CN111061253A - Fault diagnosis method, system and readable medium for electromechanical hybrid system - Google Patents
Fault diagnosis method, system and readable medium for electromechanical hybrid system Download PDFInfo
- Publication number
- CN111061253A CN111061253A CN201911378054.0A CN201911378054A CN111061253A CN 111061253 A CN111061253 A CN 111061253A CN 201911378054 A CN201911378054 A CN 201911378054A CN 111061253 A CN111061253 A CN 111061253A
- Authority
- CN
- China
- Prior art keywords
- flow model
- hybrid system
- diagnosed
- electromechanical hybrid
- 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
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
- G05B23/0227—Qualitative history assessment, whereby the type of data acted upon, e.g. waveforms, images or patterns, is not relevant, e.g. rule based assessment; if-then decisions
- G05B23/0229—Qualitative history assessment, whereby the type of data acted upon, e.g. waveforms, images or patterns, is not relevant, e.g. rule based assessment; if-then decisions knowledge based, e.g. expert systems; genetic algorithms
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
- G05B23/0245—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model based on a qualitative model, e.g. rule based; if-then decisions
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
A fault diagnosis method for an electromechanical hybrid system, comprising: dividing the electromechanical hybrid system to be diagnosed into a plurality of levels according to the requirement analysis result of the electromechanical hybrid system to be diagnosed, and dividing the electromechanical hybrid system to be diagnosed into a plurality of components on each level; establishing a flow model for each component in each hierarchy, the flow model comprising a signal flow model, an energy flow model and a control flow model; for each component in each hierarchy, determining a set of test signal parameters for the component in accordance with a flow model for the component; and based on the flow model and the test signal parameter set, performing fault location on the electromechanical hybrid system to be diagnosed by adopting an inference mode of an expert system.
Description
Technical Field
The present disclosure relates to the field of fault diagnosis technologies, and in particular, to a fault diagnosis method and system for an electromechanical hybrid system, and a readable medium.
Background
The automatic fault diagnosis of the current electromechanical hybrid system is one of hot spots and difficult problems in equipment security engineering application, while the current fault diagnosis methods are mostly fault diagnosis methods which are only aiming at electronic systems or mechanical systems, for example, fault diagnosis methods based on model diagnosis methods (such as fault dictionary, network tearing method and the like) or fault diagnosis methods based on pure data driven artificial intelligence, and the methods have the disadvantages that the global view angle is lacked, the method is too microscopic, and the method is generally only suitable for fault diagnosis of components or assemblies. For a complex electromechanical hybrid system, an expert system-based reasoning diagnosis method is generally adopted. However, the traditional inference diagnosis method based on the expert system mostly depends on fault statistics and expert experience, and due to the lack of scientific and systematic method for effectively dividing the large system, the efficiency of diagnosis inference is greatly reduced, the precision of fault location is also limited, and the diagnosis real-time performance and effectiveness are both required to be improved.
Disclosure of Invention
The application provides a fault diagnosis method, a fault diagnosis system and a readable medium for an electromechanical hybrid system, which can improve the real-time performance and effectiveness of fault diagnosis of the electromechanical hybrid system.
In one aspect, the present application provides a fault diagnosis method for an electromechanical hybrid system, including: dividing the electromechanical hybrid system to be diagnosed into a plurality of levels according to the requirement analysis result of the electromechanical hybrid system to be diagnosed, and dividing the electromechanical hybrid system to be diagnosed into a plurality of components on each level; establishing a flow model for each component in each hierarchy, the flow model comprising a signal flow model, an energy flow model and a control flow model; for each component in each hierarchy, determining a set of test signal parameters for the component in accordance with a flow model for the component; and based on the flow model and the test signal parameter set, performing fault location on the electromechanical hybrid system to be diagnosed by adopting an inference mode of an expert system.
In another aspect, the present application provides a fault diagnosis system for an electromechanical hybrid system, comprising: the hierarchy dividing module is used for dividing the electromechanical hybrid system to be diagnosed into a plurality of hierarchies according to the requirement analysis result of the electromechanical hybrid system to be diagnosed, and dividing the electromechanical hybrid system to be diagnosed into a plurality of components on each hierarchy; the model establishing module is used for establishing a flow model for each component in each hierarchy, and the flow model comprises a signal flow model, an energy flow model and a control flow model; a test signal parameter set determining module, configured to determine, for each component in each hierarchy, a test signal parameter set of the component according to a stream model of the component; and the fault positioning module is used for positioning the fault of the electromechanical hybrid system to be diagnosed by adopting an inference mode of an expert system based on the flow model and the test signal parameter set.
In another aspect, the present application provides a computer-readable storage medium storing a computer program that, when executed, implements the fault diagnosis method as described above.
According to the fault diagnosis method for the electromechanical hybrid system, the electromechanical hybrid system to be diagnosed is divided into a plurality of levels according to the requirement analysis result of the electromechanical hybrid system to be diagnosed, the components included in each level are determined, a flow model is established for each component in each level, the test signal parameter set of each component is determined, and fault location is performed on the electromechanical hybrid system to be diagnosed by adopting an expert system reasoning mode based on the flow model and the test signal parameter set. Therefore, for the electromechanical hybrid system to be diagnosed, the real-time performance and the effectiveness of fault diagnosis can be obviously improved by combining the flow model and the expert system.
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. Other advantages of the present application may be realized and attained by the instrumentalities and combinations particularly pointed out in the specification and the 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 flow chart of a fault diagnosis method for an electromechanical hybrid system provided by an embodiment of the present application;
FIG. 2 is an exemplary diagram of a hierarchy provided by an embodiment of the present application;
FIG. 3 is a schematic diagram of a flow model provided by an embodiment of the present application;
FIG. 4 is a diagram illustrating an example of a signal flow model for a subsystem provided by an embodiment of the present application;
FIG. 5 is an exemplary diagram of an energy flow model for a subsystem provided by an embodiment of the present application;
FIG. 6 is a diagram illustrating an application example of a fault diagnosis method according to an embodiment of the present application;
fig. 7 is a schematic diagram of a fault diagnosis system for an electromechanical hybrid system according to an 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 embodiments, 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.
The embodiment of the application provides a fault diagnosis method, a fault diagnosis system and a readable medium for an electromechanical hybrid system, and the fault diagnosis real-time performance and effectiveness of the electromechanical hybrid system can be effectively improved.
Fig. 1 is a flowchart of a fault diagnosis method for an electromechanical hybrid system according to an embodiment of the present application. As shown in fig. 1, the fault diagnosis method provided in this embodiment includes:
102, establishing a signal flow model for each component in each level, wherein the flow model comprises a signal flow model, an energy flow model and a control flow model;
and step 104, performing fault location on the electromechanical hybrid system to be diagnosed by adopting an inference mode of an expert system based on the flow model and the test signal parameter set.
The fault diagnosis method provided by the embodiment can be applied to different types of electromechanical hybrid systems. However, this is not limited in this application.
In an exemplary embodiment, step 101 may include: determining the number of levels required to be divided by the electromechanical hybrid system to be diagnosed according to the requirement analysis result of the electromechanical hybrid system to be diagnosed; and dividing the electromechanical hybrid system to be diagnosed into a plurality of levels according to the number of the levels to be divided and the composition structure and the function of the electromechanical hybrid system to be diagnosed, and dividing the electromechanical hybrid system to be diagnosed into a plurality of components on each level. According to the method and the device, the electromechanical hybrid system is subjected to hierarchical division on the basis of requirement analysis, so that an efficient search path can be provided for fault location, namely, hierarchical search is realized.
The requirement analysis result of the electromechanical hybrid system to be diagnosed can include one or more of the following information: the scale of the electromechanical hybrid system to be diagnosed (for example, the number of electronic components and the number of mechanical components included in the electromechanical hybrid system, etc.), the fault location range of the electromechanical hybrid system to be diagnosed (for example, a component or an assembly with a fault needs to be located), the real-time requirement for diagnosis (for example, the time requirement for obtaining a fault location result), and the fault phenomenon. However, this is not limited in this application. In practical application, a demand analysis result can be obtained through comprehensive analysis and balance according to various information of the electromechanical hybrid system to be diagnosed.
The number of the levels to be divided by the electromechanical hybrid system to be diagnosed is the diagnosis level depth of the electromechanical hybrid system to be diagnosed, for example, the electromechanical hybrid system to be diagnosed can be divided into three, four or more levels. Wherein the number of levels may be an integer greater than or equal to two. The numbering of the levels may increase sequentially in a top-down order or decrease sequentially in a top-down order. However, this is not limited in this application. In practical application, the number of the layers to be divided is determined according to the practical situation of the electromechanical hybrid system to be diagnosed.
In one example, an electromechanical hybrid system to be diagnosed may be divided into the following six levels in a top-down order: subsystems, sub-subsystems, field replaceable units, modules, components or elements, or may be divided into the following four levels: subsystem, sub-subsystem, field replaceable unit. However, this is not limited in this application.
In an example, the number of the levels to be divided by the electromechanical hybrid system to be diagnosed can be determined according to the fault location range of the electromechanical hybrid system to be diagnosed, in other words, the fault location range requires that the fault is located to which level, and the electromechanical hybrid system to be diagnosed is divided to which level; for example, if the fault location range requires locating a fault to a field replaceable unit level, it may be determined that the number of levels to be divided by the electromechanical hybrid system to be diagnosed is four, that is, the electromechanical hybrid system may be divided into the following four levels from top to bottom: subsystem, sub-subsystem, field replaceable unit. Or, determining the number of the levels to be divided of the electromechanical hybrid system to be diagnosed according to the scale and the fault location range of the electromechanical hybrid system to be diagnosed; for example, the fault locating range requires locating a fault to a field replaceable unit, and if the size of the electromechanical hybrid system to be diagnosed is small (that is, the number of electronic components included is small), it may be determined that the number of the layers of the electromechanical hybrid system to be diagnosed needs to be divided into three layers, that is, the number of the layers may be divided into the following three layers: subsystem, field replaceable unit. Or, determining the number of levels required to be divided by the electromechanical hybrid system to be diagnosed according to the fault location range and the diagnosis real-time requirement of the electromechanical hybrid system to be diagnosed; for example, if the fault location range requires locating a fault to the field replaceable unit, and the real-time performance of the diagnosis of the to-be-diagnosed electromechanical hybrid system is relatively high (i.e., a fault location is required to be located relatively quickly), it may be determined that the number of the levels required to be divided by the to-be-diagnosed electromechanical hybrid system is three, that is, the to-be-diagnosed electromechanical hybrid system may be divided into the following three levels: subsystem, field replaceable unit. However, this is not limited in this application.
In one example, a plurality of levels may be divided according to the number of levels to be divided by the electromechanical hybrid system to be diagnosed and the constituent structure and function of the electromechanical hybrid system to be diagnosed, and the division of the constituent parts may be performed in each level. For example, taking an electromechanical hybrid system to be diagnosed as an armored vehicle system as an example, the number of the layers required to be divided by the armored vehicle system is three (i.e. subsystem layer, subsystem layer and subsystem layer), the armored vehicle system may be firstly divided into the following subsystems according to the composition structure and function of the armored vehicle system: power divides system, firepower to strike branch system, protection branch system, communication control branch system, wherein, power divides the system to divide into following a plurality of subsystems again: the system comprises an engine subsystem, a gearbox subsystem and a vehicle chassis subsystem, and in addition, each part (namely each subsystem) in the subsystem level can be further divided into a plurality of subsystems according to needs.
Fig. 2 is an exemplary diagram of the hierarchical division provided in the embodiment of the present application. As shown in fig. 2, the electromechanical hybrid system to be diagnosed can be divided into the following two levels: a subsystem level and a subsystem level; the electromechanical hybrid system to be diagnosed comprises a subsystem 1 to a subsystem n on a subsystem level, wherein the subsystem 1 can be divided into a subsystem 1, a subsystem 2 and relevant parts in an integrated system part, the subsystem 2 can be divided into a subsystem 3, a subsystem 4 and relevant parts in the integrated system part, and the subsystem n can be divided into a subsystem n-1, a subsystem n and relevant parts in the integrated system part; wherein n is an integer greater than 1. In FIG. 2, TiRepresenting the testing of the diagnostic test signal parameters during the diagnostic process, the value of i is an integer greater than 0 and less than or equal to n.
In the embodiment, the electromechanical hybrid system to be diagnosed is hierarchically divided from top to bottom, that is, after the number of hierarchies is determined, the division of the components is performed step by step in the order from large to small in scope. In the present embodiment, the circuit scale, the number of components, and the like included in each level of the subsystem, and the like need to be determined according to the scale size and the composition structure of the electromechanical hybrid system to be diagnosed, and there is no uniform hard constraint.
In an exemplary embodiment, the signal flow model includes core representation elements for illustrating the transmission path (e.g., the propagation way through which the signal travels, e.g., amplification, filtering, etc.) and the sequential relationship (i.e., the precedence order of the propagation way of the signal) of the signal; the energy flow model comprises core representation elements for explaining the transmission path and the sequence relation of the non-electric energy; the control flow model comprises core representation elements for explaining the transmission path and the sequence relation of the control quantity of the non-electric system; wherein the core representation element comprises a key signal and a core parameter. Wherein, the core representation element is a carrier for expressing signal flow, energy flow and control flow. The present application is not limited to the type of core representation element. In practical applications, the core representation elements may be determined according to an actual electromechanical hybrid system.
The electromechanical hybrid system comprises an electronic information system and a non-electric system. The signal flow model, the energy flow model and the control flow model respectively describe the signal propagation of an electronic information system, the transmission of mechanical or hydraulic non-electric system energy and the transmission path and the sequential relation of control quantity of a control system. No matter how complex the composition structure and the function of the electromechanical hybrid system are, the electromechanical hybrid system can be abstracted into a whole with mutually independent or cross-coupled signal flow, energy flow and control flow. By establishing the signal flow model, the energy flow model and the control flow model, parameter indexes of the structure, the function, the performance and the like of any complex electromechanical hybrid system and logic relations among the parameter indexes can be fully extracted and expressed, and then the three models are only required to be developed in the fault diagnosis process.
The method comprises the steps of establishing a flow model of each component in each hierarchy, and establishing a logical relation basis among signal, energy and control quantity parameters for reasoning and diagnosing faults. The basis for establishing the flow model is as follows: the structure, function, working principle and signal propagation sequence of the electromechanical hybrid system to be diagnosed. In one example, the electromechanical hybrid system to be diagnosed is divided into the following three levels: the subsystem level, the subsystem level and the subsystem level can respectively establish a flow model (including a signal flow model, an energy flow model and a control flow model) of each subsystem, a flow model of each subsystem and a flow model of each subsystem.
Fig. 3 is a schematic diagram of a flow model provided in an embodiment of the present application. Fig. 3(a) is a schematic diagram of a signal flow model, which describes the precedence relationship of signal flows from generation to conversion (processing) to output; FIG. 3(b) is a schematic diagram of an energy flow model, depicting the precedence relationship of energy flow from production to transformation (processing) to output; FIG. 3(c) is a schematic diagram of a control flow model, depicting the precedence relationship of the control flow from production to transformation (processing) to output.
Fig. 4 is an exemplary diagram of a signal flow model of a subsystem according to an embodiment of the present application. The solid arrows in fig. 4 express the flow direction of each key function signal in the electronic information system. The amplified high-frequency signal is sent to a mixer, the intermediate-frequency signal obtained after mixing is sent to an intermediate-frequency amplifier, the signal amplified by the intermediate-frequency amplifier is sent to a signal detection circuit for detection processing, the low-frequency signal after detection processing is sent to a low-frequency amplification circuit for voltage amplification, the low-frequency signal after voltage amplification is sent to a power amplification circuit for power amplification, and finally the power capable of driving a load is achieved. All the signal flow directions of different forms (different sizes) are definite and have a sequential logic order, so that fig. 4 expresses both the signal flow propagation logic and the signal data chain for fault diagnosis reasoning. T indicated by a dotted arrow in FIG. 41To T5Is the test performed during the fault diagnosis. As can be seen from fig. 4, according to the signal flow model, the relationship between the parameters of the test signals for diagnosis can be traced back, and the propagation condition of the fault can be determined, so as to determine the fault location.
For mechanical, hydraulic, etc. energy transmission systems or control systems (refer to fig. 3(b) and 3(c)) using energy (or force) as a control quantity, key signals, core parameters, etc. in an energy flow model or a control flow model may be different parameters such as force, power, energy, etc., or may be converted parameters thereof, and are selected according to specific working principle conditions.
Fig. 5 is an exemplary diagram of an energy flow model of a subsystem according to an embodiment of the present application. The solid arrows in fig. 5 express the flow direction of each key signal in the electromechanical hybrid system. The energy provided by the electric control signal can be sequentially transmitted to the transmitter and the gearbox, and is directly provided to the gearbox and finally used for driving the load. T indicated by a dotted arrow in FIG. 51To T4Is the test performed during the fault diagnosis.
In an exemplary embodiment, step 103 may include: for each component of each hierarchy, a set of key signal and core parameters for the component is determined from a flow model for the component, forming a set of test signal parameters for the component. The test signal parameter set is a summary of necessary and sufficient test signals and parameters in the process of realizing fault diagnosis of the electromechanical hybrid system. Based on the system level division and the flow model establishment, a set of key signals and core parameters of the components of each level is determined, namely a set of test signal parameters of the corresponding components.
Taking the signal flow model shown in FIG. 4 as an example, the test item T is indicated by a dashed arrow1、T2、T3、T4、T5The high-frequency signal, the intermediate-frequency signal, the low-frequency small signal, the low-frequency large signal and the low-frequency power signal which respectively correspond to the high-frequency signal, the intermediate-frequency signal, the low-frequency small signal, the low-frequency large signal and the low-frequency power signal are the test signal parameter set of the subsystem, and when fault diagnosis is carried out, a fault can be located in the corresponding functional circuit block by carrying out specific combination test on the signals. Similarly, the next level of the test signal parameter set can be obtained according to all the critical function signals in the next level of the signal flow model.
For mechanical, hydraulic and other energy transmission systems or control systems using energy as control quantity, the determination of the test signal parameter set can be realized by directly selecting corresponding partsIs tested for such parameters as force, power, energy, etc., as shown by T in FIG. 52，T3(ii) a Corresponding coupling quantity or conversion quantity which can truly reflect different parameters of force, power, energy and the like can be indirectly selected as a test signal parameter set, and the corresponding coupling quantity or the conversion quantity is comprehensively determined according to the specific working principle condition and the complexity of realizing the test. For example, if the power or energy is difficult to directly test, the measurement may be converted into a measurement by testing the magnitude of the corresponding force (thrust, tension, pressure, etc.), the magnitude of the heat generation, or even the magnitude of the corresponding vibration strength, which is also a feasible indirect measurement method.
In an exemplary embodiment, after step 103, the fault diagnosis method of the present embodiment may further include: and carrying out fault location on the electromechanical hybrid system to be diagnosed based on the flow model and the test signal parameter set according to a set diagnosis strategy.
In the present exemplary embodiment, the diagnostic strategy may include: and performing fault diagnosis according to the sequence of the top-down levels, wherein the numbers of the levels are sequentially increased according to the sequence of the top-down levels, the level with the number smaller than the first threshold value performs fault diagnosis in a first diagnosis mode, and the level with the number larger than or equal to the first threshold value performs fault diagnosis in a second diagnosis mode. The first threshold is a preset value, or a default value, or a value adaptively adjusted by a user. However, this is not limited in this application.
The exemplary embodiment can meet the diagnosis requirements of different levels and different positioning range requirements by adopting a proper diagnosis strategy to realize fault positioning. It should be noted that the diagnosis policy provided by the present embodiment may be preset by the user, or may be adjusted according to the user's requirement. However, this is not limited in this application.
In an exemplary embodiment, the first diagnostic mode may include: the second diagnostic modality may include a model diagnostic modality based on an inferential diagnostic modality of the expert system. The inference diagnosis method based on the expert system is to process the fault diagnosis problem by using a program system with a great deal of special knowledge and experience, and the expert system generally comprises an expert database and an inference engine. The model diagnosis mode can comprise a fault dictionary, a network tearing method and the like. The specific implementation process of the inference diagnosis mode and the model diagnosis mode based on the expert system may refer to the related art, and therefore, details are not described herein.
In this embodiment, the diagnosis strategy refers to the adopted diagnosis method and the diagnosis sequence, and the diagnosis strategy is a key ring for performing fault diagnosis. In an example, the process of fault location is a process of gradually compressing from large to small, taking five levels of top-down division of the electromechanical hybrid system to be diagnosed into subsystems, sub-subsystems, field replaceable units and modules as an example, the diagnosis strategy may be set as: combining signal flow models of all levels (namely signal flow models of all subsystems, signal flow models of all sub-subsystems, signal flow models of all field replaceable units and signal flow models of all modules), firstly determining the subsystem where the fault is located by adopting an expert system-based reasoning diagnosis method, then determining the subsystem where the fault is located, and further determining the sub-subsystem where the fault is located and the field replaceable unit; next, a model diagnostic is used to determine the module in which the fault is located. The diagnosis on the levels (determined according to specific conditions) of the subsystems, the subsystems and the field replaceable units is carried out, and the positioning precision requirement on a fault area is not high, so that only the range of the level where the fault is located needs to be determined, and an expert system reasoning diagnosis method can be adopted; in the field replaceable unit and the following level of diagnosis, if the requirement on the positioning accuracy of the fault area is high, a model diagnosis method (for example, a fault dictionary method, a network tearing method and the like) can be adopted for diagnosis according to specific conditions, namely, a model diagnosis method and other methods can be adopted for positioning faults in a small range of the bottom layer. In the embodiment, the diagnosis is performed level by level according to the top-down levels, and different diagnosis methods (for example, a reasoning diagnosis method and a model diagnosis method combined with an expert system) can be adopted for different levels, so that the diagnosis requirements of different levels and different positioning range requirements are met, and the diagnosis real-time performance and the fault isolation rate are effectively improved.
In the expert system reasoning diagnosis method, the main points of adopting the expert system to carry out fault diagnosis are as follows: the fault phenomenon is a source, a signal flow model and expert experience of each level of the electromechanical hybrid system to be diagnosed are reasoning bases, and fault conclusions of the subsystems, the subsystems and the sub-subsystems are gradually obtained through necessary testing and logical reasoning. In one example, based on the levels adopting the expert system reasoning diagnosis method, a diagnosis reasoning logic relation graph of signals of each level can be established, and a reasoning route and a reasoning machine of the expert system are constructed by the diagnosis reasoning logic relation graph of the signals; carrying out statistical analysis on historical fault data, and preliminarily establishing a fault database corresponding to fault phenomena and fault reasons by combining expert experience and the diagnosis inference logic relation graph; establishing a typical fault database by adopting an analog simulation method (realized by simulation software), and adding data in the typical fault database into the fault database to form a relatively complete fault diagnosis database; based on the demand analysis, reasoning and judging step by step according to the hierarchy sequence from top to bottom aiming at the actual fault phenomenon by taking the system hierarchy division and the signal flow model of each hierarchy as guidance; and according to the prompt of an expert system, when the targeted test is required, the test result is imported into an expert system database, and a reasoning machine deduces the test to be carried out next step or gives a diagnosis conclusion according to the test result.
Fig. 6 is a diagram illustrating an application example of the fault diagnosis method according to the embodiment of the present application. The following describes the fault diagnosis process of the present embodiment by taking the module-level fault diagnosis of the fighter plane system as an example with reference to fig. 6.
In this example, the electromechanical hybrid system to be diagnosed is a warplane system. Firstly, according to the analysis result of the requirement, the warplane system is divided into the following five levels according to the sequence from top to bottom: system level, subsystem level, sub-subsystem level, module level. As shown in fig. 6, the fighter system can be broadly divided into a power system, a combat system, an avionics system and a maneuvering system, each of which can be further divided into the following four levels: subsystem hierarchy, sub-subsystem hierarchy, and module hierarchy.
In this example, after determining the hierarchical division, a flow model may be built for each hierarchy and a corresponding set of test signal parameters determined. The method comprises the steps of establishing a signal flow model, an energy flow model and a control flow model for each component in each level, determining a corresponding test signal parameter set on the basis of the three models, establishing a diagnosis and inference logic relation diagram, and establishing an inference route diagram and an inference engine of an expert system according to the diagnosis and inference logic relation diagram. A diagnostic expert database may then be built. The historical fault data of the warplane of the model is subjected to statistical analysis and arrangement, and a fault database corresponding to the fault phenomenon and the fault reason can be preliminarily established by combining expert experience and the diagnosis inference logic relation graph. Meanwhile, a typical fault database is established by adopting an analog simulation method, and the analog data is added into the fault database to form a relatively complete fault database.
In this example, the following fault phenomena are diagnosed for a particular warplane: after the fighter is lifted off, all the instruments are normal, the fighter operates normally, but the specified target in the detection distance cannot be found.
And (4) aiming at the actual fault phenomenon, diagnosing, reasoning and judging step by step according to a top-down hierarchical sequence. The range of apparent failure occurrence was preliminarily determined as: a radar subsystem in a fire control subsystem of a combat system. According to fig. 6, the radar subsystem is further divided into: a transmitter sub-system, a receiver sub-system, an antenna feeder sub-system, a signal processing sub-system, etc. According to the prompt of the diagnosis system: firstly, whether power supply (key test signals) of each subsystem of the radar is normal or not is monitored, and the fact that power supply data of the power supply are normal is found through tests. The system then prompts for sequential monitoring of the transmitter sub-system, the receiver sub-system, etc. The transmitter subsystem is found to work normally through monitoring and diagnosis. And further monitoring a radar receiver subsystem, finding that the output signal of the receiver becomes small, respectively monitoring key test signals of each module according to system division of the receiver subsystem, finding that the intermediate frequency amplification module has a fault, and finally confirming that the intermediate frequency amplification circuit is damaged, wherein the amplification factor is reduced by one order of magnitude. At this point, the diagnosis is finished.
In the area range below the module level, if a specific faulty component needs to be determined, further fault diagnosis and location can be performed by combining a model diagnosis method. The fault diagnosis process of the model diagnosis method can refer to the related art, and therefore, the details thereof are not described herein.
The fault diagnosis method provided in the embodiment of the application sufficiently combines macroscopic information (for example, information such as a total architecture of the electromechanical hybrid system to be diagnosed, system components, and logical relationships among the components) and mesoscopic information (for example, information such as a connection relationship, a circuit schematic diagram, and a structural schematic diagram among components of a next hierarchy of the system components of the electromechanical hybrid system to be diagnosed) of the electromechanical hybrid system to be diagnosed, and microscopic information (for example, information such as a mechanical structure, a circuit component, and the like of the electromechanical hybrid system to be diagnosed), performs hierarchical division from top to bottom and division of components for each hierarchy by the electromechanical hybrid system to be diagnosed, establishes a flow model of each component in each hierarchy, obtains a test signal parameter set based on the flow model, and then, based on an inference diagnosis mode of an expert system, and carrying out layered step-by-step fault diagnosis on the electromechanical hybrid system. According to the embodiment of the application, the complicated electromechanical hybrid system is described by adopting the flow model, so that the high-efficiency reasoning of the inference engine of the expert system can be effectively supported, various typical faults can be efficiently simulated according to the flow model, and a fault database with enough number of fault cases can be quickly established. By combining the flow model and the expert system, fault diagnosis can be performed in a layered and step-by-step manner, so that the diagnosis requirements of different levels are met, and the diagnosis real-time performance and the fault isolation rate of the electromechanical hybrid system are effectively improved.
Fig. 7 is a schematic diagram of a fault diagnosis system for an electromechanical hybrid system according to an embodiment of the present application. As shown in fig. 7, the fault diagnosis system provided in the embodiment of the present application includes: the hierarchical division module 201 is configured to divide the electromechanical hybrid system to be diagnosed into multiple hierarchies according to a requirement analysis result of the electromechanical hybrid system to be diagnosed, and divide the electromechanical hybrid system to be diagnosed into multiple components on each hierarchy; a model building module 202 for building a flow model for each component in each hierarchy, the flow model including a signal flow model, an energy flow model, and a control flow model; a test signal parameter set determining module 203, configured to determine, for each component in each hierarchy, a test signal parameter set of the component according to a stream model of the component; and the fault positioning module 204 is configured to perform fault positioning on the electromechanical hybrid system to be diagnosed by using an inference mode of an expert system based on the flow model and the test signal parameter set.
In an exemplary embodiment, the signal flow model includes core representation elements for illustrating the transmission paths and the sequential relationships of the signals; the energy flow model comprises core representation elements for explaining the transmission path and the sequence relation of the non-electric energy; the control flow model comprises core representation elements for explaining the transmission path and the sequence relation of the control quantity of the non-electric system; wherein the core representation element comprises a key signal and a core parameter.
In an exemplary embodiment, the fault location module 204 is further configured to locate a fault of the electromechanical hybrid system to be diagnosed according to a set diagnosis strategy based on the flow model and the set of test signal parameters.
For the related description of the fault diagnosis system provided in the embodiment of the present application, reference may be made to the above description of the embodiment of the fault diagnosis method, and therefore, details are not described herein again.
Furthermore, an embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and the computer program, when executed by a processor, implements the fault diagnosis method as described above.
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.
The foregoing shows and describes the general principles and features of the present application, together with the advantages thereof. The present application is not limited to the above-described embodiments, which are described in the specification and drawings only to illustrate the principles of the application, but also to provide various changes and modifications within the spirit and scope of the application, which are within the scope of the claimed application.
Claims (10)
1. A fault diagnosis method for an electromechanical hybrid system, comprising:
dividing the electromechanical hybrid system to be diagnosed into a plurality of levels according to the requirement analysis result of the electromechanical hybrid system to be diagnosed, and dividing the electromechanical hybrid system to be diagnosed into a plurality of components on each level;
establishing a flow model for each component in each hierarchy, the flow model comprising a signal flow model, an energy flow model and a control flow model;
for each component in each hierarchy, determining a set of test signal parameters for the component in accordance with a flow model for the component;
and based on the flow model and the test signal parameter set, performing fault location on the electromechanical hybrid system to be diagnosed by adopting an inference mode of an expert system.
2. The fault diagnosis method according to claim 1, characterized in that the signal flow model comprises core representation elements for illustrating transmission routes and sequence relations of signals; the energy flow model comprises core representation elements for explaining the transmission path and the sequence relation of the non-electric energy; the control flow model comprises core representation elements for explaining transmission paths and sequence relations of control quantities of the non-electric system; wherein the core representation element comprises a key signal and a core parameter.
3. The method of claim 2, wherein determining, for each component in each hierarchy, a set of test signal parameters for the component from a flow model of the component comprises:
for each component in each hierarchy, determining a set of key signal and core parameters for the component from a flow model of the component, forming a set of test signal parameters for the component.
4. The fault diagnosis method according to claim 1, characterized in that the fault diagnosis method further comprises: and according to a set diagnosis strategy, based on the flow model and the test signal parameter set, carrying out fault location on the electromechanical hybrid system to be diagnosed.
5. The fault diagnosis method according to claim 4, characterized in that the diagnosis strategy comprises: and performing fault diagnosis according to the sequence of the top-down levels, wherein the numbers of the levels are sequentially increased according to the sequence of the top-down levels, the level with the number smaller than the first threshold value performs fault diagnosis in a first diagnosis mode, and the level with the number larger than or equal to the first threshold value performs fault diagnosis in a second diagnosis mode.
6. The fault diagnosis method according to claim 5, wherein the first diagnosis means includes: the second diagnosis mode comprises the following steps of: and (4) model diagnosis mode.
7. A fault diagnosis system for an electromechanical hybrid system, comprising:
the hierarchy dividing module is used for dividing the electromechanical hybrid system to be diagnosed into a plurality of hierarchies according to the requirement analysis result of the electromechanical hybrid system to be diagnosed, and dividing the electromechanical hybrid system to be diagnosed into a plurality of components on each hierarchy;
the model establishing module is used for establishing a flow model for each component in each hierarchy, and the flow model comprises a signal flow model, an energy flow model and a control flow model;
a test signal parameter set determining module, configured to determine, for each component in each hierarchy, a test signal parameter set of the component according to a stream model of the component;
and the fault positioning module is used for positioning the fault of the electromechanical hybrid system to be diagnosed by adopting an inference mode of an expert system based on the flow model and the test signal parameter set.
8. The fault diagnosis system according to claim 7, characterized in that the signal flow model comprises core representation elements for illustrating transmission routes and order relations of signals; the energy flow model comprises core representation elements for explaining the transmission path and the sequence relation of the non-electric energy; the control flow model comprises core representation elements for explaining transmission paths and sequence relations of control quantities of the non-electric system; wherein the core representation element comprises a key signal and a core parameter.
9. The fault diagnosis system of claim 7, wherein the fault location module is further configured to locate a fault of the electromechanical hybrid system to be diagnosed based on the flow model and the set of test signal parameters according to a set diagnosis strategy.
10. A computer-readable storage medium, characterized in that a computer program is stored which, when executed, implements the fault diagnosis method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911378054.0A CN111061253A (en) | 2019-12-27 | 2019-12-27 | Fault diagnosis method, system and readable medium for electromechanical hybrid system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911378054.0A CN111061253A (en) | 2019-12-27 | 2019-12-27 | Fault diagnosis method, system and readable medium for electromechanical hybrid system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111061253A true CN111061253A (en) | 2020-04-24 |
Family
ID=70304083
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911378054.0A Pending CN111061253A (en) | 2019-12-27 | 2019-12-27 | Fault diagnosis method, system and readable medium for electromechanical hybrid system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111061253A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN113820153A (en) * | 2021-08-25 | 2021-12-21 | 北京旋极信息技术股份有限公司 | Built-in test method and system of electromechanical hybrid system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101980225A (en) * | 2010-11-16 | 2011-02-23 | 中国人民解放军63908部队 | Method for implementing testability analysis and diagnosis decision system for electronic products |
| WO2012162360A2 (en) * | 2011-05-23 | 2012-11-29 | Siemens Corporation | Simulation based fault diagnosis using extended heat flow models |
| CN103487749A (en) * | 2013-09-18 | 2014-01-01 | 国家电网公司 | On-line monitoring and diagnosing system and method for mechanical state of high-voltage circuit breaker |
| 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 |
| CN104238545A (en) * | 2014-07-10 | 2014-12-24 | 中国石油大学(北京) | Fault diagnosis and pre-warning system in oil refining production process and establishment method thereof |
| CN104392752A (en) * | 2014-10-13 | 2015-03-04 | 中国科学院合肥物质科学研究院 | Real-time on-line nuclear reactor fault diagnosis and monitoring system |
| CN104504248A (en) * | 2014-12-05 | 2015-04-08 | 中国航空工业集团公司第六三一研究所 | Failure diagnosis modeling method based on designing data analysis |
| CN104597892A (en) * | 2014-12-16 | 2015-05-06 | 北京航天测控技术有限公司 | Hierarchical fault diagnosis method for electronic information equipment |
-
2019
- 2019-12-27 CN CN201911378054.0A patent/CN111061253A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101980225A (en) * | 2010-11-16 | 2011-02-23 | 中国人民解放军63908部队 | Method for implementing testability analysis and diagnosis decision system for electronic products |
| WO2012162360A2 (en) * | 2011-05-23 | 2012-11-29 | Siemens Corporation | Simulation based fault diagnosis using extended heat flow models |
| CN103487749A (en) * | 2013-09-18 | 2014-01-01 | 国家电网公司 | On-line monitoring and diagnosing system and method for mechanical state of high-voltage circuit breaker |
| 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 |
| CN104238545A (en) * | 2014-07-10 | 2014-12-24 | 中国石油大学(北京) | Fault diagnosis and pre-warning system in oil refining production process and establishment method thereof |
| CN104392752A (en) * | 2014-10-13 | 2015-03-04 | 中国科学院合肥物质科学研究院 | Real-time on-line nuclear reactor fault diagnosis and monitoring system |
| CN104504248A (en) * | 2014-12-05 | 2015-04-08 | 中国航空工业集团公司第六三一研究所 | Failure diagnosis modeling method based on designing data analysis |
| CN104597892A (en) * | 2014-12-16 | 2015-05-06 | 北京航天测控技术有限公司 | Hierarchical fault diagnosis method for electronic information equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN113820153A (en) * | 2021-08-25 | 2021-12-21 | 北京旋极信息技术股份有限公司 | Built-in test method and system of electromechanical hybrid system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104597892A (en) | Hierarchical fault diagnosis method for electronic information equipment | |
| JP2008537262A (en) | Decision support method and system | |
| US11776330B2 (en) | Closed-loop diagnostic model maturation for complex systems | |
| JPH03119434A (en) | Method and apparatus for generating multi- branch diagnostic tree | |
| CN109581190B (en) | Optimal diagnosis tree generation method for circuit fault diagnosis | |
| US20210171221A1 (en) | Onboard diagnosis and correlation of failure data to maintenance actions | |
| CN102363969A (en) | Excavator and method and system for determining equipment fault | |
| CN111061293B (en) | Multi-parameter coupled aircraft fault positioning method, aircraft and storage medium | |
| CN111061253A (en) | Fault diagnosis method, system and readable medium for electromechanical hybrid system | |
| CN104238546B (en) | Based on the direct current master-failure diagnostic method for mixing neutral net | |
| CN105825045B (en) | Phased mission systems can repair spare parts demand Forecasting Methodology | |
| KR20230158787A (en) | Prognostic and health management apparatus based on digital twin | |
| GB2590671A (en) | Control system | |
| CN115564210A (en) | Network entity task completion capability evaluation method and evaluation system | |
| CN111176877A (en) | Fault diagnosis method, system and readable medium for electronic information system | |
| Zhang et al. | Hierarchical hybrid testability modeling and evaluation method based on information fusion | |
| Ruan et al. | On a multimode test sequencing problem | |
| CN109828857B (en) | Vehicle fault cause positioning method, device, equipment and storage medium | |
| CN113310171A (en) | Central air-conditioning system fault detection and diagnosis method based on Bayesian network unit | |
| Azam et al. | Optimal sensor allocation for fault detection and isolation | |
| Rodrigues et al. | Learning and diagnosis in manufacturing processes through an executable Bayesian network | |
| US7739213B1 (en) | Method for developing complex probabilistic models | |
| Hallaji et al. | A digital twin framework for enhancing predictive maintenance of pumps in wastewater treatment plants | |
| CN112084909B (en) | Fault diagnosis method, system and computer readable storage medium | |
| US20240338270A1 (en) | Method and apparatus for reliability evaluation based on multiple performance degradation, and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200424 |
|
| RJ01 | Rejection of invention patent application after publication |