CN117786461A - Water pump fault diagnosis method, control device and storage medium thereof - Google Patents
Water pump fault diagnosis method, control device and storage medium thereof Download PDFInfo
- Publication number
- CN117786461A CN117786461A CN202311844581.2A CN202311844581A CN117786461A CN 117786461 A CN117786461 A CN 117786461A CN 202311844581 A CN202311844581 A CN 202311844581A CN 117786461 A CN117786461 A CN 117786461A
- Authority
- CN
- China
- Prior art keywords
- water pump
- data
- vibration
- parameter set
- fault
- 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.)
- Pending
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 142
- 238000003745 diagnosis Methods 0.000 title claims abstract description 73
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 238000004458 analytical method Methods 0.000 claims abstract description 27
- 230000035945 sensitivity Effects 0.000 claims abstract description 8
- 238000009826 distribution Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 13
- 238000003062 neural network model Methods 0.000 claims description 11
- 230000036541 health Effects 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 4
- 230000002087 whitening effect Effects 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000007257 malfunction Effects 0.000 claims 6
- 238000012423 maintenance Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000005856 abnormality Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 239000012530 fluid Substances 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003449 preventive effect Effects 0.000 description 2
- 238000007789 sealing Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000012097 association analysis method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Landscapes
- Control Of Positive-Displacement Pumps (AREA)
Abstract
The application provides a fault diagnosis method of a water pump, control equipment and a storage medium thereof. The fault diagnosis method of the water pump comprises the following steps: collecting vibration data of a water pump, and extracting a vibration parameter set; determining a sensitive characteristic parameter set in the vibration parameter set according to the sensitivity degree of the data in the vibration parameter set to faults; trend analysis is carried out according to the data distribution of the sensitive characteristic parameter set, and the running state of the water pump in a future set time period is predicted; comparing the running state in the future set time period with the fault state in the fault diagnosis knowledge base, and predicting the fault trend of the water pump. By determining the sensitive characteristic parameter set, the accuracy and the comprehensiveness of data are ensured, so that the failure trend of the water pump is predicted more accurately, the failure diagnosis efficiency of the water pump is improved, and the method is applicable to water pumps with different use conditions.
Description
Technical Field
The present disclosure relates to the field of mechanical fault detection technologies, and in particular, to a fault diagnosis method, a control device, and a storage medium thereof for a water pump.
Background
In modern industry, rotary machines play an important role in the fields of electric power, traffic, manufacturing, etc. As the main rotating machinery of a hydropower plant, pumps are responsible for the important tasks of fluid transport and pressure elevation. In order to meet the demands of hydropower plants, pumps are required to have excellent properties such as long service life, long-term safe and stable operation, excellent sealing performance and the like. Therefore, timely and accurate fault diagnosis is important for the state maintenance of the water pump.
In the prior art, by collecting the name of vibration data, pressure data and rotating speed data in the operation of the pump, characteristic values related to vibration are extracted according to the collected data, so that a reasonable threshold value is set for judging whether the pump has faults or not.
However, the actual running condition of the pump is complex, and the pump with different running conditions cannot be covered by simply relying on threshold early warning.
Disclosure of Invention
The application provides a fault diagnosis method, control equipment and a storage medium thereof for a water pump, which are used for diagnosing water pump faults under different working conditions.
In one aspect, the present application provides a fault diagnosis method for a water pump, including:
collecting vibration data of a water pump, and extracting a vibration parameter set;
determining a sensitive characteristic parameter set in the vibration parameter set according to the sensitivity degree of the data in the vibration parameter set to faults;
trend analysis is carried out according to the data distribution of the sensitive characteristic parameter set, and the running state of the water pump in a future set time period is predicted;
comparing the running state in the future set time period with the fault state in the fault diagnosis knowledge base, and predicting the fault trend of the water pump.
In one possible implementation manner, the method for diagnosing the fault of the water pump provided by the application further comprises the following steps:
and predicting failure occurrence rate, failure point and failure type of different component nodes of the water pump according to the current running state and the future running state of the water pump.
In one possible implementation manner, the method for diagnosing a fault of a water pump provided in the present application collects vibration data of the water pump, and extracts a vibration parameter set, including:
collecting vibration data of the water pump, and performing time domain analysis to obtain a primary selection data set;
and carrying out frequency domain analysis on the primary selection data to obtain a vibration parameter set.
In one possible implementation manner, the method for diagnosing a fault of a water pump provided in the present application collects vibration data of the water pump, and extracts a vibration parameter set, including:
collecting vibration data of the water pump, and decomposing the vibration data to obtain a primary selection data set;
and analyzing the primary selection data set to obtain a vibration parameter set.
In one possible implementation manner, the method for diagnosing a fault of a water pump provided in the present application predicts the fault occurrence rate, the fault point and the fault type of different nodes according to the current running state and the future running state of the water pump, including:
and inputting the sensitive characteristic parameter set into the fault diagnosis model, and outputting the fault occurrence rate, the fault point and the fault type.
In one possible implementation manner, the method for diagnosing the fault of the water pump provided by the application further comprises the following steps:
collecting vibration signals representing different faults as original data of the fault diagnosis model;
extracting features of the original data to be used as training and testing samples of a twin neural network model;
and training and optimizing the twin neural network model to obtain the fault diagnosis model.
In one possible implementation manner, the method for diagnosing the fault of the water pump provided by the application further comprises the following steps:
inputting historical record data of the water pump;
extracting associated data of which the degree of correlation with the vibration state of the water pump is higher than a threshold value from the historical record data;
performing whitening treatment on the associated data to obtain gray association degree among the associated data, and sequencing;
obtaining an association rule between the history data and the vibration state;
and training a hierarchical model for quantifying the health state of the system, and establishing a fault diagnosis knowledge base according to the association rule.
In one possible implementation manner, the method for diagnosing the fault of the water pump provided by the application further comprises the following steps:
and generating a fault diagnosis list and an equipment state monitoring report.
In another aspect, the present application provides a control device comprising a processor for executing code to perform the method of diagnosing a failure of a water pump as described in any one of the above, and a memory for storing the code for the processor to perform the method.
In another aspect, the present application provides a control device readable storage medium having stored therein a fault diagnosis execution instruction, which when executed by a control device, is configured to implement a fault diagnosis method of a water pump according to any one of the above.
According to the fault diagnosis method, the control equipment and the storage medium of the water pump, the vibration parameter set is extracted by collecting vibration data of the water pump, and the sensitive characteristic parameter set is determined in the vibration parameter set according to the sensitivity of the data in the vibration parameter set to faults, so that the accuracy and the comprehensiveness of the sensitive characteristic parameter set are ensured; trend analysis is carried out according to the data distribution of the sensitive characteristic parameter set, so that the running state of the water pump in a future set time period can be rapidly and accurately predicted, the predicted running state is compared with the fault state in the fault diagnosis knowledge base, the fault trend of the water pump is predicted more accurately, the fault diagnosis efficiency of the water pump is improved, and the method is applicable to water pumps with different use conditions.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
Fig. 1 is a flowchart of a method for diagnosing a failure of a water pump according to an embodiment of the present disclosure;
fig. 2 is a flowchart two of a fault diagnosis method of a water pump according to an embodiment of the present application;
fig. 3 is a flowchart III of a fault diagnosis method of a water pump according to an embodiment of the present application;
fig. 4 is a flowchart of a fault diagnosis method of a water pump according to an embodiment of the present application;
fig. 5 is a flowchart five of a fault diagnosis method of a water pump according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a control device according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of a control device according to an embodiment of the present application.
Specific embodiments thereof have been shown by way of example in the drawings and will herein be described in more detail. These drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the present application more apparent, the technical solutions in the present application will be clearly and completely described below with reference to the drawings in the present application, and it is apparent that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
In the embodiments of the present application, the terms "upper", "lower", "inner", "middle", "outer", "front", "rear", and the like indicate an azimuth or a positional relationship based on that shown in the drawings. These terms are used primarily to better describe the present application and its embodiments and are not intended to limit the indicated device, element or component to a particular orientation or to be constructed and operated in a particular orientation. Also, some of the terms described above may be used to indicate other meanings in addition to orientation or positional relationships, for example, the term "upper" may also be used to indicate some sort of attachment or connection in some cases. The specific meaning of these terms in the embodiments of the present application will be understood by those of ordinary skill in the art in view of the specific circumstances.
In addition, the terms "disposed," "connected," "secured" and "affixed" are to be construed broadly. For example, "connected" may be in a fixed connection, a removable connection, or a unitary construction; may be a mechanical connection, or an electrical connection; may be directly connected, or indirectly connected through intervening media, or may be in internal communication between two devices, elements, or components. The specific meaning of the above terms in the embodiments of the present disclosure may be understood by those of ordinary skill in the art according to specific circumstances.
The terms "first," "second," "third," "fourth" and the like in the description and in the claims of this application and in the above-described figures, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented, for example, in sequences other than those illustrated or described herein.
In the embodiments of the present application, words such as "exemplary" or "such as" are used to mean examples, illustrations, or descriptions. Any embodiment or design described herein as "exemplary" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.
The term "plurality" means two or more, unless otherwise indicated.
As described in the background art, in the modern industry, rotary machines play an important role in the fields of electric power, transportation, manufacturing, and the like. As the main rotating machinery of a hydropower plant, pumps are responsible for the important tasks of fluid transport and pressure elevation. In order to meet the demands of hydropower plants, pumps are required to have excellent properties such as long service life, long-term safe and stable operation, excellent sealing performance and the like. Therefore, timely and accurate fault diagnosis is important for the state maintenance of the water pump.
In the prior art, by collecting the name of vibration data, pressure data and rotating speed data in the operation of the pump, characteristic values related to vibration are extracted according to the collected data, so that a reasonable threshold value is set for judging whether the pump has faults or not.
However, the actual running condition of the pump is complex, and the pump with different running conditions cannot be covered by simply relying on threshold early warning.
In order to solve the problems, the application provides a fault diagnosis method, control equipment and a storage medium thereof for a water pump, wherein the fault diagnosis method for the water pump is used for extracting a vibration parameter set by collecting vibration data of the water pump, and determining a sensitive characteristic parameter set in the vibration parameter set according to the sensitivity of the data in the vibration parameter set to faults so as to ensure the accuracy and the comprehensiveness of the sensitive characteristic parameter set; trend analysis is carried out according to the data distribution of the sensitive characteristic parameter set, so that the running state of the water pump in a future set time period can be rapidly and accurately predicted, the predicted running state is compared with the fault state in the fault diagnosis knowledge base, the fault trend of the water pump is predicted more accurately, the fault diagnosis efficiency of the water pump is improved, and the method is applicable to water pumps with different use conditions.
The following describes the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems in detail with specific embodiments. The following specific embodiments may be combined with each other and may not be described in detail in some embodiments for the same or similar concepts or processes. Embodiments of the present application will be described below with reference to the accompanying drawings.
Fig. 1 is a flowchart illustrating a fault diagnosis method of a water pump according to the present embodiment.
The embodiment provides a fault diagnosis method for a water pump, which comprises the following steps:
s100, collecting vibration data of a water pump, and extracting a vibration parameter set;
s200, determining a sensitive characteristic parameter set in the vibration parameter set according to the sensitivity degree of data in the vibration parameter set to faults;
s300, carrying out trend analysis according to data distribution of the sensitive characteristic parameter set, and predicting the running state of the water pump in a future set time period;
s400, comparing the running state in a set time period in the future with the fault state in the fault diagnosis knowledge base, and predicting the fault trend of the water pump.
Specifically, in this embodiment, vibration data of the water pump is collected, and a vibration parameter set is extracted to obtain data related to a fault in the vibration data of the water pump, and then a sensitive characteristic parameter set is determined in the vibration parameter set according to the sensitivity of the data in the vibration parameter set to the fault. The higher the sensitivity degree of the data to the faults is, the larger the influence of the data on the faults is, so that the sensitive characteristic parameter set can reflect the existence and influence degree of the faults more accurately, and the accuracy of fault diagnosis is improved.
After the sensitive characteristic parameter set is obtained, the sensitive characteristic parameter set is subjected to qualitative trend analysis according to the historical change characteristic trend of the vibration data of the water pump, so that the change trend of the vibration signal and the technological parameter of the water pump is obtained, the running state of the water pump in a future set time period is predicted, the running state of the water pump is compared with the fault state in a fault diagnosis knowledge base, the fault trend of the water pump is obtained, potential problems can be found in time according to the fault trend of the water pump, preventive maintenance is carried out in advance, the water pump is prevented from being failed in the running process, and therefore the shutdown time and the maintenance cost are reduced.
It should be noted that, in this embodiment, the future set time is 30 minutes in the future, so as to avoid the calculation burden and possible errors caused by too frequent prediction while predicting the running state of the water pump in time. In other embodiments, an appropriate prediction duration may be selected as needed, which is not limited in this embodiment.
Fig. 2 shows a second flowchart of the fault diagnosis method of the water pump according to the present embodiment, please refer to fig. 1 and 2.
Further, in an alternative embodiment, the fault diagnosis method of the water pump further includes:
s500, predicting failure occurrence rate, failure point and failure type of different component nodes of the water pump according to the current running state and the future running state of the water pump.
Specifically, after the failure trend of the water pump is predicted, the failure occurrence rate, the failure point and the failure type of the nodes of different parts of the water pump are further predicted, the failure position of the water pump can be more accurately positioned, and the part nodes which are likely to fail are recognized in advance, so that preventive maintenance is performed, a worker can conveniently formulate a more specific maintenance strategy according to the predicted failure point and the failure type, and the reliability and the stability of the water pump are improved.
Further, in an alternative embodiment, S100, collecting vibration data of the water pump, and extracting a vibration parameter set includes:
s110, collecting vibration data of the water pump, and performing time domain analysis to obtain a primary selection data set;
s120, performing frequency domain analysis on the primary selection data to obtain a vibration parameter set.
Specifically, since external interference or other influence may exist in the vibration data itself of the direct water pump such that the data is inaccurate and unstable, it is difficult to determine whether there is a failure or not by directly observing the vibration data, and also to analyze the cause and evaluation performance of the vibration, it is necessary to process the data through time domain analysis and frequency domain analysis, thereby extracting the vibration parameter set more accurately.
When the method is specifically implemented, firstly, the collected vibration data of the water pump are preprocessed, including noise removal, data smoothing and the like, so that the accuracy and stability of the data are improved. And drawing a time domain waveform chart, extracting characteristic parameters such as the mean value, the mean square error, the kurtosis value, the peak value and the like of the vibration data of the water pump in the time domain waveform chart, and calculating the characteristics of the characteristic parameters at different moments so as to form a primary selection data set.
It should be noted that, according to the requirement, the characteristic parameters of the vibration data of the water pump extracted in the time domain waveform diagram may be selected, and the embodiment is not limited at all.
The average value of the vibration data of the water pump is extracted, so that the stability and trend of the data can be known, and if the average value continuously rises or falls, the average value may mean that the water pump has faults or performance falls; extracting the mean square error of the vibration data of the water pump, reflecting the fluctuation range and the change rule of the data, and if the mean square error is obviously increased, possibly meaning that the water pump has abnormality or failure; extracting kurtosis value of vibration data of the water pump, reflecting the peak degree of the data, and if the kurtosis value suddenly increases, possibly meaning that the water pump has abnormality or failure; the peak value of the vibration data of the water pump is extracted, the maximum fluctuation condition of the data can be reflected, and if the peak value suddenly increases, the peak value can mean that the water pump has abnormality or fault.
Meanwhile, in the specific implementation, the specific application content of the characteristic parameters such as the mean value, the mean square error, the kurtosis value, the peak value and the like of the vibration data of the water pump is not limited to the above, and the calculation should be performed according to the actual situation, and the above scheme is only exemplary.
Further, in this embodiment, after the initially selected parameter set is obtained through the time domain analysis, since the time domain analysis only provides information of the signal changing along with time, but cannot reveal the frequency component or the frequency spectrum characteristic of the signal, the frequency domain analysis is also required to be performed on the initially selected parameter set.
In specific implementation, the initially selected parameter set is converted to a frequency domain through fourier transform to decompose a time domain signal into superposition of different frequency components, so that frequency components of the signal are revealed, then a frequency spectrum after fourier transform is analyzed, amplitude and phase information of different frequency components, frequency ranges and distribution conditions of the signal are identified through observation of a spectrogram, a result of combined frequency spectrum analysis is obtained, and a vibration parameter set is obtained through identification of abnormal frequency components, harmonic components and characteristic frequencies related to working conditions.
Fig. 3 shows a flowchart III of a fault diagnosis method for a water pump according to the present embodiment, please refer to fig. 1, 2 and 3.
Further, in an alternative embodiment, S100, collecting vibration data of the water pump, and extracting a vibration parameter set includes:
s130, collecting vibration data of the water pump, and decomposing the vibration data to obtain a primary selection data set;
and S140, analyzing the primary selection data set to obtain a vibration parameter set.
Specifically, in this embodiment, after vibration data of the water pump is collected, the vibration data may be decomposed to obtain a primary selected data set, and the decomposed primary selected data set is analyzed to obtain a vibration parameter set, so that feature data with more dimensions can be extracted, and local features of signals can be reflected more accurately.
In specific implementation, in this embodiment, the vibration data of the water pump is decomposed by using an EMD (Empirical Mode Decomposition ) algorithm, the vibration data of the water pump is decomposed by using the EMD algorithm to obtain a limited number of IMFs (Intrinsic Mode Function, eigen-mode functions), and the IMF components are analyzed, so as to obtain a vibration parameter set.
In particular, since the EMD algorithm decomposes based on the input signal itself, it does not require manual selection or preset basis functions. The self-adaptive capacity enables the EMD algorithm to adapt to various different types of signal data, whether linear or nonlinear, steady or unsteady signals, so that richer characteristic information can be extracted from the signals, and more accurate data bases are provided for subsequent analysis and processing.
Further, in this embodiment, after the IMF component is obtained, time domain analysis and frequency domain analysis are performed on the IMF component, so as to obtain a vibration parameter set, thereby improving accuracy of the vibration parameter set.
The time domain analysis and the frequency domain analysis have been described in the above embodiments, and are not described in detail herein.
Further, in an alternative embodiment, S500 predicts failure occurrence, failure point, and failure type of different component nodes of the water pump according to the current operation state and the future operation state of the water pump, including:
s510, inputting a sensitive characteristic parameter set into the fault diagnosis model, and outputting the fault occurrence rate, the fault point and the fault type.
Specifically, in this embodiment, the fault prediction of the nodes of the different components of the water pump is implemented by the fault diagnosis model, and the fault occurrence rate, the fault point and the fault type of the nodes of the different components of the water pump are obtained by inputting the sensitive characteristic parameter set into the fault diagnosis model, so that the efficiency of fault diagnosis is improved by the fault diagnosis model.
Fig. 4 shows a flowchart four of the diagnosis method of the water pump provided in the present embodiment, and fig. 6 shows a schematic structural diagram one of the control device provided in the present embodiment. Please refer to fig. 4 and 6.
Further, in an alternative embodiment, the fault diagnosis method of the water pump further includes:
s10, collecting vibration signals representing different faults as original data of a fault diagnosis model;
s20, extracting features of the original data to serve as training and testing samples of the twin neural network model;
and S30, training and optimizing the twin neural network model to obtain a fault diagnosis model.
Specifically, in this embodiment, the fault diagnosis model is constructed based on a twin neural network model, by taking vibration signals representing different faults as original data of the fault diagnosis model, performing feature extraction on the original data through an EMD algorithm to obtain IMF components, then calculating energy feature vectors corresponding to the IMF components of each section of signals as training and testing samples of the twin neural network model, and training and optimizing the twin neural network model to obtain the fault diagnosis model.
The twin neural network is a network model for judging the similarity of samples, so that the output of the network is the similarity between two samples. The characteristics are utilized to enable the sample to be tested and the training sample to be compared one by one, samples with high similarity with the sample to be tested are found out, the types of the samples determine the types of the sample to be tested, and therefore the types of the sample to be tested, namely the fault types, are output.
The twin neural network model is used without prior knowledge of the type or number of faults. As long as the training data set is large enough and contains various possible fault types, the network can learn how to distinguish different fault types, thereby improving the applicability of the fault diagnosis of the water pump and saving time and cost.
Meanwhile, with the addition of a new fault sample, the twin neural network model can be continuously learned and optimized, and the identification capability of unknown fault types is improved.
Fig. 5 shows a flowchart five of a fault diagnosis method for a water pump according to the present embodiment, please refer to fig. 5 and 6.
Further, in an alternative embodiment, the fault diagnosis method of the water pump further includes:
s1, inputting historical record data of a water pump;
s2, extracting associated data with the vibration state relativity of the water pump higher than a threshold value from the historical record data;
s3, performing whitening treatment on the associated data to obtain gray association degree among the associated data, and sequencing;
s4, obtaining association rules between the historical record data and the vibration state;
s5, training a hierarchical model of the system health state quantification, and establishing a fault diagnosis knowledge base according to association rules.
Specifically, relevant data, of which the degree of correlation with the vibration state of the water pump is higher than a threshold value, are mined from historical record data of the water pump, technological parameters (the technological parameters comprise voltage, current, pressure, temperature, motor current, motor coil temperature, bearing temperature, vibration value, inlet and outlet medium temperature, flow and the like) closely related to the vibration state are obtained, the relevant data are whitened through a GRA (gradient correlation analysis) method (Grey Relational Analysis, gray correlation analysis) to obtain gray correlation degree among the relevant data, and the relevant data are sequenced to obtain the correlation rule between the historical record data and the vibration state.
Before the whitening data is analyzed by the GRA method, the related data may be preprocessed by the FRA method (Fuzzy Relational Analysis, fuzzy association analysis method) to obtain objective interval values from the multi-source data, thereby further improving the accuracy and reliability of the data analysis.
Further, when the association rule between the history data and the vibration state is obtained, reasonable vibration abnormality definition can be given according to the existing technical knowledge aiming at the vibration abnormal fluctuation condition and the normal fluctuation condition, and the relationship between the history data and the vibration state can be summarized.
Further, after the association rule between the historical record data and the vibration state is obtained, a dynamic Bayesian network is adopted for carrying out fault analysis aiming at nodes of different parts of the water pump, and the occurrence probability of fault characteristics is counted. The components of the pump and an auxiliary system related to the pump are split, a hierarchical model for quantifying the health state of the system is trained, and a fault diagnosis knowledge base is established according to association rules, so that powerful support is provided for subsequent fault diagnosis.
Referring to fig. 2, further, in an alternative embodiment, the fault diagnosis method of the water pump further includes:
s600, generating a fault diagnosis list and an equipment state monitoring report.
Specifically, after the fault trend of the water pump is detected, a fault diagnosis list and a device state monitoring report are generated, and detailed analysis and diagnosis are performed on the fault trend of the water pump, so that a worker can better know the fault condition and the running state of the water pump.
Fig. 7 shows a second schematic structural diagram of the control apparatus provided in the present embodiment. Please refer to fig. 7.
On the other hand, the present embodiment also provides a control device, including a processor for executing codes to perform the fault diagnosis method of the water pump according to any one of the above embodiments, and a memory for storing codes for the processor to perform the method.
The method for diagnosing the failure of the water pump is described in the above embodiments, and will not be described herein.
Specifically, the memory may be a computer memory, or may be an external storage device such as a hard disk, a flash memory, etc., and the type of the memory adapted may be selected according to actual needs.
In this embodiment, the memory and the processor are connected by a bus to implement data transmission. The processor runs the code by reading the data stored in the memory to achieve fault diagnosis.
On the other hand, the present embodiment also provides a control device readable storage medium, in which a fault diagnosis execution instruction is stored, which is used to implement the fault diagnosis method of the water pump according to any one of the above embodiments when executed by the control device.
Specifically, the control device readable storage medium and the control device provided in this embodiment may be connected through a data interface. The present embodiment does not limit the specific connection method.
The data interface may be a physical interface or a wireless connection mode. The control device readable storage medium is illustratively connected to the control device via an interface such as USB, HDMI, SATA or via a wireless communication protocol such as bluetooth, wiFi, etc.
When the control device readable storage medium is connected with the control device, the control device can read and execute corresponding execution instructions from the control device readable storage medium so as to realize fault diagnosis of the water pump.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the present application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (10)
1. A method of diagnosing a failure of a water pump, comprising:
collecting vibration data of a water pump, and extracting a vibration parameter set;
determining a sensitive characteristic parameter set in the vibration parameter set according to the sensitivity degree of the data in the vibration parameter set to faults;
trend analysis is carried out according to the data distribution of the sensitive characteristic parameter set, and the running state of the water pump in a future set time period is predicted;
comparing the running state in the future set time period with the fault state in the fault diagnosis knowledge base, and predicting the fault trend of the water pump.
2. The method of diagnosing a malfunction of a water pump according to claim 1, further comprising:
and predicting failure occurrence rate, failure point and failure type of different component nodes of the water pump according to the current running state and the future running state of the water pump.
3. The method of diagnosing a malfunction of a water pump according to claim 1, wherein the collecting vibration data of the water pump and extracting a vibration parameter set includes:
collecting vibration data of the water pump, and performing time domain analysis to obtain a primary selection data set;
and carrying out frequency domain analysis on the primary selection data to obtain a vibration parameter set.
4. The method of diagnosing a malfunction of a water pump according to claim 1, wherein the collecting vibration data of the water pump and extracting a vibration parameter set includes:
collecting vibration data of the water pump, and decomposing the vibration data to obtain a primary selection data set;
and analyzing the primary selection data set to obtain a vibration parameter set.
5. The method according to claim 2, wherein predicting the failure occurrence rate, the failure point, and the failure type of the different nodes based on the current operation state and the future operation state of the water pump comprises:
and inputting the sensitive characteristic parameter set into the fault diagnosis model, and outputting the fault occurrence rate, the fault point and the fault type.
6. The method of diagnosing a malfunction of a water pump according to claim 5, further comprising:
collecting vibration signals representing different faults as original data of the fault diagnosis model;
extracting features of the original data to be used as training and testing samples of a twin neural network model;
and training and optimizing the twin neural network model to obtain the fault diagnosis model.
7. The method for diagnosing a malfunction of a water pump according to any one of claims 1 to 6, further comprising:
inputting historical record data of the water pump;
extracting associated data of which the degree of correlation with the vibration state of the water pump is higher than a threshold value from the historical record data;
performing whitening treatment on the associated data to obtain gray association degree among the associated data, and sequencing;
obtaining an association rule between the history data and the vibration state;
and training a hierarchical model for quantifying the health state of the system, and establishing a fault diagnosis knowledge base according to the association rule.
8. The method for diagnosing a malfunction of a water pump according to any one of claims 1 to 6, further comprising:
and generating a fault diagnosis list and an equipment state monitoring report.
9. A control apparatus comprising a processor for executing code to perform the method of diagnosing a failure of the water pump of any one of claims 1-7, and a memory for storing the code for the processor to perform the method.
10. A control device readable storage medium, wherein a fault diagnosis execution instruction is stored in the control device readable storage medium, which execution instruction, when executed by a control device, is for implementing the fault diagnosis method of the water pump according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311844581.2A CN117786461A (en) | 2023-12-27 | 2023-12-27 | Water pump fault diagnosis method, control device and storage medium thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311844581.2A CN117786461A (en) | 2023-12-27 | 2023-12-27 | Water pump fault diagnosis method, control device and storage medium thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117786461A true CN117786461A (en) | 2024-03-29 |
Family
ID=90386957
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311844581.2A Pending CN117786461A (en) | 2023-12-27 | 2023-12-27 | Water pump fault diagnosis method, control device and storage medium thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117786461A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118194165A (en) * | 2024-05-17 | 2024-06-14 | 湖南大学 | Assembly robot fault diagnosis feature transformation method based on transfer learning |
-
2023
- 2023-12-27 CN CN202311844581.2A patent/CN117786461A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118194165A (en) * | 2024-05-17 | 2024-06-14 | 湖南大学 | Assembly robot fault diagnosis feature transformation method based on transfer learning |
| CN118194165B (en) * | 2024-05-17 | 2024-08-09 | 湖南大学 | Assembly robot fault diagnosis feature transformation method based on transfer learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220283576A1 (en) | Automatic diagnosis method, system and storage medium for equipment | |
| Yu | Health condition monitoring of machines based on hidden Markov model and contribution analysis | |
| Li et al. | Bearing fault feature selection method based on weighted multidimensional feature fusion | |
| JPH07168619A (en) | Method and system for equipment/facility diagnosis | |
| KR102206737B1 (en) | Method and system for fault diagnosis of pump-turbines based on machine learning | |
| CN107291475B (en) | Universal PHM application configuration method and device | |
| KR20190013017A (en) | Method and device for equipment health monitoring based on sensor clustering | |
| CN111964909A (en) | Rolling bearing operation state detection method, fault diagnosis method and system | |
| CN114184367B (en) | Rotary mechanical equipment fault diagnosis method, device, equipment and readable storage medium | |
| CN111881594A (en) | Non-stationary signal state monitoring method and system for nuclear power equipment | |
| CN116625683A (en) | Wind turbine generator system bearing fault identification method, system and device and electronic equipment | |
| US6107919A (en) | Dual sensitivity mode system for monitoring processes and sensors | |
| CN117786461A (en) | Water pump fault diagnosis method, control device and storage medium thereof | |
| CN118051822A (en) | Equipment running state abnormality detection method based on voiceprint recognition technology | |
| CN112380782A (en) | Rotating equipment fault prediction method based on mixed indexes and neural network | |
| CN115392782A (en) | Method and system for monitoring and diagnosing health state of process system of nuclear power plant | |
| CN112257224B (en) | Method, system and terminal for overhauling state of steam turbine generator | |
| CN118033266A (en) | Transformer fault prediction method and system considering non-uniform aging | |
| US11339763B2 (en) | Method for windmill farm monitoring | |
| CN117423345A (en) | Voiceprint recognition monitoring system for power equipment | |
| CN117708542A (en) | Equipment fault diagnosis method and system based on deep neural network | |
| CN114837902B (en) | Health degree evaluation method, system, equipment and medium for wind turbine generator | |
| CN116226719A (en) | Bearing fault diagnosis method based on multidimensional steady-state vibration characteristics and related components | |
| KR102212022B1 (en) | Method of automatically determining condition of hydro turbine in hydroelectric power plant and system for the same | |
| Yang et al. | Remaining useful life prediction for bearing based on online oil parameters and vibration signals |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Lei Chengliang Inventor after: Zhang Meijun Inventor after: Zhu Yiping Inventor after: Zhang Xiaobo Inventor after: Hao Wei Inventor after: Zhu Ruiting Inventor after: Xue Dong Inventor after: Zou Zubing Inventor after: Hu He Inventor after: Lin Xuelong Inventor after: Wang Yunhu Inventor after: Gui Ben Inventor after: Jin Xuewei Inventor after: Li Xiaojing Inventor after: Feng Rui Inventor before: Lei Chenglong Inventor before: Zhang Meijun Inventor before: Zhu Yiping Inventor before: Zhang Xiaobo Inventor before: Hao Wei Inventor before: Zhu Ruiting Inventor before: Xue Dong Inventor before: Zou Zubing Inventor before: Hu He Inventor before: Lin Xuelong Inventor before: Wang Yunhu Inventor before: Gui Ben Inventor before: Jin Xuewei Inventor before: Li Xiaojing Inventor before: Feng Rui |