first environment feature registration coefficient according to the preset normal registration weight condition, a weighting formula or algorithm is used for multiplying each registration coefficient by the corresponding weight, and the results are added to obtain the first feature composite registration coefficient. Step S215, judging whether the first characteristic composite registration coefficient meets a preset composite registration constraint; step S216, if the first feature composite registration coefficient meets the preset composite registration constraint, adding the first speed reducer normal vibration data record, the first speed reducer normal lubrication data record and the first speed reducer normal temperature data record to the registration speed reducer normal record set. Specifically, the preset composite registration constraint is formulated based on historical data, experience knowledge or business requirements, and is used for screening out a historical record with higher matching degree with real-time data, comparing a first characteristic composite registration coefficient with the preset composite registration constraint, judging whether the first characteristic composite registration coefficient is larger than or equal to a certain threshold value or within a certain specific numerical range, if the first characteristic composite registration coefficient meets the constraint condition, indicating that the real-time acquired working condition characteristic and working environment characteristic data have higher matching degree with the first group of historical data, extracting the normal vibration data record, the normal lubrication data record and the normal temperature data record of the first group of speed reducers, adding the normal vibration data record, the normal lubrication data record and the normal temperature data record into a normal record set of the speed reducers, and updating the state information of the normal record set of the speed reducers, such as the number of records, last update time, etc. according to the implementation mode, through the data registration and record screening flow, records with high matching degree with real-time data are screened out from a large amount of historical data, and the technical effect of providing accurate and reliable data base is achieved.
In a possible implementation manner, step S220 further includes step S221 of classifying the registration reducer normal record set to obtain a registration normal vibration record set, a registration normal lubrication record set and a registration normal temperature record set. Specifically, three empty sets are created and are respectively used for storing registration normal vibration records, registration normal lubrication records and registration normal temperature records, each record in the registration reducer normal record set is registered one by one, and is respectively added into a corresponding classification set according to the type (vibration, lubrication and temperature) of each record, and after all records are traversed, classification is finished, so that three classified record sets are obtained. And step S222, evaluating the concentration value according to the registration normal vibration record set to obtain registration normal vibration concentration quantity. Specifically, a statistical method (such as a mean value, a median value, a mode value and the like) is used for evaluating the concentrated value of the concentrated vibration data of the registration normal vibration record, so that the registration normal vibration concentrated quantity is obtained, and the registration normal vibration concentrated quantity represents the vibration characteristic of the target cutting speed reducer in a normal working state. And S223, performing multi-feature deviation calculation on the vibration sensing data flow of the speed reducer based on the registration normal vibration concentration quantity, and generating the vibration normal deviation vector. Specifically, according to the characteristics and monitoring requirements of the target cutting speed reducer, a plurality of characteristics including amplitude, frequency, waveform parameters and the like are extracted from the vibration sensing data stream of the speed reducer, and for each extracted characteristic, the deviation between the extracted characteristic and the registration normal vibration concentration quantity is calculated through subtraction, division or other mathematical operations. The bias values of all features are combined into one vector, i.e. a vibration normal bias vector. According to the realization mode, the registration normal record set is classified, the registration normal vibration record set is subjected to concentrated value evaluation, and the vibration sensing data flow of the speed reducer is subjected to multi-feature deviation calculation, so that the data processing flow is simplified, the analysis efficiency is improved, the more accurate and more comprehensive vibration normal deviation vector is obtained, and the technical effect of providing more reliable support for fault diagnosis of the target cutting speed reducer is achieved.
And step S300, activating a multi-component speed reducer fault sensing channel based on the real-time working condition characteristic data, the real-time working environment characteristic data and the normal deviation vector set of the speed reducer, and obtaining a speed reducer compound fault sensing result. Specifically, real-time data (real-time working condition characteristic data and real-time working environment characteristic data) and data in a normal deviation vector set of the speed reducer are matched and aligned, corresponding relation between the real-time working condition characteristic data and the real-time working environment characteristic data in time and space is ensured, a multi-element speed reducer fault sensing channel is initialized according to the real-time working condition characteristic data, the real-time working environment characteristic data and the normal deviation vector set of the speed reducer, corresponding parameters such as a threshold value, a weight and a filter are configured for each speed reducer fault sensing channel and used for sensing and identifying fault characteristics, the multi-element speed reducer fault sensing channel is activated and started, each activated speed reducer fault sensing channel processes and analyzes the real-time data, characteristic information related to faults is extracted, weighted average, maximum voting or other fusion algorithms are adopted for fusing processing results of the channels, and composite fault sensing results of the speed reducer including information such as fault type, position and severity are generated according to fused results, and the information is used for providing basis for subsequent fault diagnosis and maintenance.
In one possible implementation, step 300 further includes step S310, where the multiple retarder fault sensing passages include a first retarder fault sensing passage, a second retarder fault sensing passage, and a third retarder fault sensing passage. Specifically, the multiple speed reducer fault sensing channels include three fault sensing channels, wherein a first speed reducer fault sensing channel is aimed at vibration characteristics, a second speed reducer fault sensing channel is aimed at lubrication states, a third speed reducer fault sensing channel is aimed at temperature characteristics, and each channel is provided with a specific algorithm and model for analyzing fault characteristics of corresponding types. Step S320, inputting the real-time working condition characteristic data, the real-time working environment characteristic data and the vibration normal deviation vector into the first speed reducer fault sensing channel, and generating a first speed reducer fault sensing result. Specifically, the first speed reducer fault sensing channel utilizes a pre-trained vibration analysis model (based on a machine learning or deep learning model) to perform feature extraction and pattern recognition on vibration data to generate a first speed reducer fault sensing result, wherein the first speed reducer fault sensing result can be a probability value to represent the possibility of the fault of the target cutting speed reducer in the current vibration state. And step S330, inputting the real-time working condition characteristic data, the real-time working environment characteristic data and the lubrication normal deviation vector into the second speed reducer fault sensing channel to obtain a second speed reducer fault sensing result. Specifically, the second speed reducer fault sensing channel utilizes a lubrication state evaluation algorithm to process and analyze lubrication data, identify poor lubrication or other fault characteristics related to lubrication, and generate a second speed reducer fault sensing result according to the analysis result, wherein the second speed reducer fault sensing result can also be a probability value representing the possibility of faults. And S340, inputting the real-time working condition characteristic data, the real-time working environment characteristic data and the temperature normal deviation vector into the third speed reducer fault sensing channel to obtain a third speed reducer fault sensing result. Specifically, the third speed reducer fault sensing channel performs anomaly detection and trend analysis on the temperature data through a temperature monitoring and analysis model, identifies faults caused by overheating or other temperature related problems, and generates a third speed reducer fault sensing result based on the analysis. And step S350, performing fault fusion according to the first speed reducer fault sensing result, the second speed reducer fault sensing result and the third speed reducer fault sensing result to generate a speed reducer composite fault sensing result. Specifically, the first speed reducer fault sensing result, the second speed reducer fault sensing result and the third speed reducer fault sensing result are fused by adopting methods such as rule-based fusion, probability-based fusion or machine learning-based fusion, and according to the fault sensing result of each channel and the weight thereof, a plurality of factors are comprehensively considered to generate a final speed reducer composite fault sensing result which comprehensively reflects the fault state of the target cutting speed reducer, including a plurality of possible fault types and severity. According to the implementation mode, the complex faults of the target cutting speed reducer can be more accurately identified by designing the fault sensing channels of the multi-speed reducer and performing fault fusion processing, so that the technical effects of improving the reliability and efficiency of fault diagnosis are achieved.
And step 400, loading a real-time operation data stream of the target cutting speed reducer, correcting the composite fault sensing result of the speed reducer based on the real-time operation data stream, and generating a speed reducer fault sensing report. Specifically, the real-time operation data stream is an operation data stream of the target cutting speed reducer acquired in real time through a sensor, a monitoring system or other data acquisition equipment, and comprises various types of parameters such as real-time output rotating speed, real-time load, real-time output torque, real-time output power and the like, the real-time operation data stream and a speed reducer composite fault sensing result are matched and aligned, the corresponding relation between the real-time operation data stream and the speed reducer composite fault sensing result in time and space is ensured, the real-time operation data stream and the speed reducer composite fault sensing result are compared with characteristic parameters in the real-time operation data stream to verify and correct the speed reducer composite fault sensing result, the accuracy and the reliability of the speed reducer composite fault sensing result are judged, and errors caused by operation condition changes are eliminated. And carrying out necessary adjustment on the composite fault sensing result of the speed reducer according to the verification result of the real-time operation data stream data, and carrying out corresponding correction and updating if the real-time operation data stream data indicate that the composite fault sensing result of the speed reducer has deviation or misjudgment. And (3) sorting the corrected related information such as the composite fault sensing result, the real-time operation data flow, the correction process and the result of the speed reducer, and using a preset report template or report generating tool to generate a speed reducer fault sensing report containing information such as fault type, position, severity, correction basis and the like.
In one possible implementation manner, the step 400 further includes a step 410 of correcting the composite fault sensing result of the speed reducer based on the real-time job data stream, and generating a speed reducer fault sensing report, and performing anomaly detection according to the real-time job data stream to obtain a job anomaly detection result. Specifically, the real-time operation data stream is preprocessed, such as filtering, denoising, standardization and the like, key features are extracted from the preprocessed data, and the key features are closely related to the performance, state or failure mode of the target cutting reducer. And analyzing the extracted characteristics by using an abnormality detection algorithm based on methods such as statistics, machine learning or deep learning, identifying an abnormality mode or behavior, recording the detected abnormality result, and obtaining an operation abnormality detection result, wherein the operation abnormality detection result comprises information such as time, position, type and the like of abnormality. And step S420, performing fault prediction on the target cutting speed reducer based on the operation abnormality detection result, and generating an operation abnormality fault prediction result. Specifically, the detected operation abnormality is matched with a known failure mode, a possible failure cause and a possible failure type are determined, abnormal data are analyzed by utilizing a pre-trained failure prediction model (such as a machine learning model, a time sequence analysis model and the like), the failure risk of the target cutting speed reducer in a future period of time is predicted, and a failure prediction result is output in the form of probability or risk level and comprises information such as the possible failure type, the expected occurrence time and the like. And step S430, performing fault fusion on the composite fault sensing result of the speed reducer based on the operation abnormal fault prediction result to obtain a fault sensing report of the speed reducer. Specifically, the operation abnormal fault prediction result and the speed reducer composite fault sensing result are aligned in time and space, the operation abnormal fault prediction result and the speed reducer composite fault sensing result are integrated into a unified framework, a fusion algorithm (such as weighted average and Bayesian fusion) is selected, the results are fused according to factors such as confidence coefficient and relevance of the operation abnormal fault prediction result and the speed reducer composite fault sensing result, and a speed reducer fault sensing report is generated based on the fused results. According to the implementation mode, the accuracy of the composite fault sensing result of the speed reducer is corrected and enhanced by utilizing the real-time operation data stream, so that a more reliable and valuable speed reducer fault sensing report is generated, and the technical effects of timely finding and processing potential faults of the target cutting speed reducer and improving the reliability and the operation efficiency of equipment are achieved.
And S500, carrying out fault operation and maintenance on the target cutting speed reducer by combining a speed reducer fault operation and maintenance library based on the speed reducer fault perception report. Specifically, through analyzing the fault perception report of the speed reducer, the specific type, position, severity, occurrence probability, influence possibly generated on the performance, safety, operation efficiency and the like of the target cutting speed reducer are determined, and according to the fault type and description in the fault perception report of the speed reducer, a related operation and maintenance scheme, a maintenance manual or an operation guide is searched in a speed reducer fault operation and maintenance library, wherein the speed reducer fault operation and maintenance library is a pre-established database containing related information such as operation and maintenance schemes, historical fault records, maintenance experience and the like of various faults. According to the retrieved operation and maintenance scheme, the detailed fault operation and maintenance steps including maintenance sequence, operation key points, safety precautions and the like are formulated by combining the existing operation and maintenance resources such as personnel, tools and spare parts, and meanwhile, according to the emergency degree of the fault and the availability of the operation and maintenance resources, a reasonable operation and maintenance schedule is set, so that the fault can be timely processed. And finally, performing fault treatment on the target cutting speed reducer step by step according to the formulated operation and maintenance steps, including operations such as disassembly, inspection, maintenance, part replacement and the like, and recording the operation condition, encountered problems and solutions of each step in detail in the operation and maintenance process so as to provide basis for subsequent fault analysis and improvement. After the operation and maintenance are finished, the function test and performance evaluation are carried out on the target cutting speed reducer, the fault is ensured to be properly solved, and the experience, teaching training and improvement measures of the operation and maintenance are arranged into a document and updated into a speed reducer fault operation and maintenance library for subsequent reference and reference. The embodiment of the application achieves the technical effects of improving the diagnosis precision, reducing the false alarm rate and realizing accurate fault positioning by comprehensively utilizing the technical means of multisource sensing data, constructing a normal deviation vector set, activating a multi-element fault sensing channel and the like.
Hereinabove, a fault diagnosis method of a cutting speed reducer of a boom-type heading machine according to an embodiment of the present invention is described in detail with reference to fig. 1. Next, a fault diagnosis system of a cutting speed reducer of a boom-type entry driving machine according to an embodiment of the present invention will be described with reference to fig. 2.
The fault diagnosis system of the cutting speed reducer of the cantilever type heading machine is used for solving the technical problems of low diagnosis precision, high false alarm rate and inaccurate fault location existing in the fault diagnosis of the cutting speed reducer of the existing cantilever type heading machine, and achieves the technical effects of improving the diagnosis precision, reducing the false alarm rate and realizing accurate fault location. A fault diagnosis system of a cutting speed reducer of a cantilever type heading machine comprises: the system comprises a real-time speed reducer perception data source acquisition module 10, a speed reducer normal deviation vector set construction module 20, a speed reducer composite fault perception result acquisition module 30, a speed reducer composite fault perception result correction module 40 and a target cutting speed reducer fault operation and maintenance module 50.
The real-time speed reducer sensing data source acquisition module 10 is used for monitoring the target cutting speed reducer in real time according to a speed reducer sensing array which is arranged in advance to obtain a real-time speed reducer sensing data source, wherein the real-time speed reducer sensing data source comprises a speed reducer vibration sensing data stream, a speed reducer lubrication sensing data stream and a speed reducer temperature sensing data stream, and the real-time speed reducer sensing data source is provided with real-time working condition characteristic data and real-time working environment characteristic data which correspond to the marks;
The reducer normal deviation vector set construction module 20 is configured to construct a reducer normal deviation vector set, where the real-time reducer perceived data source is subjected to multiple normal deviation calculation according to the real-time working condition feature data and the real-time working environment feature data to obtain the reducer normal deviation vector set, and the reducer normal deviation vector set includes a vibration normal deviation vector, a lubrication normal deviation vector and a temperature normal deviation vector;
the speed reducer composite fault sensing result obtaining module 30 is configured to activate a multi-speed reducer fault sensing channel based on the real-time working condition characteristic data, the real-time working environment characteristic data and the normal deviation vector set of the speed reducer, and obtain a speed reducer composite fault sensing result;
The speed reducer composite fault sensing result correction module 40 is used for loading a real-time operation data stream of the target cutting speed reducer, correcting the speed reducer composite fault sensing result based on the real-time operation data stream, and generating a speed reducer fault sensing report;
the target cutting speed reducer fault operation and maintenance module 50 is used for performing fault operation and maintenance on the target cutting speed reducer in combination with a speed reducer fault operation and maintenance library based on the speed reducer fault sensing report.
Next, the specific configuration of the real-time retarder aware data source acquisition module 10 will be described in detail. As described above, obtaining a real-time retarder aware data source, the real-time retarder aware data source acquisition module 10 may further include: the sensing equipment state source data retrieving unit is used for retrieving sensing equipment state source data corresponding to each data flow in the sensing data source of the real-time speed reducer; the depth anomaly identification unit is used for carrying out depth anomaly identification based on the state source data of the sensing equipment to obtain a sensing equipment anomaly identification result and an equipment anomaly depth index; the judging unit is used for judging whether the equipment abnormal depth index is smaller than an equipment abnormal depth threshold value or not; the sensing compensation unit is used for performing sensing compensation based on the sensing equipment abnormality recognition result to obtain abnormality sensing compensation data if the equipment abnormality depth index is larger than or equal to the equipment abnormality depth threshold; and the mapping correction unit is used for carrying out mapping correction on the real-time speed reducer perception data source based on the abnormal perception compensation data.
Next, the specific configuration of the decelerator normal deviation vector set construction module 20 will be described in detail. As described above, a normal deviation vector set of the speed reducer is constructed, wherein the normal deviation vector set of the speed reducer is obtained by performing multi-component normal deviation calculation on the real-time speed reducer sensing data source through the real-time working condition characteristic data and the real-time working environment characteristic data, and the normal deviation vector set of the speed reducer includes a vibration normal deviation vector, a lubrication normal deviation vector and a temperature normal deviation vector, and the normal deviation vector set of the speed reducer constructing module 20 may further include: the normal recording registration unit of the speed reducer is used for carrying out normal recording registration of the speed reducer according to the real-time working condition characteristic data and the real-time working environment characteristic data to obtain a normal recording set of the registration speed reducer; the vibration normal deviation vector construction unit is used for carrying out multi-element normal deviation calculation on the vibration sensing data flow of the speed reducer based on the registration speed reducer normal record set, and constructing the vibration normal deviation vector; the lubrication normal deviation vector construction unit is used for carrying out multi-element normal deviation calculation on the lubrication sensing data flow of the speed reducer based on the registration speed reducer normal record set, and constructing the lubrication normal deviation vector; the temperature normal deviation vector construction unit is used for carrying out multi-element normal deviation calculation on the temperature sensing data flow of the speed reducer based on the registration speed reducer normal record set, and constructing the temperature normal deviation vector.
The normal recording registration of the speed reducer is performed according to the real-time working condition characteristic data and the real-time working environment characteristic data, a normal recording set of the speed reducer is obtained, and the normal recording registration unit of the speed reducer can further comprise: the multi-group reducer normal perception record acquisition subunit is used for carrying out normal sample global retrieval based on big data to acquire multi-group reducer normal perception records; the first group of normal sensing record extraction subunit is used for traversing the plurality of groups of normal sensing records of the speed reducer and extracting a first group of normal sensing records of the speed reducer, wherein the first group of normal sensing records of the speed reducer comprise a first normal vibration data record of the speed reducer, a first normal lubrication data record of the speed reducer and a first normal temperature data record of the speed reducer, and first history working condition characteristic data and first history working environment characteristic data corresponding to the first normal vibration data record of the speed reducer, the first normal lubrication data record of the speed reducer and the first normal temperature data record of the speed reducer; the registration analysis subunit is used for carrying out registration analysis on the first historical working condition characteristic data and the first historical working environment characteristic data respectively based on the real-time working condition characteristic data and the real-time working environment characteristic data to obtain a first working condition characteristic registration coefficient and a first environment characteristic registration coefficient; the weighting calculation subunit is used for carrying out weighting calculation on the first working condition characteristic registration coefficient and the first environment characteristic registration coefficient based on a preset normal registration weight condition to obtain a first characteristic composite registration coefficient; the judging subunit is used for judging whether the first characteristic composite registration coefficient meets a preset composite registration constraint; and the record adding subunit is used for adding the first speed reducer normal vibration data record, the first speed reducer normal lubrication data record and the first speed reducer normal temperature data record to the registration speed reducer normal record set if the first characteristic composite registration coefficient meets the preset composite registration constraint.
Wherein, based on the registration reducer normal record set, performing a multivariate normal deviation calculation on the reducer vibration sensing data stream, and constructing the vibration normal deviation vector, the vibration normal deviation vector constructing unit may further include: the classifying subunit is used for classifying the registration reducer normal record set to obtain a registration normal vibration record set, a registration normal lubrication record set and a registration normal temperature record set; the centralized value evaluation subunit is used for evaluating the centralized value according to the registration normal vibration record set to obtain registration normal vibration centralized quantity; the multi-feature deviation calculation subunit is used for carrying out multi-feature deviation calculation on the vibration sensing data stream of the speed reducer based on the registration normal vibration concentration quantity, and generating the vibration normal deviation vector.
Next, the specific configuration of the decelerator composite fault perception result acquisition module 30 will be described in detail. As described above, based on the real-time working condition feature data, the real-time working environment feature data, and the normal deviation vector set of the speed reducer, activating a multi-speed reducer fault sensing channel to obtain a speed reducer composite fault sensing result, and the speed reducer composite fault sensing result obtaining module 30 may further include: the multi-speed reducer fault sensing channel building unit is used for enabling the multi-speed reducer fault sensing channel to comprise a first speed reducer fault sensing channel, a second speed reducer fault sensing channel and a third speed reducer fault sensing channel; the first speed reducer fault sensing result generation unit is used for inputting the real-time working condition characteristic data, the real-time working environment characteristic data and the vibration normal deviation vector into the first speed reducer fault sensing channel to generate a first speed reducer fault sensing result; the second speed reducer fault sensing result generation unit is used for inputting the real-time working condition characteristic data, the real-time working environment characteristic data and the lubrication normal deviation vector into the second speed reducer fault sensing channel to obtain a second speed reducer fault sensing result; the third speed reducer fault sensing result generation unit is used for inputting the real-time working condition characteristic data, the real-time working environment characteristic data and the temperature normal deviation vector into the third speed reducer fault sensing channel to obtain a third speed reducer fault sensing result; the fault fusion unit is used for carrying out fault fusion according to the first speed reducer fault sensing result, the second speed reducer fault sensing result and the third speed reducer fault sensing result to generate the speed reducer composite fault sensing result.
Next, the specific configuration of the decelerator composite fault-sensing result correction module 40 will be described in detail. As described above, correcting the retarder composite fault perception result based on the real-time job data stream, generating a retarder fault perception report, the retarder composite fault perception result correction module 40 may further include: the abnormality detection unit is used for carrying out abnormality detection according to the real-time operation data stream to obtain an operation abnormality detection result; the fault prediction unit is used for performing fault prediction on the target cutting speed reducer based on the operation abnormality detection result and generating an operation abnormality fault prediction result; and the speed reducer fault perception report generation unit is used for carrying out fault fusion on the speed reducer composite fault perception result based on the operation abnormal fault prediction result to obtain the speed reducer fault perception report.
The fault diagnosis system of the cutting speed reducer of the cantilever type heading machine provided by the embodiment of the invention can execute the fault diagnosis method of the cutting speed reducer of the cantilever type heading machine provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Although the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server, including units and modules that are merely partitioned by functional logic, but are not limited to the above-described partitioning, so long as the corresponding functionality is enabled; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the present application.
The above embodiments do not limit the scope of the present application. It will be apparent to those skilled in the art that various modifications, combinations, and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the scope of the present application. In some cases, the acts or steps recited in the present application may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
Claims (8)
1. A fault diagnosis method for a cutting speed reducer of a cantilever type heading machine, the method comprising:
Real-time monitoring is carried out on a target cutting speed reducer according to a speed reducer sensing array which is arranged in advance, so that a real-time speed reducer sensing data source is obtained, wherein the real-time speed reducer sensing data source comprises a speed reducer vibration sensing data stream, a speed reducer lubrication sensing data stream and a speed reducer temperature sensing data stream, and the real-time speed reducer sensing data source has real-time working condition characteristic data and real-time working environment characteristic data which correspond to the marks;
Constructing a normal deviation vector set of the speed reducer, wherein the real-time speed reducer perceived data source is subjected to multi-element normal deviation calculation through the real-time working condition characteristic data and the real-time working environment characteristic data, specifically, the real-time working condition characteristic data and the real-time working environment characteristic data are matched with data in a preset normal working state, according to a matching result, deviation values between the real-time data and the normal data in the real-time speed reducer perceived data source, including vibration deviation, lubrication deviation and temperature deviation, are calculated, the calculated deviation values are subjected to normal treatment, differences between different data types and dimensions are eliminated, normal deviation values are obtained, the normal deviation values are combined into vectors according to corresponding categories, and the normal deviation vector set of the speed reducer is obtained, wherein the normal deviation vector set of the speed reducer comprises the vibration normal deviation vector, the lubrication normal deviation vector and the temperature normal deviation vector;
activating a multi-element speed reducer fault sensing channel based on the real-time working condition characteristic data, the real-time working environment characteristic data and the normal deviation vector set of the speed reducer to obtain a speed reducer compound fault sensing result;
loading a real-time operation data stream of the target cutting speed reducer, correcting the speed reducer composite fault sensing result based on the real-time operation data stream, processing and analyzing real-time data by each activated speed reducer fault sensing channel, extracting feature information related to faults, fusing processing results of each channel by adopting a weighted average and maximum voting method, generating a speed reducer composite fault sensing result according to the fused result, and generating a speed reducer fault sensing report based on the speed reducer composite fault sensing result;
And carrying out fault operation and maintenance on the target cutting speed reducer by combining a speed reducer fault operation and maintenance library based on the speed reducer fault perception report.
2. The fault diagnosis method for a cutting reducer of a cantilever excavator according to claim 1, wherein a real-time reducer perceived data source is obtained, further comprising:
the state source data of sensing equipment corresponding to each data flow in the sensing data source of the real-time speed reducer is called;
Carrying out depth abnormality recognition based on the state source data of the sensing equipment to obtain a sensing equipment abnormality recognition result and an equipment abnormality depth index;
judging whether the equipment abnormality depth index is smaller than an equipment abnormality depth threshold value or not;
if the equipment abnormality depth index is larger than or equal to the equipment abnormality depth threshold, performing sensing compensation based on the sensing equipment abnormality identification result to obtain abnormality sensing compensation data;
and carrying out mapping correction on the real-time speed reducer perception data source based on the abnormal perception compensation data.
3. The fault diagnosis method for a cutting speed reducer of a cantilever type heading machine according to claim 1, wherein a normal deviation vector set of the speed reducer is constructed, wherein a multi-element normal deviation calculation is performed on a sensing data source of the real-time speed reducer through the real-time working condition characteristic data and the real-time working environment characteristic data to obtain the normal deviation vector set of the speed reducer, and the normal deviation vector set of the speed reducer comprises a vibration normal deviation vector, a lubrication normal deviation vector and a temperature normal deviation vector, and the fault diagnosis method comprises the following steps:
Performing normal record registration of the speed reducer according to the real-time working condition characteristic data and the real-time working environment characteristic data to obtain a registration speed reducer normal record set;
performing multi-element normal deviation calculation on the vibration sensing data flow of the speed reducer based on the registration speed reducer normal record set, and constructing the vibration normal deviation vector;
performing multi-element normal deviation calculation on the lubrication sensing data flow of the speed reducer based on the registration speed reducer normal record set, and constructing the lubrication normal deviation vector;
and carrying out multi-element normal deviation calculation on the temperature sensing data flow of the speed reducer based on the registration speed reducer normal record set, and constructing the temperature normal deviation vector.
4. A fault diagnosis method for a cutting speed reducer of a cantilever type heading machine as defined in claim 3, wherein the step of performing a normal recording registration of the speed reducer according to the real-time working condition characteristic data and the real-time working environment characteristic data to obtain a registered normal recording set of the speed reducer comprises:
Performing normal sample global retrieval based on big data to obtain a plurality of groups of normal perception records of the speed reducer;
Traversing the plurality of groups of normal sensing records of the speed reducers, and extracting a first group of normal sensing records of the speed reducers, wherein the first group of normal sensing records of the speed reducers comprise a first normal vibration data record of the speed reducers, a first normal lubrication data record of the speed reducers and a first normal temperature data record of the speed reducers, and first historical working condition characteristic data and first historical working environment characteristic data corresponding to the first normal vibration data record of the speed reducers, the first normal lubrication data record of the speed reducers and the first normal temperature data record of the speed reducers;
Based on the real-time working condition characteristic data and the real-time working environment characteristic data, carrying out registration analysis on the first historical working condition characteristic data and the first historical working environment characteristic data respectively to obtain a first working condition characteristic registration coefficient and a first environment characteristic registration coefficient;
Weighting calculation is carried out on the first working condition characteristic registration coefficient and the first environment characteristic registration coefficient based on a preset normal registration weight condition, and a first characteristic composite registration coefficient is obtained;
Judging whether the first characteristic composite registration coefficient meets a preset composite registration constraint;
And if the first characteristic composite registration coefficient meets the preset composite registration constraint, adding the first speed reducer normal vibration data record, the first speed reducer normal lubrication data record and the first speed reducer normal temperature data record to the registration speed reducer normal record set.
5. A fault diagnosis method for a cantilever heading machine cutting reducer as defined in claim 3, wherein said calculating a multivariate normal deviation of said reducer vibration-sensing data stream based on said registration reducer normal record set, constructing said vibration normal deviation vector, comprises:
Classifying the registration reducer normal record set to obtain a registration normal vibration record set, a registration normal lubrication record set and a registration normal temperature record set;
Evaluating the concentrated value according to the registration normal vibration record set to obtain registration normal vibration concentrated quantity;
And carrying out multi-feature deviation calculation on the vibration sensing data flow of the speed reducer based on the registration normal vibration concentration quantity, and generating the vibration normal deviation vector.
6. The fault diagnosis method for a cutting speed reducer of a cantilever type heading machine according to claim 1, wherein activating a multi-speed reducer fault sensing channel based on the real-time working condition characteristic data, the real-time working environment characteristic data and the normal deviation vector set of the speed reducer to obtain a composite fault sensing result of the speed reducer comprises:
The multi-speed reducer fault sensing channel comprises a first speed reducer fault sensing channel, a second speed reducer fault sensing channel and a third speed reducer fault sensing channel;
inputting the real-time working condition characteristic data, the real-time working environment characteristic data and the vibration normal deviation vector into the first speed reducer fault sensing channel to generate a first speed reducer fault sensing result;
inputting the real-time working condition characteristic data, the real-time working environment characteristic data and the lubrication normal deviation vector into the second speed reducer fault sensing channel to obtain a second speed reducer fault sensing result;
Inputting the real-time working condition characteristic data, the real-time working environment characteristic data and the temperature normal deviation vector into the third speed reducer fault sensing channel to obtain a third speed reducer fault sensing result;
And performing fault fusion according to the first speed reducer fault sensing result, the second speed reducer fault sensing result and the third speed reducer fault sensing result to generate a speed reducer compound fault sensing result.
7. The fault diagnosis method for a cutting speed reducer of a cantilever type heading machine according to claim 1, wherein the step of correcting the composite fault sensing result of the speed reducer based on the real-time operation data stream to generate a speed reducer fault sensing report comprises the steps of:
Performing abnormality detection according to the real-time operation data stream to obtain an operation abnormality detection result;
performing fault prediction on the target cutting speed reducer based on the operation abnormality detection result to generate an operation abnormality fault prediction result;
and carrying out fault fusion on the composite fault sensing result of the speed reducer based on the operation abnormal fault prediction result to obtain the speed reducer fault sensing report.
8. A fault diagnosis system for a cutting speed reducer of a boom-type entry-driving machine, characterized in that the system is adapted to implement a fault diagnosis method for a cutting speed reducer of a boom-type entry-driving machine according to any one of claims 1 to 7, the system comprising:
The real-time speed reducer perception data source acquisition module is used for monitoring the target cutting speed reducer in real time according to a speed reducer sensing array which is arranged in advance to obtain a real-time speed reducer perception data source, wherein the real-time speed reducer perception data source comprises a speed reducer vibration perception data stream, a speed reducer lubrication perception data stream and a speed reducer temperature perception data stream, and the real-time speed reducer perception data source is provided with real-time working condition characteristic data and real-time working environment characteristic data which correspond to the marks;
The speed reducer normal deviation vector set construction module is used for constructing a speed reducer normal deviation vector set, wherein the real-time speed reducer perceived data source is subjected to multi-element normal deviation calculation through the real-time working condition characteristic data and the real-time working environment characteristic data, specifically, the real-time working condition characteristic data and the real-time working environment characteristic data are matched with data in a preset normal working state, according to a matching result, deviation values between the real-time data and the normal data in the real-time speed reducer perceived data source, including vibration deviation, lubrication deviation and temperature deviation, are calculated, the calculated deviation values are subjected to normal treatment, differences between different data types and dimensions are eliminated, normal deviation values are obtained, the normal deviation values are combined into vectors according to corresponding categories, and the speed reducer normal deviation vector set is obtained, and comprises the vibration normal deviation vector, the lubrication normal deviation vector and the temperature normal deviation vector;
The speed reducer composite fault sensing result acquisition module is used for activating a multi-speed reducer fault sensing channel based on the real-time working condition characteristic data, the real-time working environment characteristic data and the speed reducer normal deviation vector set to acquire a speed reducer composite fault sensing result;
the speed reducer composite fault perception result correction module is used for loading real-time operation data flow of the target cutting speed reducer, correcting the speed reducer composite fault perception result based on the real-time operation data flow, processing and analyzing real-time data by each activated speed reducer fault perception channel, extracting feature information related to faults, fusing processing results of the channels by adopting a weighted average and maximum voting method, generating a speed reducer composite fault perception result according to the fused result, and generating a speed reducer fault perception report based on the speed reducer composite fault perception result;
The target cutting speed reducer fault operation and maintenance module is used for carrying out fault operation and maintenance on the target cutting speed reducer by combining a speed reducer fault operation and maintenance library based on the speed reducer fault perception report.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410666954.XA CN118243378B (en) | 2024-05-28 | 2024-05-28 | Fault diagnosis method and system for cutting speed reducer of cantilever type heading machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410666954.XA CN118243378B (en) | 2024-05-28 | 2024-05-28 | Fault diagnosis method and system for cutting speed reducer of cantilever type heading machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118243378A CN118243378A (en) | 2024-06-25 |
| CN118243378B true CN118243378B (en) | 2024-08-09 |
Family
ID=91563997
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410666954.XA Active CN118243378B (en) | 2024-05-28 | 2024-05-28 | Fault diagnosis method and system for cutting speed reducer of cantilever type heading machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118243378B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115962944A (en) * | 2022-10-11 | 2023-04-14 | 西山煤电(集团)有限责任公司 | VMD-based real-time diagnosis method for bearing fault of cutting part of intelligent coal mining machine group |
| CN117609869A (en) * | 2024-01-22 | 2024-02-27 | 深圳市陶氏精密技术有限公司 | Intelligent fault diagnosis and self-learning method and system for speed reducer |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6240050B2 (en) * | 2014-09-17 | 2017-11-29 | 株式会社東芝 | Bias estimation apparatus, method and program thereof, and fault diagnosis apparatus, method and program thereof |
| US11906395B2 (en) * | 2018-02-13 | 2024-02-20 | Halliburton Energy Services, Inc. | Shaker vibration and downhole cuttings measurement analysis and processing |
| CN113093693B (en) * | 2021-03-18 | 2022-04-12 | 北京天玛智控科技股份有限公司 | Online fault diagnosis method for operation state of coal mining machine |
| CN114813115A (en) * | 2022-03-28 | 2022-07-29 | 天地上海采掘装备科技有限公司 | Online identification method for broken shaft fault of rocker arm of drum shearer |
| CN114813105B (en) * | 2022-04-11 | 2023-04-28 | 西安热工研究院有限公司 | Gear box fault early warning method and system based on working condition similarity evaluation |
| CN115392349A (en) * | 2022-08-02 | 2022-11-25 | 三一重型装备有限公司 | Fault diagnosis method and device for cutting part of heading machine and heading machine |
| CN115630946A (en) * | 2022-10-19 | 2023-01-20 | 延长油田股份有限公司 | Oil well multi-parameter abnormity diagnosis and early warning method based on machine learning |
| KR102589094B1 (en) * | 2022-10-26 | 2023-10-16 | (재)대구기계부품연구원 | Training data set configuration system and method for development of diagnosis model of the machine tool |
| CN117491000B (en) * | 2023-11-08 | 2024-09-24 | 联峰钢铁（张家港）有限公司 | Diagnosis method for abnormal working condition of steel rolling process |
| CN117762117A (en) * | 2023-12-05 | 2024-03-26 | 中国煤炭科工集团太原研究院有限公司 | AR acquisition and analysis tunneling equipment fault processing method and device |
| CN117704054B (en) * | 2024-02-04 | 2024-05-14 | 山西天地煤机装备有限公司 | Online monitoring system and method for oil liquid of cutting speed reducer of cantilever type heading machine |
-
2024
- 2024-05-28 CN CN202410666954.XA patent/CN118243378B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115962944A (en) * | 2022-10-11 | 2023-04-14 | 西山煤电(集团)有限责任公司 | VMD-based real-time diagnosis method for bearing fault of cutting part of intelligent coal mining machine group |
| CN117609869A (en) * | 2024-01-22 | 2024-02-27 | 深圳市陶氏精密技术有限公司 | Intelligent fault diagnosis and self-learning method and system for speed reducer |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118243378A (en) | 2024-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7496798B2 (en) | Data-centric monitoring method | |
| JP5016519B2 (en) | Diagnostic system and method for predictive condition monitoring | |
| AU2002246994A1 (en) | Diagnostic systems and methods for predictive condition monitoring | |
| CN115099260A (en) | Online monitoring mechanical fault real-time diagnosis method for double-screw oil transfer pump | |
| Demilia et al. | Measurements for smart manufacturing in an Industry 4.0 scenario a case-study on a mechatronic system | |
| Jain et al. | Dynamic optimization of process quality control and maintenance planning | |
| Li et al. | Fault forecasting of a machining center tool magazine based on health assessment | |
| CN118243378B (en) | Fault diagnosis method and system for cutting speed reducer of cantilever type heading machine | |
| CN117689269B (en) | Fault tracing method for intelligent watch processing stage | |
| CN117131364B (en) | Rolling bearing process detection integration method and system | |
| KR20220085827A (en) | Prediction systems, information processing devices and recording media | |
| CN117961646A (en) | Method and system for predicting residual service life of numerical control blade for heavy load machining | |
| CN108427375B (en) | Method for monitoring cutter state based on band-pass filtering processing multi-sensor | |
| Lorenti et al. | Cuad-mo: Continuos unsupervised anomaly detection on machining operations | |
| CN115659271A (en) | Sensor abnormality detection method, model training method, system, device, and medium | |
| CN118171753B (en) | Motor fault intelligent diagnosis system based on vibration analysis | |
| CN118114081B (en) | Method and system for predicting residual life of plunger pump | |
| CN117359391B (en) | Intelligent fault diagnosis method and system for rolling bearing of numerical control machine tool | |
| CN117972989B (en) | Service life prediction method and system for coal machine equipment | |
| Hurtado Carreon et al. | CNC linear axis condition-based monitoring: a statistics-based framework to establish a baseline dataset and case study | |
| CN118625791B (en) | Fault-tolerant control system and method for conveying equipment abnormality | |
| CN115488696B (en) | Cutter abrasion prediction method based on variation modal decomposition and neural network | |
| Shankar | Intelligent Fault Diagnosis in Electric Motors Using AI Techniques | |
| Bouyahrouzi et al. | Defining and Implementing Predictive Maintenance Based on Artificial Intelligence for Rotating Machines | |
| CN117806233A (en) | Intelligent monitoring system and method for numerical control machine tool |
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 |