CN112084909A - Fault diagnosis method, system and computer readable storage medium - Google Patents
Fault diagnosis method, system and computer readable storage medium Download PDFInfo
- Publication number
- CN112084909A CN112084909A CN202010885405.3A CN202010885405A CN112084909A CN 112084909 A CN112084909 A CN 112084909A CN 202010885405 A CN202010885405 A CN 202010885405A CN 112084909 A CN112084909 A CN 112084909A
- Authority
- CN
- China
- Prior art keywords
- macro
- test
- module
- data
- fault diagnosis
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 147
- 238000000034 method Methods 0.000 title claims abstract description 110
- 238000012360 testing method Methods 0.000 claims abstract description 201
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 36
- 238000004458 analytical method Methods 0.000 claims abstract description 16
- 238000010168 coupling process Methods 0.000 claims description 24
- 238000005859 coupling reaction Methods 0.000 claims description 24
- 230000008878 coupling Effects 0.000 claims description 23
- 230000002159 abnormal effect Effects 0.000 claims description 21
- 230000004044 response Effects 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- 238000013528 artificial neural network Methods 0.000 description 7
- 238000005259 measurement Methods 0.000 description 7
- 238000002474 experimental method Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000000429 assembly Methods 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Abstract
A fault diagnosis method comprising: dividing the target system into at least one macro module according to the fault diagnosis requirement analysis result of the target system, wherein any macro module is a modeling macro module or a non-modeling macro module; determining typical faults of any macro module, corresponding test points and test parameters of the macro module, and acquiring test data of the macro module by using the test points and the test parameters; aiming at the modeling macro module, according to the test data, adopting a model diagnosis method to carry out fault diagnosis; and aiming at the unmodeled macro module, according to the test data, adopting an artificial intelligence data driving fault diagnosis method to carry out fault diagnosis.
Description
Technical Field
The present disclosure relates to, but not limited to, the field of fault diagnosis technologies, and in particular, to a fault diagnosis method, system, and computer readable storage medium.
Background
Fault diagnosis methods can be generally divided into two major categories, namely, fault diagnosis methods based on models and fault diagnosis methods based on data driving. The fault diagnosis method based on the model is the key point of the research of the early classical fault diagnosis method, and mainly aims at diagnosing a system easy to model; the data-driven fault diagnosis method is generally used for the situation that a system which is difficult to model or a model is not high in accuracy.
Disclosure of Invention
The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.
The application provides a fault diagnosis method, which comprises the following steps: dividing a target system into at least one macro module according to the fault diagnosis requirement analysis result of the target system; any macro module is a modeling macro module or an unmodeled macro module; determining typical faults of the macro module, corresponding test points and test parameters aiming at any macro module, and acquiring test data of the macro module by using the test points and the test parameters; for any modeling macro module, fault diagnosis is carried out by adopting a model diagnosis method according to the obtained test data; and aiming at any non-modeled macro module, carrying out fault diagnosis by adopting an artificial intelligence data driving fault diagnosis method according to the obtained test data.
In some exemplary embodiments, for any macro block, determining a test point corresponding to a typical fault of the macro block includes: when the target system is divided into a plurality of macro modules and different macro modules have no coupling relation, selecting test points corresponding to typical faults from a plurality of signal output ends of each macro module; when the target system is divided into a plurality of macro blocks and different macro blocks have coupling relations, test points corresponding to typical faults are selected from a plurality of signal output ends and internal nodes of each macro block.
In some exemplary embodiments, the obtaining of the test data of the macroblock using the test point and the test parameters includes: the test point of the macro module in the fault-free state corresponds to the first test data of the test parameter, and the test point of the macro module in the fault state corresponds to the second test data of the test parameter.
In some exemplary embodiments, when the target system is divided into a plurality of macro blocks and there is a coupling relationship between the macro blocks, the fault determination rule for determining a faulty macro block in the target system includes: aiming at any macro module of which the test point comprises a signal output end and an internal node, when the output data of the internal node is normal and the output data of the signal output end is abnormal, a fault occurs in the macro module or a subsequent N-level macro module connected with the signal output end of the macro module, wherein N is an integer larger than 0; when the output data of the internal node is abnormal and the output data of the signal output end is abnormal, the fault occurs in the macro module; when the output data of the internal node is abnormal and the output data of the signal output end is normal, the fault occurs in the macro module.
In some exemplary embodiments, the test data of the macro block includes: response signal data of the test point of the macro module, or feature data obtained by processing the response signal data.
In some exemplary embodiments, the fault diagnosis method further includes:
respectively training a plurality of artificial intelligence data-driven fault diagnosis methods by adopting the test data of the plurality of combinations of the non-modeled macro modules, wherein the signal types of the test data in different combinations are different or partially the same; and selecting an optimal artificial intelligence data-driven fault diagnosis method from a plurality of trained artificial intelligence data-driven fault diagnosis methods to carry out fault diagnosis on the unmodeled macro module.
The present application provides a fault diagnosis system, comprising:
the system comprises a dividing module, a judging module and a judging module, wherein the dividing module is configured to divide a target system into at least one macro module according to a fault diagnosis requirement analysis result of the target system; any macro module is a modeling macro module or an unmodeled macro module; the test module is configured to determine typical faults of the macro module, corresponding test points and test parameters aiming at any macro module, and obtain test data of the macro module by using the test points and the test parameters; the diagnosis module is configured to perform fault diagnosis by adopting a model diagnosis method according to the obtained test data aiming at any one of the modeled macro modules; and aiming at any non-modeled macro module, carrying out fault diagnosis by adopting an artificial intelligence data driving fault diagnosis method according to the obtained test data.
In some exemplary embodiments, the test module is configured to determine the test point corresponding to a typical failure of any macro module by:
when the target system is divided into a plurality of macro modules and different macro modules have no coupling relation, selecting test points corresponding to typical faults from a plurality of signal output ends of each macro module; when the target system is divided into a plurality of macro blocks and different macro blocks have coupling relations, test points corresponding to typical faults are selected from a plurality of signal output ends and internal nodes of each macro block.
The present application further provides a fault diagnosis system, including: a memory in which a computer program is stored, and a processor, the computer program of the memory being executed by the processor to perform any of the above-described fault diagnosis methods.
The application also provides a computer-readable storage medium, wherein the storage medium stores computer-executable commands, and the computer-executable commands are used for executing any one of the fault diagnosis methods.
In the fault diagnosis method and system provided by the application, the target system is divided into at least one macro module according to the analysis result of the fault diagnosis requirement, any macro module is a modeled macro module or a non-modeled macro module, fault diagnosis is carried out by adopting a model diagnosis method aiming at the modeled macro module, and fault diagnosis is carried out by adopting an artificial intelligence data driving fault diagnosis method aiming at the non-modeled macro module, so that the advantages of two fault diagnosis modes of the model diagnosis method and the artificial intelligence data driving fault diagnosis method are fully combined, data processing can be simplified, and the practicability of fault diagnosis is improved.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and drawings.
Drawings
The accompanying drawings are included to provide an understanding of the present disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the examples serve to explain the principles of the disclosure and not to limit the disclosure.
Fig. 1 is a flowchart of a fault diagnosis method provided in an embodiment of the present application;
fig. 2 is an exemplary diagram of a macro module of a target system according to an embodiment of the present application;
FIG. 3 is a diagram illustrating an example of a macro module of another target system provided by an embodiment of the present application;
fig. 4 is a schematic structural diagram of a fault diagnosis system provided in an embodiment of the present application;
fig. 5 is a schematic structural diagram of another fault diagnosis system provided in the embodiment of the present application.
Detailed Description
The present application describes embodiments, but the description is illustrative rather than limiting and it will be apparent to those of ordinary skill in the art that many more embodiments and implementations are possible within the scope of the embodiments described herein. Although many possible combinations of features are shown in the drawings and discussed in the detailed description, many other combinations of the disclosed features are possible. Any feature or element of any embodiment may be used in combination with or instead of any other feature or element in any other embodiment, unless expressly limited otherwise.
The present application includes and contemplates combinations of features and elements known to those of ordinary skill in the art. The embodiments, features and elements disclosed in this application may also be combined with any conventional features or elements to form a unique inventive concept as defined by the claims. Any feature or element of any embodiment may also be combined with features or elements from other inventive aspects to form yet another unique inventive aspect, as defined by the claims. Thus, it should be understood that any of the features shown and/or discussed in this application may be implemented alone or in any suitable combination. Accordingly, the embodiments are not limited except as by the appended claims and their equivalents. Furthermore, various modifications and changes may be made within the scope of the appended claims.
Further, in describing representative embodiments, the specification may have presented the method and/or process as a particular sequence of steps. However, to the extent that the method or process does not rely on the particular order of steps set forth herein, the method or process should not be limited to the particular sequence of steps described. Other orders of steps are possible as will be understood by those of ordinary skill in the art. Therefore, the particular order of the steps set forth in the specification should not be construed as limitations on the claims. Further, the claims directed to the method and/or process should not be limited to the performance of their steps in the order written, and one skilled in the art can readily appreciate that the sequences may be varied and still remain within the spirit and scope of the embodiments of the present application.
In the present disclosure, "a plurality" means two and more than two. The ordinal numbers such as "first", "second", and the like in the present disclosure are provided to avoid confusion of the constituent elements, and are not limited in terms of number.
At least one embodiment of the present disclosure provides a fault diagnosis method, a system, and a computer-readable storage medium, which fully combine the advantages of two fault diagnosis methods, namely, a model diagnosis method and an artificial intelligence data-driven fault diagnosis method, and can simplify data processing and improve the practicability of fault diagnosis.
Fig. 1 is a flowchart of a fault diagnosis method according to at least one embodiment of the present disclosure. As shown in fig. 1, the fault diagnosis method of the present embodiment includes the following steps:
103, aiming at the modeling macro module, performing fault diagnosis by adopting a model diagnosis method according to the test data; and aiming at the unmodeled macro module, according to the test data, adopting an artificial intelligence data driving fault diagnosis method to carry out fault diagnosis.
The fault diagnosis method provided by the embodiment can be applied to different types of target systems, such as an electronic system, a mechanical system, an electromechanical hybrid system and the like. However, the present disclosure is not limited thereto.
In some exemplary embodiments, the hardware elements involved in implementing the same function are treated as a macro block in the target system. A macroblock can be treated as a functional unit. In the fault diagnosis method of the present embodiment, only the following two states of the macroblock are distinguished: a no fault condition and a fault condition. The fault diagnosis method of the embodiment is used for determining whether the target system has a fault, and if the target system has the fault, which macro module has the fault, so that the targeted maintenance can be performed subsequently. By dividing the state of the macro module into two types of no fault and fault, detailed fault types do not need to be distinguished, the data processing process can be simplified, and the practical use is convenient.
In some examples, the fault diagnosis requirement analysis result of the target system includes at least one of: the system comprises a target system, a configuration (for example, the type and number of electronic components included in the target system, etc.), a structure (for example, the coupling relationship between the electronic components included in the target system, etc.), a working principle (for example, information about the working mode of the target system, etc.), and a fault location requirement of a user (for example, a fault location range (for example, a component or assembly in which a fault exists needs to be located), a fault location real-time requirement (for example, a time requirement required for obtaining a fault diagnosis result), etc.). However, this embodiment is not limited to this. In some examples, the macro block of the target system may be divided according to various information of the target system through comprehensive analysis and balancing.
In some examples, the target system is partitioned into at least one macroblock in a manner that facilitates isolating the location fault while meeting the user location range requirements. For example, when it is necessary to obtain a diagnosis result of whether a target system has a fault within a shortest time, the entire target system may be divided into one macroblock. For example, when a component fault existing in the target system needs to be diagnosed, the entire target system may be divided into a plurality of macro blocks, and each macro block may include a component (e.g., a resistor, a capacitor, or a diode). For example, when a component or component existing in the target system needs to be diagnosed, the entire target system may be divided into a plurality of macro blocks, and each macro block may include components or components (e.g., circuit boards) involved in implementing the same function. The macro module of the embodiment is flexible and various in division mode, and can be completely adapted to various practical application scenes. For example, when a fault diagnosis needs to be performed on an armored vehicle system in a military maneuver, the armored vehicle system may be divided into macro-modules according to a subsystem level or a field replaceable unit level, so as to quickly locate the fault and repair the system (for example, locate a circuit board with a fault and replace the whole circuit board); in routine maintenance of armored vehicle systems, the armored vehicle systems may be macro-modular in component level to facilitate accurate fault location and maintenance (e.g., locating a faulty component and replacing a particular component).
In some examples, when the target system is divided into a plurality of macroblocks, the hardware units included in different macroblocks may be completely different, or partially the same. This embodiment is not limited to this.
In some examples, the plurality of macroblocks demarcated by the target system may include both modeled and unmodeled macroblocks types. Any of the macroblocks can be either modeled or unmodeled. All hardware elements (e.g., components, parts, or assemblies) that are encompassed by a modeled macroblock may be modeled (i.e., fully expressed using a mathematical or physical model). Unmodeled macroblocks contain hardware elements that are not convenient to model. In the embodiment, different fault diagnosis modes are adopted for the modeled macro module and the unmodeled macro module, so that the fault diagnosis complexity of the target system is reduced, and the fault diagnosis efficiency is improved.
In some exemplary embodiments, typical failures of any macroblock and corresponding test points and test parameters may be determined by Failure Mode, impact and hazard Analysis (FMECA, Failure Mode, Effects and Criticality Analysis). FMECA is a technique summarized in engineering practice that is based on failure modes and an analysis that targets the effects or consequences of a failure. For example, for any macro block, information such as typical faults and fault reasons of the macro block can be obtained through FMECA.
In some examples, when the target system is divided into a plurality of macroblocks and there is no coupling relationship between different macroblocks, test points corresponding to typical faults may be selected from a plurality of signal outputs of each macroblock. When the target system is divided into a plurality of macro blocks and coupling relations exist among the different macro blocks, test points corresponding to typical faults can be selected from a plurality of signal output ends of each macro block and a plurality of internal nodes. When the target system is divided into a macro block, test points corresponding to typical faults can be selected from a plurality of internal nodes of the macro block.
In some exemplary embodiments, the macro block test data obtained by using the test points and the test parameters of the macro block includes: the test point of the macro module in the fault-free state corresponds to the first test data of the test parameters, and the test point of the macro module in the fault state corresponds to the second test data of the test parameters. The second test data corresponding to the test parameters and the test points of the macro module in the fault state includes: and testing data corresponding to the testing parameters are tested according to the testing points of the macro module under various typical faults analyzed by the FMECA. In some examples, for a modeled macroblock, first test data corresponding to test points and test parameters of the modeled macroblock in a fault-free state can be obtained through simulation analysis; and acquiring second test data corresponding to the test points and the test parameters of the modeled macro module in the typical fault state by simulating the typical fault analyzed according to the FMECA through software. Aiming at the non-modeled macro module, acquiring first test data corresponding to test points and test parameters of the non-modeled macro module in a fault-free state in a mode of simulating an operation experiment, a bench experiment and the like; and simulating typical faults analyzed according to FMECA through modes of simulating operation experiments, bench experiments and the like to obtain second test data corresponding to the test points and the test parameters of the non-modeled macro module in the typical fault state. However, the present embodiment is not limited to the manner of acquiring the test data.
In some exemplary embodiments, in the actual diagnosis process, actual measurement data corresponding to the test points of the modeled macro module and the test parameters may be obtained, and whether the modeled macro module fails or not may be determined according to a comparison result between the test data and the actual measurement data of the test points of the modeled macro module by using a model diagnosis method (e.g., a fault dictionary method, a sub-network tearing method, a spectrum analysis method, etc.). For the unmodeled macro module, in the actual diagnosis process, actual measurement data corresponding to the test points and the test parameters of the unmodeled macro module can be obtained, and whether the unmodeled macro module has a fault or not is judged by using an artificial intelligence data driving fault diagnosis method (such as a neural network method, a support vector machine method and the like) based on the actual measurement data.
In some exemplary embodiments, when the target system is divided into a plurality of macro blocks and there is a coupling relationship between the macro blocks, the fault determination rule for determining a macro block having a fault in the target system may include: aiming at any one macro module of a test point comprising a signal output end and an internal node, when the output data of the internal node is normal and the output data of the signal output end is abnormal, a fault occurs in the macro module or a subsequent N-level macro module connected with the signal output end of the macro module, wherein N is an integer greater than 0; when the output data of the internal node is abnormal and the output data of the signal output end is abnormal, the fault occurs in the macro module; when the output data of the internal node is abnormal and the output data of the signal output end is normal, the fault occurs in the macro module. When the fault is masked by the specific logic and is not sensitized and transmitted, the output data of the internal node of the macro module is abnormal, the output data of the signal output end is normal, but the macro module has a fault.
In some exemplary embodiments, the test data of the macro block includes: response signal data of a test point of the macro module, or feature data obtained by processing the response signal data. In some examples, the response signal data for the test points of the macro block may include: real-time current values, real-time voltage values, real-time temperature values, and the like. The characteristic data may include: maximum, minimum, mean, variance of output voltage, frequency spectrum, power spectrum of mechanical vibration, etc. However, this embodiment is not limited to this.
In some examples, when the target system is a dc electronic system, in the fault diagnosis process of the target system, response signal data may be collected from the test points of the macro module, and the collected response signal data (e.g., current values, voltage values, etc.) of the test points may be directly used for fault diagnosis. In some examples, when the target system is an ac electrical subsystem, in a fault diagnosis process of the target system, response signal data may be collected from test points of the macro module, the directly collected response signal data (e.g., a current value, a voltage value, etc.) may be processed to obtain characteristic data (e.g., a current average value, a voltage average value, etc.), and fault diagnosis may be performed using the characteristic data.
In some exemplary embodiments, the fault diagnosis method of the present embodiment further includes: respectively training a plurality of artificial intelligence data-driven fault diagnosis methods by adopting the test data of the plurality of combinations of the non-modeled macro blocks, wherein the signal types (such as current, voltage, temperature, pressure, amplitude and the like) of the test data in different combinations are different or partially the same; and selecting an optimal artificial intelligence data-driven fault diagnosis method from a plurality of trained artificial intelligence data-driven fault diagnosis methods to carry out fault diagnosis on the unmodeled macro module. For example, the target system is an electronic system, and the signal types of the test data of the unmodeled macro block include: and voltage, current and temperature, the test values of the voltage and the current can be used as one combined test data to train one artificial intelligence data-driven fault diagnosis method, the test values of the voltage, the current and the temperature can be used as another combined test data to train another artificial intelligence data-driven fault diagnosis method, and according to the diagnosis accuracy of the two artificial intelligence data-driven fault diagnosis methods, one artificial intelligence data-driven fault diagnosis method with high diagnosis accuracy is selected to carry out fault diagnosis on the unmodeled macro module of the target system.
In the exemplary embodiment, the test data includes response signal data or characteristic data of the macroblock in different states, including a no fault state and a fault state. The feature data is signal data (e.g., mean, variance, effective value, peak, kurtosis, frequency component, power spectrum, etc.) after secondary processing of the response signal data of the macroblock in different states. Artificial intelligence data-driven fault diagnostics is essentially the correct classification of response signal data or feature data. The response signals of the unmodeled macroblock are generally of various types, such as vibration, pressure, temperature, voltage current, and the like. It is generally determined by comparing actual fault detection accuracy rates, as to which signals can better distinguish different states depending on the situation. A neural network classifier is designed, test data of an unmodeled macro module in a fault-free state is used as one type of input data, test data in various typical fault states are used as the other type of input data, and a two-classifier is designed. Assuming that the output states correspond to [ 0, 1 ] (for example, output 0 indicates no fault, output 1 indicates fault), the input data of the input layer of the neural network may be selected as the test data (i.e., the original response signal data) of the macro module of the target system, or may be selected as the feature data after the test data is subjected to secondary processing. The connection weights of different hidden layers and output layers of the neural network are adjusted and solidified through training of a certain data volume. Finally, the test data under some typical faults are selected as test samples, the output classification accuracy of the neural network classifier under different input data is counted, and when the classification accuracy reaches a relatively acceptable degree (such as 90%), the neural network classifier is considered to be feasible.
In some exemplary embodiments, the fault diagnosis method of the present embodiment further includes: training a plurality of artificial intelligence data-driven fault diagnosis methods of different types, and selecting the optimal artificial intelligence data-driven fault diagnosis method from the artificial intelligence data-driven fault diagnosis methods to carry out fault diagnosis on the unmodeled macro module.
In some examples, the artificial intelligence data driven fault diagnostics may include: artificial neural networks, support vector machine methods, and methods of driving fault diagnosis using different types of artificial intelligence data. The diagnosis and identification accuracy of various artificial intelligence algorithms needs to be obtained by experiments and simulation data training tests of specific target systems to be diagnosed, and the optimal method is selected by taking different test data or characteristic data as input and considering various factors (such as identification accuracy, training time, algorithm convergence stability and the like). On the basis of selecting the optimal method, the accuracy of classification judgment can be further improved through further perfection of the details of the division mode of the macro model, selection of the test points and the test parameters, improvement of the feature extraction aspect of the test data and the like until the judgment accuracy reaches an ideal value.
According to the fault diagnosis method provided by the embodiment, the target system is divided into the macro module, and fault diagnosis is performed based on the macro module in combination with the model diagnosis method and the artificial intelligence data driving fault diagnosis method, so that the data processing process can be simplified, the practicability is improved, and the fault diagnosis method is suitable for various actual scenes.
The technical solution of the present embodiment is illustrated by a plurality of exemplary embodiments.
Fig. 2 is an exemplary diagram of a macro module of a target system according to at least one embodiment of the disclosure, which takes a land battle equipment system as an example, and the equipment system mainly includes: weapon system, protection system, power propulsion system, communication system and power supply and distribution system. The major functions performed by the subsystems are independent and different, so that each subsystem can be defined as a large macro-module with no coupling between modules, using the relationships shown in fig. 2. As shown in fig. 2, in the exemplary embodiment, the target system may be divided into five macroblocks (i.e., macroblocks 11, 12, 13, 14, and 15) according to the user's requirements for fault location scope (e.g., location to subsystem level). The five macroblocks may include both modeled and unmodeled macroblocks, or one portion may be modeled and another portion may be unmodeled macroblocks. However, this embodiment is not limited to this.
In the present exemplary embodiment, as shown in fig. 2, there is no coupling relationship between the five macroblocks divided by the target system. For any macro module, according to FMECA, typical faults of the macro module can be determined, test points corresponding to the typical faults are selected from the signal output end of the macro module, and corresponding test parameters are determined. As shown in fig. 2, the test point of the macro block 11 includes a signal output terminal T1Macro block 12Includes a signal output terminal T2The test point of the macro module 13 comprises a signal output end T3The test point of the macroblock 14 includes a signal output terminal T4The test point of the macro block 15 includes a signal output terminal T5。
In the exemplary embodiment, there is no coupling between the five macroblocks shown in fig. 2, and each macroblock can be tested separately and diagnosed independently. For any macro block, test data of the test points of the macro block under a no-fault state and a fault state (for example, a typical fault obtained by FMECA analysis) can be obtained through simulation. In the actual diagnosis process, for the modeled macro module in the target system, actual measurement data can be obtained from the test point of each modeled macro module of the target system, and then, a model diagnosis method is adopted to judge whether the modeled macro module has a fault according to the comparison result between the actual measurement data and the test data of the test point. For the non-modeled macro module in the target system, actual measurement data can be obtained from the test point of each non-modeled macro module of the target system, and then an artificial intelligence data-driven fault diagnosis method is adopted to judge whether the non-modeled macro module has a fault.
Fig. 3 is another exemplary diagram of a macro module of a target system according to at least one embodiment of the present disclosure, which illustrates a specific control system hardware circuit, where each macro module is a different functional block composed of different discrete components or integrated chip circuits, and the connection relationship of each macro module is the connection sequence relationship of respective signal output and input. The macro block of the present exemplary figure contains many fewer components and parts than the sub-system macro block of figure 2. As shown in fig. 3, in the present exemplary embodiment, the target system may be divided into 8 macroblocks (i.e., macroblocks 21, 22, 23, 24, 25, 26, 27, and 28) according to the result of the fault requirement analysis of the target system. The eight macro blocks are not limited in type, and may be modeled macro blocks or unmodeled macro blocks, for example, although a specific modeled macro block is illustrated here.
In the present exemplary embodiment, as shown in fig. 3, the target systemThere is a coupling relation between the eight divided macro blocks. Macroblock 21 is coupled to macroblocks 22 and 23, macroblock 22 is coupled to macroblock 21, macroblock 24, and macroblock 25, macroblock 23 is coupled to macroblocks 21 and 26, macroblock 24 is coupled to macroblocks 22 and 28, macroblock 25 is coupled to macroblocks 22, 26, and 27, and macroblock 27 is coupled to macroblocks 25 and 28. For any macro module, according to FMECA, typical faults of the macro module can be determined, test points corresponding to the typical faults are selected from the signal output end of the macro module, and corresponding test parameters are determined. As shown in fig. 3, the test points of macro block 21 include internal nodes TI1And signal output terminal TM1And TM2(ii) a The test points of the macroblock 22 include a signal output terminal TM3And TM4(ii) a The test point of the macroblock 23 comprises a signal output terminal TM5(ii) a The test point of the macroblock 24 comprises a signal output terminal TM6(ii) a The test point of macro-module 25 includes a signal output terminal TM7And TM8(ii) a The test point of the macroblock 26 comprises a signal output terminal TM9(ii) a The test point of the macroblock 27 comprises a signal output TM10(ii) a The test points of macro block 28 include signal output terminal TM11。
In the present exemplary embodiment, there is a coupling between the eight macroblocks shown in fig. 3. The test data acquisition and fault diagnosis method for the modeled macro module and the unmodeled macro module may refer to the description of the no-coupling condition, and therefore, the description thereof is omitted here. In this example, due to the coupling between the eight macro blocks, the fault determination rule of the target system may include: aiming at any one macro module of a test point comprising a signal output end and an internal node, when the output data of the internal node is normal and the output data of the signal output end is abnormal, a fault occurs in the macro module or a subsequent N-level macro module connected with the signal output end of the macro module, wherein N is an integer greater than 0; when the output data of the internal node is abnormal and the output data of the signal output end is abnormal, the fault occurs in the macro module; when the output data of the internal node is abnormal and the output data of the signal output end is normal, the fault occurs in the macro module.
Fig. 4 is a schematic structural diagram of a fault diagnosis system according to at least one embodiment of the present disclosure. As shown in fig. 4, the fault diagnosis system of the present embodiment includes:
the dividing module 201 is configured to divide a target system into at least one macro module according to a fault diagnosis requirement analysis result of the target system; any macro module is a modeling macro module or an unmodeled macro module;
a test module 202 configured to determine a typical fault of a macro module, a corresponding test point and a corresponding test parameter for any macro module, and obtain test data of the macro module by using the test point and the test parameter;
the diagnosis module 203 is configured to perform fault diagnosis by adopting a model diagnosis method according to the obtained test data aiming at any one of the modeled macro modules; and aiming at any non-modeled macro module, carrying out fault diagnosis by adopting an artificial intelligence data driving fault diagnosis method according to the obtained test data.
In some examples, the testing module 202 is configured to determine the test points corresponding to typical failures of any macro module by:
when the target system is divided into a plurality of macro modules and different macro modules have no coupling relation, selecting test points corresponding to typical faults from a plurality of signal output ends of each macro module;
when the target system is divided into a plurality of macro blocks and different macro blocks have coupling relations, test points corresponding to typical faults are selected from a plurality of signal output ends and internal nodes of each macro block.
In some examples, the obtaining test data for the macroblock using the test point and the test parameters includes: the test point of the macro module in the fault-free state corresponds to the first test data of the test parameter, and the test point of the macro module in the fault state corresponds to the second test data of the test parameter.
In some examples, when the target system is divided into a plurality of macro blocks and there is a coupling relationship between the macro blocks, the fault determination rule for determining a macro block in the target system that has a fault includes: aiming at any one macro module of a test point comprising a signal output end and an internal node, when the output data of the internal node is normal and the output data of the signal output end is abnormal, a fault occurs in the macro module or a subsequent N-level macro module connected with the signal output end of the macro module, wherein N is an integer greater than 0; when the output data of the internal node is abnormal and the output data of the signal output end is abnormal, the fault occurs in the macro module; when the output data of the internal node is abnormal and the output data of the signal output end is normal, the fault occurs in the macro module.
In some examples, the test data for the macroblock includes: response signal data of the test point of the macro module, or feature data obtained by processing the response signal data.
In some examples, the diagnostic module 202 is further to:
respectively training a plurality of artificial intelligence data-driven fault diagnosis methods by adopting the test data of the plurality of combinations of the non-modeled macro modules, wherein the signal types of the test data in different combinations are different or partially the same;
and selecting an optimal artificial intelligence data-driven fault diagnosis method from a plurality of trained artificial intelligence data-driven fault diagnosis methods to carry out fault diagnosis on the unmodeled macro module.
Fig. 5 is a schematic structural diagram of another fault diagnosis system according to at least one embodiment of the present disclosure, as shown in fig. 5, including: a memory 301 and a processor 302, wherein the memory 301 stores a computer program, and the computer program of the memory 301 is executed by the processor 302 to execute the fault diagnosis method described in any one of the above embodiments.
The present disclosure also provides a computer-readable storage medium having stored thereon computer-executable instructions for performing the fault diagnosis method as described in any one of the above embodiments.
It will be understood by those of ordinary skill in the art that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware implementation, the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed by several physical components in cooperation. Some or all of the components may be implemented as software executed by a processor, such as a digital signal processor or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
Claims (10)
1. A fault diagnosis method comprising:
dividing a target system into at least one macro module according to the fault diagnosis requirement analysis result of the target system; any macro module is a modeling macro module or an unmodeled macro module;
determining typical faults of the macro module, corresponding test points and test parameters aiming at any macro module, and acquiring test data of the macro module by using the test points and the test parameters;
for any modeling macro module, fault diagnosis is carried out by adopting a model diagnosis method according to the obtained test data; and aiming at any non-modeled macro module, carrying out fault diagnosis by adopting an artificial intelligence data driving fault diagnosis method according to the obtained test data.
2. The method of claim 1, wherein determining, for any macroblock, test points corresponding to typical faults of the macroblock comprises:
when the target system is divided into a plurality of macro modules and different macro modules have no coupling relation, selecting test points corresponding to typical faults from a plurality of signal output ends of each macro module;
when the target system is divided into a plurality of macro blocks and different macro blocks have coupling relations, test points corresponding to typical faults are selected from a plurality of signal output ends and internal nodes of each macro block.
3. The method of claim 1, wherein the obtaining test data of the macroblock using the test point and the test parameter comprises: the test point of the macro module in the fault-free state corresponds to the first test data of the test parameter, and the test point of the macro module in the fault state corresponds to the second test data of the test parameter.
4. The fault diagnosis method according to claim 2, wherein when the target system is divided into a plurality of macro blocks and there is a coupling relationship between the macro blocks, the fault determination rule for determining the macro block having a fault in the target system includes: aiming at any macro module of which the test point comprises a signal output end and an internal node, when the output data of the internal node is normal and the output data of the signal output end is abnormal, a fault occurs in the macro module or a subsequent N-level macro module connected with the signal output end of the macro module, wherein N is an integer larger than 0; when the output data of the internal node is abnormal and the output data of the signal output end is abnormal, the fault occurs in the macro module; when the output data of the internal node is abnormal and the output data of the signal output end is normal, the fault occurs in the macro module.
5. The fault diagnosis method according to claim 1, characterized in that the test data of the macro module comprises: response signal data of the test point of the macro module, or feature data obtained by processing the response signal data.
6. The fault diagnosis method according to claim 1, characterized by further comprising:
respectively training a plurality of artificial intelligence data-driven fault diagnosis methods by adopting the test data of the plurality of combinations of the non-modeled macro modules, wherein the signal types of the test data in different combinations are different or partially the same;
and selecting an optimal artificial intelligence data-driven fault diagnosis method from a plurality of trained artificial intelligence data-driven fault diagnosis methods to carry out fault diagnosis on the unmodeled macro module.
7. A fault diagnosis system, comprising:
the system comprises a dividing module, a judging module and a judging module, wherein the dividing module is configured to divide a target system into at least one macro module according to a fault diagnosis requirement analysis result of the target system; any macro module is a modeling macro module or an unmodeled macro module;
the test module is configured to determine typical faults of the macro module, corresponding test points and test parameters aiming at any macro module, and obtain test data of the macro module by using the test points and the test parameters;
the diagnosis module is configured to perform fault diagnosis by adopting a model diagnosis method according to the obtained test data aiming at any one of the modeled macro modules; and aiming at any non-modeled macro module, carrying out fault diagnosis by adopting an artificial intelligence data driving fault diagnosis method according to the obtained test data.
8. The fault diagnosis system of claim 7 wherein the test module is configured to determine the test points corresponding to a typical fault for any macroblock by:
when the target system is divided into a plurality of macro modules and different macro modules have no coupling relation, selecting test points corresponding to typical faults from a plurality of signal output ends of each macro module;
when the target system is divided into a plurality of macro blocks and different macro blocks have coupling relations, test points corresponding to typical faults are selected from a plurality of signal output ends and internal nodes of each macro block.
9. A fault diagnosis system, comprising: a memory in which a computer program is stored and a processor, the computer program of the memory being executed by the processor to perform the fault diagnosis method according to any one of claims 1 to 6.
10. A computer-readable storage medium having stored thereon computer-executable instructions for performing the fault diagnosis method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010885405.3A CN112084909A (en) | 2020-08-28 | 2020-08-28 | Fault diagnosis method, system and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010885405.3A CN112084909A (en) | 2020-08-28 | 2020-08-28 | Fault diagnosis method, system and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112084909A true CN112084909A (en) | 2020-12-15 |
Family
ID=73728834
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010885405.3A Pending CN112084909A (en) | 2020-08-28 | 2020-08-28 | Fault diagnosis method, system and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112084909A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113672498A (en) * | 2021-07-19 | 2021-11-19 | 华人运通(江苏)技术有限公司 | Automatic diagnosis test method, device and equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5375126A (en) * | 1991-04-09 | 1994-12-20 | Hekimian Laboratories, Inc. | Integrated logical and physical fault diagnosis in data transmission systems |
| CN102707712A (en) * | 2012-06-06 | 2012-10-03 | 广州山锋测控技术有限公司 | Electronic equipment fault diagnosis method and system |
| CN103617105A (en) * | 2013-12-17 | 2014-03-05 | 中国科学院合肥物质科学研究院 | Self-adaptation multilevel flow model equipment diagnosis method based on data driving |
| CN106569095A (en) * | 2016-11-09 | 2017-04-19 | 于祥茹 | Power grid fault diagnosis system based on weighted average dependence classifier |
| CN110728377A (en) * | 2019-10-21 | 2020-01-24 | 山东大学 | Intelligent fault diagnosis method and system for electromechanical equipment |
| CN110766143A (en) * | 2019-10-31 | 2020-02-07 | 上海埃威航空电子有限公司 | Equipment fault intelligent diagnosis method based on artificial neural network |
| CN111176877A (en) * | 2019-12-27 | 2020-05-19 | 北京旋极信息技术股份有限公司 | Fault diagnosis method, system and readable medium for electronic information system |
| CN112084910A (en) * | 2020-08-28 | 2020-12-15 | 北京旋极信息技术股份有限公司 | Fault diagnosis method and system |
-
2020
- 2020-08-28 CN CN202010885405.3A patent/CN112084909A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5375126A (en) * | 1991-04-09 | 1994-12-20 | Hekimian Laboratories, Inc. | Integrated logical and physical fault diagnosis in data transmission systems |
| US5375126B1 (en) * | 1991-04-09 | 1999-06-22 | Hekimian Laboratories Inc | Integrated logical and physical fault diagnosis in data transmission systems |
| CN102707712A (en) * | 2012-06-06 | 2012-10-03 | 广州山锋测控技术有限公司 | Electronic equipment fault diagnosis method and system |
| CN103617105A (en) * | 2013-12-17 | 2014-03-05 | 中国科学院合肥物质科学研究院 | Self-adaptation multilevel flow model equipment diagnosis method based on data driving |
| CN106569095A (en) * | 2016-11-09 | 2017-04-19 | 于祥茹 | Power grid fault diagnosis system based on weighted average dependence classifier |
| CN110728377A (en) * | 2019-10-21 | 2020-01-24 | 山东大学 | Intelligent fault diagnosis method and system for electromechanical equipment |
| CN110766143A (en) * | 2019-10-31 | 2020-02-07 | 上海埃威航空电子有限公司 | Equipment fault intelligent diagnosis method based on artificial neural network |
| CN111176877A (en) * | 2019-12-27 | 2020-05-19 | 北京旋极信息技术股份有限公司 | Fault diagnosis method, system and readable medium for electronic information system |
| CN112084910A (en) * | 2020-08-28 | 2020-12-15 | 北京旋极信息技术股份有限公司 | Fault diagnosis method and system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113672498A (en) * | 2021-07-19 | 2021-11-19 | 华人运通(江苏)技术有限公司 | Automatic diagnosis test method, device and equipment |
| CN113672498B (en) * | 2021-07-19 | 2023-09-15 | 华人运通(江苏)技术有限公司 | Automatic diagnosis test method, device and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112084910A (en) | Fault diagnosis method and system | |
| US5919267A (en) | Neural network fault diagnostics systems and related method | |
| US6226760B1 (en) | Method and apparatus for detecting faults | |
| JP2004118839A (en) | Method for supporting specification of function unit failed in technical equipment | |
| CN110889111A (en) | Power grid virtual data injection attack detection method based on deep belief network | |
| CN105762427A (en) | Apparatus And Method For Controlling High Voltage Battery In Vehicle | |
| CN110308384B (en) | Analog circuit fault diagnosis method based on circle model and neural network | |
| CN113561853B (en) | On-line fault diagnosis method and device for fuel cell system | |
| CN112084909A (en) | Fault diagnosis method, system and computer readable storage medium | |
| CN103608815B (en) | Method and diagnostic system for supporting the controlled fault detection in technical systems | |
| US6370659B1 (en) | Method for automatically isolating hardware module faults | |
| CN112147973A (en) | Inspection system, method and apparatus for selecting a true test and test system | |
| EP2082375B1 (en) | Fault isolation in a vehicle | |
| CN115563868A (en) | Fault diagnosis method and device for oil circuit system of aviation alternating-current generator | |
| Franco | Experiences gained using the navy's IDSS weapon system testability analyzer | |
| AU2020227791B2 (en) | Method for monitoring points of a railway track installation | |
| CN113986618A (en) | Cluster brain split automatic repairing method, system, device and storage medium | |
| CN116341224A (en) | Method, system and readable storage medium for designing practical BIT of electromechanical hybrid system | |
| CN111880073A (en) | Built-in test design method and system | |
| CN112578194B (en) | Automobile electrical system fault troubleshooting method | |
| Foran et al. | An intelligent diagnostic system for distributed, multi-ECU automotive control systems | |
| CN111562489B (en) | Track circuit fault diagnosis method, terminal and storage medium | |
| CN113537288B (en) | Method and system for training target model based on modification of sample signal | |
| KR102632918B1 (en) | Relay accelerated life prediction system and method | |
| CN117609927B (en) | Method and device for determining production state of carbon discharging mechanism and electronic equipment |
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 |