CN115827353A - Fault diagnosis method and device - Google Patents
Fault diagnosis method and device Download PDFInfo
- Publication number
- CN115827353A CN115827353A CN202211638071.5A CN202211638071A CN115827353A CN 115827353 A CN115827353 A CN 115827353A CN 202211638071 A CN202211638071 A CN 202211638071A CN 115827353 A CN115827353 A CN 115827353A
- Authority
- CN
- China
- Prior art keywords
- fault
- model
- target object
- hierarchical
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Test And Diagnosis Of Digital Computers (AREA)
Abstract
The embodiment of the invention relates to a fault diagnosis method and a device, wherein the method comprises the following steps: establishing a hierarchical fault model according to the data characteristics of a target object, wherein the hierarchical fault model is a hierarchical data structure associated with the target object; establishing a hierarchical fault category of the target object according to the hierarchical fault model; after test data corresponding to the hierarchical fault category are collected, carrying out simulation processing on the test data to construct a simulation model of the target object; and performing fault diagnosis processing on the target object based on the simulation model to obtain a fault diagnosis result. Thus, the technical effect of improving the efficiency and the capability of diagnosing the failure of the target object can be achieved.
Description
Technical Field
The embodiment of the invention relates to the technical field of function testing, in particular to a fault diagnosis method and device.
Background
With the continuous development of science and technology and the continuous application of new technology, electronic systems are also continuously developed towards the direction of high integration and automation, and an equipment system with the advantages of large system, dense technology, increased scale and complex management is gradually formed. In the process that equipment is continuously developed to be complicated, automatic and large-scale, high attention is gradually paid to the safe and reliable operation of the whole electronic system, namely reliability, guarantee and maintainability, and test diagnosis is an important technical guarantee for the safe and reliable operation of the electronic system. Nowadays, more and more attention is paid to the test and diagnosis problems of electronic systems or equipment, and by establishing a fault diagnosis knowledge model and using a simulation mode to replace a complex manual means to realize automatic fault positioning, the method has important application value in improving fault diagnosis efficiency and making maintenance and repair decisions.
The complex electronic system is often composed of a plurality of subsystems or sub-modules, and the subsystems or sub-modules contain various functional circuits or control units, and the failure causes are generally caused by mutual influence of a plurality of different complex factors. Meanwhile, due to the characteristics of modularization and standardization of the complex electronic system, the complex electronic system has the characteristics of layering and relevance when a fault occurs. A high-level fault is usually caused by a low-level fault, and after a component or a functional circuit in a system fails, the component or the functional circuit often affects circuit units related to the same level, and at the same time, a high-level module also fails.
Disclosure of Invention
In view of this, in order to solve the above technical problems of low test diagnosis efficiency and poor diagnosis capability for a target object, embodiments of the present invention provide a fault diagnosis method and apparatus.
In a first aspect, an embodiment of the present invention provides a fault diagnosis method, including:
establishing a hierarchical fault model according to the data characteristics of a target object, wherein the hierarchical fault model is a hierarchical data structure associated with the target object;
establishing a hierarchical fault category of the target object according to the hierarchical fault model;
after test data corresponding to the hierarchical fault category are collected, carrying out simulation processing on the test data to construct a simulation model of the target object;
and executing fault diagnosis processing on the target object based on the simulation model to obtain a fault diagnosis result.
In one possible embodiment, the creating a hierarchical fault model according to the data characteristics of the target object includes:
generating a topological relation data module according to the data characteristics of the target object, wherein the topological relation data module is used for describing the hierarchical incidence relation among the target object data;
determining diagnostic reference information of the target object according to the data characteristics of the target object, wherein the diagnostic reference information is used for describing the fault type and the fault influence relation of the target object;
and compiling the topological relation data model and the diagnosis reference information to generate a hierarchical fault model of the target object.
In one possible embodiment, the creating a hierarchical fault category of the target object according to the hierarchical fault model includes:
analyzing the hierarchical fault model to generate a fault category two-dimensional table;
and creating a hierarchical fault category based on the fault category two-dimensional table.
In a possible embodiment, the analyzing the hierarchical fault model to generate a fault category two-dimensional table includes:
analyzing the model file corresponding to the hierarchical fault model to obtain analysis information in the model file, wherein the analysis information carries BIT information, fault types, sampling nodes and fault influence information;
establishing a fault category library of the target object based on the analysis information, wherein the fault category library is used for establishing a mapping relation between the analysis information and multi-level fault categories;
establishing a fault category library model based on the data mapping relation between the fault category libraries;
and loading sampling node information to be diagnosed in the fault category library model, and generating the fault category two-dimensional table, wherein the fault category two-dimensional table carries all reference data corresponding to each fault category.
In one possible embodiment, the collecting test data matching with the hierarchical fault category correspondence includes:
creating an actual measurement model according to the hierarchical fault category;
carrying out fault injection processing by using the actual measurement model to obtain actual measurement data corresponding to the actual measurement model;
and carrying out integrity processing on the measured data to obtain the test data.
In a possible embodiment, the performing simulation processing on the test data to construct a simulation model of the target object includes:
carrying out data preprocessing on the test data, and carrying out feature extraction on the preprocessed data to obtain feature data of the test data;
performing a plurality of fault diagnosis processes based on the characteristic data to obtain a plurality of diagnosis results of the target object;
and constructing a simulation model of the target object by fusing a plurality of diagnosis results, wherein the simulation model carries fault detection data of the target object.
In one possible embodiment, the performing a fault diagnosis process on the target object based on the simulation model includes:
obtaining a model name of the simulation model;
and inputting the fault detection data corresponding to the model name into the simulation model, and performing fault diagnosis processing to obtain a fault diagnosis result.
In one possible embodiment, after performing the fault diagnosis process on the target object, the method further includes:
determining the fault diagnosis rate corresponding to the model name according to the fault diagnosis result obtained by the fault diagnosis;
judging whether the simulation model meets a fault diagnosis condition or not according to the relation between the fault diagnosis rate and a diagnosis threshold value;
and when the fault diagnosis rate is greater than or equal to the diagnosis threshold value, determining that the simulation model meets the fault diagnosis condition of the target object.
In a second aspect, an embodiment of the present invention provides a fault diagnosis apparatus, including:
the system comprises a creating module, a fault analysis module and a fault analysis module, wherein the creating module is used for creating a hierarchical fault model according to the data characteristics of a target object, and the hierarchical fault model is a hierarchical data structure associated with the target object;
the creating module is further used for creating the hierarchical fault category of the target object according to the hierarchical fault model;
the simulation module is used for carrying out simulation processing on the test data after the test data corresponding to the hierarchical fault category is acquired, and constructing a simulation model of the target object;
and the diagnosis module is used for executing fault diagnosis processing on the target object based on the simulation model to obtain a fault diagnosis result.
According to the fault diagnosis scheme provided by the embodiment of the invention, a hierarchical fault model is established according to the data characteristics of a target object, and the hierarchical fault model is a hierarchical data structure associated with the target object; establishing a hierarchical fault category of the target object according to the hierarchical fault model; after test data corresponding to the hierarchical fault category are collected, carrying out simulation processing on the test data to construct a simulation model of the target object; and executing fault diagnosis processing on the target object based on the simulation model to obtain a fault diagnosis result. Establishing a hierarchical fault diagnosis model on the basis of a data structure of a reference target object, obtaining a hierarchical fault category through analysis processing, wherein the hierarchical fault category comprises theoretical fault reference data, acquiring actual measurement data of the target object as test data through hardware equipment, and inputting the test data into the hierarchical fault category to obtain data to be detected by faults; carrying out simulation processing on data to be subjected to fault detection to obtain a fault detection simulation model corresponding to a target object, carrying out fault diagnosis on the target object by using the simulation model to obtain fault diagnosis results under all fault categories contained in the target object, and referring to the fault diagnosis results to further position faults of the target object; by the scheme, the technical effect of improving the fault diagnosis efficiency and the fault diagnosis capability of the target object can be achieved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
Fig. 1 is a schematic flowchart of a fault diagnosis method according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of another fault diagnosis method provided in an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a hierarchical fault model according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a fault diagnosis device according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "comprising" and "having" in the embodiments of the present invention are used to mean open-ended inclusion, and mean that there may be additional elements/components/etc. in addition to the listed elements/components/etc.; the terms "first" and "second", etc. are used merely as labels, and are not limiting on the number of their objects. Further, the different elements and regions in the drawings are only schematically shown, and thus the present invention is not limited to the dimensions or distances shown in the drawings.
For the convenience of understanding the embodiments of the present invention, the following detailed description will be given with reference to the accompanying drawings, which are not intended to limit the embodiments of the present invention.
The fault diagnosis refers to that the process of finding whether a system and equipment have faults or not by utilizing various checking and testing methods is fault detection; and the process of further determining the approximate location of the fault is fault localization. Fault detection and fault location belong to the same network survivability category. The process of requiring the fault to be located at a product level (replaceable unit) that is replaceable when repairs are performed is called fault isolation. Fault diagnosis refers to the process of fault detection and fault isolation.
Fig. 1 is a schematic flow chart of a fault diagnosis method according to an embodiment of the present invention. The main execution body of the present embodiment is a failure diagnosis system. According to the diagram provided in fig. 1, the fault diagnosis method specifically includes:
s101, a hierarchical fault model is created according to the data characteristics of the target object, and the hierarchical fault model is a hierarchical data structure associated with the target object.
The execution subject of the embodiment of the invention is a fault diagnosis system. The process of fault diagnosis is also the process of fault detection. Establishing a hierarchical fault model for a detection object aiming at a plurality of fault types, fault influence factors and incidence relations between faults by establishing a fault diagnosis system framework, collecting all data characteristics contained in the detection object and the hierarchical relations among the data characteristics based on the hierarchical fault model, sorting according to the given fault type to obtain a clear fault type corresponding to each detection object, obtaining a two-dimensional table containing theoretical detection data, and acquiring real data and inputting the real data into the two-dimensional table for comparison to obtain to-be-tested data; the method comprises the steps of obtaining a plurality of simulation models by utilizing a plurality of simulation processing methods for data to be tested, carrying out fusion processing on the plurality of simulation models by utilizing fusion processing in order to improve the fault diagnosis rate to obtain a final simulation model, and carrying out fault diagnosis on a detection object to obtain a fault diagnosis result with high accuracy.
The target object referred to herein may be understood as an object to be detected. The data feature referred to herein can be understood as feature data of the object to be detected at the sampling node. The hierarchy here can be understood as the hierarchical relationship between the upper and lower layers or the flat layers between the function modules, the units or the basic control devices in the system where the object to be detected is located.
Further, when the fault diagnosis system starts diagnosis of the target object, firstly, feature data at all sampling nodes of the target object are obtained, sorting is carried out based on all the collected feature data, association relations among the levels are obtained by hierarchical division, a hierarchical fault model is created after the obtained management relations are sorted into a hierarchical data structure, and preparation is made for next step of data analysis.
And S102, establishing a hierarchical fault type of the target object according to the hierarchical fault model.
The hierarchical failure categories referred to herein may be understood as hierarchical failure modes. The method is used for loading and analyzing the hierarchical fault model, and lays a foundation for the training of the diagnosis model and the diagnosis and treatment of the fault.
And further, the obtained hierarchical fault model is used for loading and analyzing to obtain hierarchical fault categories related among the hierarchies, and preparation is made for collecting fault diagnosis data in the next step.
S103, after the test data corresponding to the hierarchical fault category are collected, simulation processing is carried out on the test data, and a simulation model of the target object is constructed.
The test data described here can be understood as actual tested data corresponding to data included in the hierarchical fault category. The simulation process described herein may be understood as performing simulation analysis calculation on test data at all sampling nodes of the target object.
Further, real data matched with each other at all the sampling points in the hierarchical fault category of the target object are collected to obtain test data, the test data are stored in the hierarchical fault category to carry out analog simulation operation, a simulation model of the target object for the test data is constructed, and preparation is made for next fault diagnosis.
And S104, performing fault diagnosis processing on the target object based on the simulation model to obtain a fault diagnosis result.
The failure diagnosis process described herein may be understood as a process of analyzing data using a selected diagnosis process manner. The fault diagnosis result can be understood as a fault analysis result for the target object, and represents information such as fault category, fault location or fault influence factor of the target object in the current state.
Further, the created simulation model is used for carrying out fault diagnosis on the target object, the information such as the fault detection rate or the fault isolation rate of the target object is calculated, the information such as the fault type, the fault number, the fault location and the influence factor causing the fault or the hierarchical fault name causing the fault of the target object existing in the current state is analyzed, the obtained diagnosis data is subjected to statistical analysis according to preset diagnosis information, the final fault diagnosis result of the target object is determined, and the fault diagnosis result is referred to further to carry out fault location on the target object; and further, the technical effect of improving the fault diagnosis efficiency and the fault diagnosis capability of the target object can be achieved.
According to the fault diagnosis scheme provided by the embodiment of the invention, a hierarchical fault model is established according to the data characteristics of a target object, and the hierarchical fault model is a hierarchical data structure associated with the target object; establishing a hierarchical fault category of the target object according to the hierarchical fault model; after test data corresponding to the hierarchical fault category are collected, simulation processing is carried out on the test data, and a simulation model of a target object is constructed; and performing fault diagnosis processing on the target object based on the simulation model to obtain a fault diagnosis result. Establishing a hierarchical fault diagnosis model on the basis of a data structure of a reference target object, obtaining a hierarchical fault category through analysis processing, wherein the hierarchical fault category comprises theoretical fault reference data, acquiring actual measurement data of the target object as test data through hardware equipment, and inputting the test data into the hierarchical fault category to obtain data to be detected by fault; carrying out simulation processing on data to be subjected to fault detection to obtain a fault detection simulation model corresponding to a target object, carrying out fault diagnosis on the target object by using the simulation model to obtain fault diagnosis results under all fault categories contained in the target object, and referring to the fault diagnosis results to further position the fault of the target object; according to the technical scheme, the technical effect of improving the fault diagnosis efficiency and the fault diagnosis capability of the target object can be achieved.
Fig. 2 is a schematic flow chart of another fault diagnosis method according to an embodiment of the present invention. Fig. 2 is introduced on the basis of the above embodiment. Referring to the diagram provided in fig. 2, the fault diagnosis method specifically further includes:
s201, generating a topological relation data module according to the data characteristics of the target object, wherein the topological relation data module is used for describing the hierarchical association relation between the target object data.
The execution subject of the embodiment of the invention is a fault diagnosis system. The process of fault diagnosis is also the process of fault detection. Establishing a hierarchical fault model for a detection object aiming at a plurality of fault types, fault influence factors and incidence relations between faults by establishing a fault diagnosis system framework, collecting all data characteristics contained in the detection object and the hierarchical relations among the data characteristics based on the hierarchical fault model, sorting according to the given fault type to obtain a clear fault type corresponding to each detection object, obtaining a two-dimensional table containing theoretical detection data, and inputting the acquired real data into the two-dimensional table for comparison to obtain to-be-tested data; the method comprises the steps of obtaining a plurality of simulation models by utilizing a plurality of simulation processing methods for data to be tested, carrying out fusion processing on the plurality of simulation models by utilizing fusion processing in order to improve the fault diagnosis rate to obtain a final simulation model, and carrying out fault diagnosis on a detection object to obtain a fault diagnosis result with high accuracy.
The target object referred to herein may be understood as an object to be detected. The data feature referred to herein can be understood as feature data of the object to be detected at the sampling node. For example, in a large power supply system, a plurality of monitoring points of the capacitor device are set for acquiring the power supply condition of the capacitor device. The hierarchy here can be understood as the hierarchical relationship between the upper and lower layers or the flat layers between the function modules, the units or the basic control devices in the system where the object to be detected is located. The topological relation data module can be understood as being used for describing the hierarchical connection relation of the tested objects.
Further, when the fault diagnosis system starts diagnosis of the target object, firstly feature data at all sampling nodes of the target object are acquired, the feature data are sorted based on all the acquired feature data, and are divided according to levels to obtain an association relation between levels, the association relation is used as a topological relation data module to express establishment and encapsulation of the target object, test information description, basic model generation, hierarchical association and the like, and preparation is made for next hierarchical data processing.
S202, determining diagnosis reference information of the target object according to the data characteristics of the target object, wherein the diagnosis reference information is used for describing the fault type and the fault influence relation of the target object.
The diagnostic reference information described here can be understood as setting and classifying information such as the type of failure related to the target object and the influence of the failure.
Furthermore, according to the collected characteristic data of the object to be detected, classification statistics is carried out on the fault class and fault influence relation of the object to be detected, and diagnosis reference information of the object to be detected is generated, wherein the diagnosis information comprises hierarchical fault influence transmission description, fault detection mode description (fault association), hierarchical diagnosis information description, fault modes, fault influences and the like of the object to be detected.
And S203, compiling the topological relation data model and the diagnosis reference information to generate a hierarchical fault model of the target object.
The compiling process described here can be understood as an implementation manner, and may be a code compiling manner, a model simulation operation manner, or the like.
Furthermore, after a topological relation data model and diagnosis reference information are obtained by using the characteristic data of the object to be detected, model compiling and storing processing is carried out, compiled information such as the hierarchical topological relation and the diagnosis information of the model is stored, a hierarchical fault model is further generated, and model data support is provided for fault category construction.
In a possible implementation scenario, fig. 3 is a schematic structural diagram of a hierarchical fault model provided in an embodiment of the present invention. According to the diagram provided in fig. 3, after feature data at a sampling node of an object to be detected is obtained, a hierarchical fault model is constructed to provide model data support for fault class construction (fault mode), and the hierarchical fault model mainly comprises three parts, which respectively include: generating a topological relation 1, diagnosing information 2 and compiling and generating a model 3. The topological relation generation 1 is used for describing the hierarchical connection relation of the tested objects, and comprises the establishment and encapsulation of the objects, the description of test information, the generation of a basic model, hierarchical association and the like; the diagnostic information 2 is used for describing fault influence relations of the fault mode and the object, and comprises fault detection mode description (fault association), hierarchical diagnostic information description and the like; the model compiling and generating 3 is used for storing compiled information such as hierarchical topological relation of the model and diagnostic information.
And S204, analyzing the hierarchical fault model to generate a fault category two-dimensional table.
The parsing process referred to herein may be understood as a data analysis process contained in the model. The two-dimensional table of the failure category referred to herein may be understood as a unit that stores theoretical data true data of sampling nodes of the target object using the two-dimensional table.
Further, by loading and analyzing the hierarchical fault model, the obtaining information includes: the method comprises a hierarchical model, all BIT codes and descriptions, all fault types (fault modes) and hierarchical corresponding relations, all sampling nodes and hierarchical corresponding relations, data acquisition instrument information and data acquisition types corresponding to the sampling nodes and the like. And storing the acquired data in a two-dimensional table to generate a fault category two-dimensional table, thereby laying a foundation for diagnostic model training and fault diagnosis.
The method for acquiring the fault category two-dimensional table related to step S204 specifically includes the following steps:
step 1: analyzing the model file corresponding to the hierarchical fault model to obtain analysis information in the model file, wherein the analysis information carries BIT information, fault category, sampling node and fault influence information.
And 2, step: and establishing a fault category library of the target object based on the analysis information, wherein the fault category library is used for establishing a mapping relation between the analysis information and the multi-level fault categories.
Firstly, loading and analyzing BIT information, sampling nodes, fault modes and fault influence information in a hierarchical fault model file, constructing a multi-level associated fault class library (fault mode library), coding the fault class library (fault mode library) according to fault levels, and establishing a mapping corresponding relation between the BIT information and the fault classes (fault modes). The association relation between the BIT codes and the fault type (fault mode) codes is gradually improved, if only the BIT error codes can be detected, whether the associated fault mode exists or not is firstly searched, if the associated fault mode exists, the associated fault mode is directly verified, if the associated fault mode does not exist, fault diagnosis is carried out layer by layer according to the hierarchy until the final diagnosis result is obtained, and the association relation between the BIT codes and the diagnosis result can be established after final confirmation.
And 3, step 3: and creating a fault category library model based on the data mapping relation between the fault category libraries.
Secondly, a hierarchical fault category library model is constructed based on a multi-level associated fault category library, key node information is replaced by measurable node information data corresponding to the fault category and the fault category, and the method is a precondition for knowledge model training and fault diagnosis.
And 4, step 4: and loading the information of the sampling nodes to be diagnosed in the fault class library model to generate a fault class two-dimensional table, wherein the fault class two-dimensional table carries all reference data corresponding to each fault class.
Finally, measurable sampling node information is added on the basis of the hierarchical fault category library model to form a hierarchical fault category two-dimensional table, the hierarchical fault category two-dimensional table is a child node fault category of the current corresponding hierarchy, and the classification of the hierarchical fault category two-dimensional table is determined by the measurable sampling node information in a father node; the columns are lists of all measurable points in the father node, and each measurable point corresponds to different feature extraction modes because the data acquisition modes and the presentation forms are different, namely the data are multi-source heterogeneous data.
S205, establishing a hierarchical fault category based on the fault category two-dimensional table.
Furthermore, after the obtained fault category two-dimensional table is analyzed, the fault category two-dimensional table under each fault category is respectively counted, so that the fault category two-dimensional table of the target object is obtained, the hierarchical fault category is constructed, and preparation is made for simulation.
And S206, creating an actual measurement model according to the hierarchical fault category.
And S207, performing fault injection processing by using the actual measurement model to obtain actual measurement data corresponding to the actual measurement model.
And S208, carrying out integrity processing on the measured data to obtain test data.
Fault injection as referred to herein may be understood as a process of enriching a two-dimensional table of fault classes. The integrity processing may be understood as a process of performing integrity check on data, and performing integrity analysis, check and storage on collected data with reference to all data of the failure mode two-dimensional table.
Furthermore, firstly, an actual measurement hardware system is built according to the hierarchical fault category two-dimensional table, a fault injector is controlled according to sampling node information or a manual intervention mode is adopted to inject a fault, then actual measurement data is loaded and collected, then the collected data is subjected to integrity analysis, verification and storage, and finally the hierarchical fault category two-dimensional table information is updated. The data acquisition, acquisition and processing provides measured data support for the construction of the fault mode.
S209, carrying out data preprocessing on the test data, and carrying out feature extraction on the preprocessed data to obtain feature data of the test data.
The data preprocessing mentioned here can be understood as processing of data format standardization, abnormal data removal, error correction, removal of duplicate data and the like on the test data. The feature extraction can be understood as accurately analyzing the signal time-frequency domain features, which are a plurality of features of the waveform of the test point, such as feature parameters of peak-to-peak value (waveform high value, low value), frequency, average value or duty ratio; and acquiring a new signal sequence through signal decomposition, and calculating an energy characteristic value of the signal sequence as a characteristic value to realize characteristic extraction.
S210, a plurality of fault diagnosis processes are carried out based on the characteristic data, and a plurality of diagnosis results of the target object are obtained.
The fault diagnosis processing can be understood as a process of performing simulation training on data by using various algorithms such as a support vector machine, a neural network, artificial immunity, a concept lattice, a fuzzy C-means and the like.
S211, a simulation model of the target object is constructed by fusing the plurality of diagnosis results, and the simulation model carries fault detection data of the target object.
The fusion processing can be understood as a processing algorithm selected by comprehensively selecting various simulation training algorithms to avoid the risk of a single algorithm as much as possible and improve the fault diagnosis accuracy.
Furthermore, the configuration workflow of the simulation scheme comprises 4 hierarchical algorithm libraries including data preprocessing, feature extraction, a diagnosis knowledge model algorithm, a fusion algorithm and the like. Processing the data format of the two-dimensional table of the hierarchical fault mode by using a data preprocessing algorithm, such as standardization, abnormal data removal, error correction, repeated data removal and the like; then, carrying out signal time-frequency domain characteristic analysis on the standard data after data preprocessing to obtain a new signal sequence, and calculating an energy characteristic value of the signal sequence to realize characteristic extraction; after the characteristics are extracted, a plurality of processing algorithms such as a support vector machine, a neural network, artificial immunity, a concept lattice, a fuzzy C mean value and the like are comprehensively applied to carry out simulation training on data through a diagnosis knowledge model algorithm library; finally, a plurality of diagnosis knowledge model algorithm libraries are comprehensively applied through a fusion algorithm, so that the diagnosis limitation of a single algorithm is avoided as much as possible, and the fault diagnosis accuracy is improved.
S212, obtaining the model name of the simulation model.
And S213, inputting the fault detection data corresponding to the model name into the simulation model, and performing fault diagnosis processing to obtain a fault diagnosis result.
The fault diagnosis process described here can be understood as a process of generating and verifying a fault station short model.
Further, the obtained model name of the simulation model is used for obtaining the algorithm of the current simulation processing, and diagnosis results under various simulation algorithms are obtained by the same method.
And S214, determining the fault diagnosis rate corresponding to the model name according to the fault diagnosis result obtained by fault diagnosis.
S215, judging whether the simulation model meets the fault diagnosis condition or not according to the relation between the fault diagnosis rate and the diagnosis threshold value.
S216, when the fault diagnosis rate is larger than or equal to the diagnosis threshold value, the simulation model is determined to meet the fault diagnosis condition of the target object.
The diagnosis threshold value referred to herein may be understood as a reference value that satisfies the degree of satisfaction of the diagnosis of the fault of the current target object. For example, when 100 preset faults of a target object are diagnosed, 80 faults are obtained through the a simulation algorithm adopted in the embodiment of the present invention, the diagnosis rate of the fault diagnosis result is 80/100=80%, if the diagnosis threshold is set to be 90%, and the diagnosis condition is satisfied only if the characterization fault diagnosis rate exceeds 90%, the currently adopted simulation algorithm does not satisfy the requirement, and when one simulation algorithm obtains a fault diagnosis rate of 98%, the currently adopted simulation algorithm satisfies the requirement.
Further, a proper fault diagnosis model algorithm is selected, a corresponding fault diagnosis model is further generated, index calculation of the fault detection rate and the isolation rate is achieved, then reasoning diagnosis is carried out through fault simulation data by using the fault diagnosis model, and the correctness of the fault diagnosis model is verified. And finally, verifying whether a data preprocessing algorithm, a feature extraction algorithm, a fault diagnosis model algorithm, a fusion algorithm and the like meet the fault diagnosis requirement through the generation and verification of the fault diagnosis model.
According to the fault diagnosis method provided by the embodiment of the invention, through setting five parts, namely a hierarchical fault model, a fault type, data acquisition, acquisition of a simulation model and generation and verification of the fault diagnosis model, sufficient simulation data with small errors are imported and analyzed on the basis of fault simulation data to obtain a fault type two-dimensional table, and fault diagnosis reasoning is finally realized through simulation scheme configuration and model training.
Firstly, constructing a hierarchical fault model of a target object; the method comprises the steps of constructing a hierarchical fault category two-dimensional table by analyzing a hierarchical fault model, and acquiring a hierarchical model, a BIT code, a fault mode, a sampling node, data acquisition instrument information, data acquisition data, corresponding relations between the data and the hierarchy and the like of a measured object; through fault injection, actual measurement data loading, acquisition and integrity verification, sufficient actual measurement data support is provided for a fault category two-dimensional table; automatically generating a fault diagnosis model and evaluating the fault diagnosis model through configuration of a data preprocessing algorithm, a feature extraction algorithm, a fault diagnosis model algorithm, a fusion algorithm and the like; and finally, carrying out reasoning diagnosis on the measured data according to the fault diagnosis model to realize fault location of the measured object. The invention can be used for testing and diagnosing a complex electronic system, adopts the design ideas of universality and convenience, modularizes, organizes and automates the testing and diagnosing process of the complex electronic system, is favorable for reducing the high dependence of the fault locating process on the professional ability level of maintenance personnel, reducing the influence of artificial subjective factors on fault locating and reducing the fault locating time, thereby furthest lightening the unnecessary over-maintenance, after-maintenance, repeated maintenance and other work in the complex electronic system and realizing the technical effect of improving the fault diagnosing efficiency and the diagnosing ability of a target object.
Fig. 4 is a schematic structural diagram of a fault diagnosis device according to an embodiment of the present invention. According to the diagram provided in fig. 4, the fault diagnosis device specifically comprises:
a creating module 41, configured to create a hierarchical fault model according to the data characteristics of the target object, where the hierarchical fault model is a hierarchical data structure associated with the target object;
a creating module 41, configured to create a hierarchical fault category of the target object according to the hierarchical fault model;
the simulation module 42 is configured to perform simulation processing on the test data after the test data corresponding to the hierarchical fault category is acquired, and construct a simulation model of the target object;
and the diagnosis module 43 is configured to perform fault diagnosis processing on the target object based on the simulation model to obtain a fault diagnosis result.
The fault diagnosis apparatus provided in this embodiment may be the fault diagnosis apparatus shown in fig. 4, and may perform all the steps of the fault diagnosis method shown in fig. 1-2, so as to achieve the technical effect of the fault diagnosis method shown in fig. 1-2, and for brevity, it is described with reference to fig. 1-2, and details are not described herein.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, where the electronic device 500 shown in fig. 5 includes: at least one processor 501, memory 502, at least one network interface 504, and other user interfaces 503. The various components in the electronic device 500 are coupled together by a bus system 505. It is understood that the bus system 505 is used to enable connection communications between these components. The bus system 505 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 505 in FIG. 5.
The user interface 503 may include, among other things, a display, a keyboard, or a pointing device (e.g., a mouse, trackball, touch pad, or touch screen, among others.
It is to be understood that the memory 502 in embodiments of the present invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of example, and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), synchronous Dynamic Random Access Memory (SDRAM), double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), enhanced Synchronous SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory 502 described herein is intended to comprise, without being limited to, these and any other suitable types of memory.
In some embodiments, memory 502 stores elements, executable units or data structures, or a subset thereof, or an expanded set thereof: an operating system 5021 and application programs 5022.
The operating system 5021 includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, and is used for implementing various basic services and processing hardware-based tasks. The application 5022 includes various applications, such as a Media Player (Media Player), a Browser (Browser), and the like, for implementing various application services. The program for implementing the method according to the embodiment of the present invention may be included in the application program 5022.
In the embodiment of the present invention, by calling a program or an instruction stored in the memory 502, specifically, a program or an instruction stored in the application 5022, the processor 501 is configured to execute the method steps provided by the method embodiments, for example, including:
establishing a hierarchical fault model according to the data characteristics of the target object, wherein the hierarchical fault model is a hierarchical data structure associated with the target object; establishing a hierarchical fault category of the target object according to the hierarchical fault model; after test data corresponding to the hierarchical fault category are collected, simulation processing is carried out on the test data, and a simulation model of a target object is constructed; and executing fault diagnosis processing on the target object based on the simulation model to obtain a fault diagnosis result.
The method disclosed by the above-mentioned embodiments of the present invention may be applied to the processor 501, or implemented by the processor 501. The processor 501 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 501. The Processor 501 may be a general-purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, or discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software elements in the decoding processor. The software elements may be located in ram, flash, rom, prom, or eprom, registers, among other storage media that are well known in the art. The storage medium is located in the memory 502, and the processor 501 reads the information in the memory 502 and completes the steps of the method in combination with the hardware.
It is to be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or any combination thereof. For a hardware implementation, the Processing units may be implemented within one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), general purpose processors, controllers, micro-controllers, microprocessors, other electronic units designed to perform the functions described herein, or a combination thereof.
For a software implementation, the techniques described herein may be implemented by means of units performing the functions described herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.
The electronic device provided in this embodiment may be the electronic device shown in fig. 5, and may perform all the steps of the fault diagnosis method shown in fig. 1-2, so as to achieve the technical effect of the fault diagnosis method shown in fig. 1-2, and for brevity, it is not described herein again.
The embodiment of the invention also provides a storage medium (computer readable storage medium). The storage medium herein stores one or more programs. Among others, the storage medium may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, a hard disk, or a solid state disk; the memory may also comprise a combination of memories of the kind described above.
When one or more programs in the storage medium are executable by one or more processors to implement the above-described failure diagnosis method performed on the failure diagnosis apparatus side.
The processor is configured to execute the fault diagnosis program stored in the memory to implement the following steps of the fault diagnosis method executed on the fault diagnosis apparatus side:
establishing a hierarchical fault model according to the data characteristics of the target object, wherein the hierarchical fault model is a hierarchical data structure associated with the target object; establishing a hierarchical fault category of the target object according to the hierarchical fault model; after test data corresponding to the hierarchical fault category are collected, simulation processing is carried out on the test data, and a simulation model of a target object is constructed; and performing fault diagnosis processing on the target object based on the simulation model to obtain a fault diagnosis result.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the components and steps of the various examples have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, a software module executed by a processor, or a combination of the two. A software module may reside in Random Access Memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (9)
1. A fault diagnosis method, comprising:
establishing a hierarchical fault model according to the data characteristics of a target object, wherein the hierarchical fault model is a hierarchical data structure associated with the target object;
establishing a hierarchical fault category of the target object according to the hierarchical fault model;
after test data corresponding to the hierarchical fault category are collected, carrying out simulation processing on the test data to construct a simulation model of the target object;
and executing fault diagnosis processing on the target object based on the simulation model to obtain a fault diagnosis result.
2. The method of claim 1, wherein creating a hierarchical fault model from data characteristics of a target object comprises:
generating a topological relation data module according to the data characteristics of the target object, wherein the topological relation data module is used for describing the hierarchical incidence relation among the target object data;
determining diagnosis reference information of the target object according to the data characteristics of the target object, wherein the diagnosis reference information is used for describing the fault type and the fault influence relation of the target object;
and compiling the topological relation data model and the diagnosis reference information to generate a hierarchical fault model of the target object.
3. The method of claim 1, wherein creating the hierarchical fault category for the target object according to the hierarchical fault model comprises:
analyzing the hierarchical fault model to generate a fault category two-dimensional table;
and creating a hierarchical fault category based on the fault category two-dimensional table.
4. The method according to claim 3, wherein the parsing the hierarchical fault model to generate a fault category two-dimensional table includes:
analyzing the model file corresponding to the hierarchical fault model to obtain analysis information in the model file, wherein the analysis information carries BIT information, fault types, sampling nodes and fault influence information;
establishing a fault category library of the target object based on the analysis information, wherein the fault category library is used for establishing a mapping relation between the analysis information and multi-level fault categories;
establishing a fault category library model based on the data mapping relation between the fault category libraries;
and loading the information of the sampling nodes to be diagnosed in the fault category library model, and generating the fault category two-dimensional table, wherein the fault category two-dimensional table carries all reference data corresponding to each fault category.
5. The method of claim 1, wherein collecting test data that matches the hierarchical fault category correspondence comprises:
creating an actual measurement model according to the hierarchical fault category;
performing fault injection processing by using the actual measurement model to obtain actual measurement data corresponding to the actual measurement model;
and carrying out integrity processing on the measured data to obtain the test data.
6. The method of claim 1, wherein the simulating the test data to construct the simulation model of the target object comprises:
carrying out data preprocessing on the test data, and carrying out feature extraction on the preprocessed data to obtain feature data of the test data;
performing a plurality of fault diagnosis processes based on the characteristic data to obtain a plurality of diagnosis results of the target object;
and constructing a simulation model of the target object by fusing a plurality of diagnosis results, wherein the simulation model carries fault detection data of the target object.
7. The method of claim 1, wherein said performing a fault diagnosis process on said target object based on said simulation model comprises:
obtaining a model name of the simulation model;
and inputting the fault detection data corresponding to the model name into the simulation model, and performing fault diagnosis processing to obtain a fault diagnosis result.
8. The method according to claim 7, wherein after performing the fault diagnosis process on the target object, the method further comprises:
determining the fault diagnosis rate corresponding to the model name according to the fault diagnosis result obtained by the fault diagnosis;
judging whether the simulation model meets a fault diagnosis condition or not according to the relation between the fault diagnosis rate and a diagnosis threshold value;
and when the fault diagnosis rate is greater than or equal to the diagnosis threshold value, determining that the simulation model meets the fault diagnosis condition of the target object.
9. A failure diagnosis device characterized by comprising:
the system comprises a creating module, a fault analysis module and a fault analysis module, wherein the creating module is used for creating a hierarchical fault model according to the data characteristics of a target object, and the hierarchical fault model is a hierarchical data structure associated with the target object;
the creating module is further used for creating a hierarchical fault category of the target object according to the hierarchical fault model;
the simulation module is used for carrying out simulation processing on the test data after the test data corresponding to the hierarchical fault category is acquired, and constructing a simulation model of the target object;
and the diagnosis module is used for executing fault diagnosis processing on the target object based on the simulation model to obtain a fault diagnosis result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211638071.5A CN115827353A (en) | 2022-12-15 | 2022-12-15 | Fault diagnosis method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211638071.5A CN115827353A (en) | 2022-12-15 | 2022-12-15 | Fault diagnosis method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115827353A true CN115827353A (en) | 2023-03-21 |
Family
ID=85516894
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211638071.5A Pending CN115827353A (en) | 2022-12-15 | 2022-12-15 | Fault diagnosis method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115827353A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116520270A (en) * | 2023-07-04 | 2023-08-01 | 四川天中星航空科技有限公司 | Radar electronic warfare testing method based on evaluation model |
-
2022
- 2022-12-15 CN CN202211638071.5A patent/CN115827353A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116520270A (en) * | 2023-07-04 | 2023-08-01 | 四川天中星航空科技有限公司 | Radar electronic warfare testing method based on evaluation model |
CN116520270B (en) * | 2023-07-04 | 2023-09-05 | 四川天中星航空科技有限公司 | Radar electronic warfare testing method based on evaluation model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US5500941A (en) | Optimum functional test method to determine the quality of a software system embedded in a large electronic system | |
CN113792825B (en) | Fault classification model training method and device for electricity information acquisition equipment | |
CN108804326B (en) | Automatic software code detection method | |
CN110083514B (en) | Software test defect evaluation method and device, computer equipment and storage medium | |
CN110245085B (en) | Embedded real-time operating system verification method and system by using online model inspection | |
CN114490404A (en) | Test case determination method and device, electronic equipment and storage medium | |
Shan et al. | Generating structurally complex test cases by data mutation: A case study of testing an automated modelling tool | |
CN112199293A (en) | Software quality evaluation method and device, terminal equipment and storage medium | |
CN108563572A (en) | A kind of regression testing method, device and server | |
CN115659335A (en) | Block chain intelligent contract vulnerability detection method and device based on mixed fuzzy test | |
CN115827353A (en) | Fault diagnosis method and device | |
CN103970654B (en) | Software reliability virtual test method | |
CN115952081A (en) | Software testing method, device, storage medium and equipment | |
CN113626326B (en) | Dragging type zero code front end automatic test system based on image recognition | |
CN116991746B (en) | Method and device for evaluating general quality characteristics of software | |
Munson et al. | Toward a quantifiable definition of software faults | |
CN115248783B (en) | Software testing method, system, readable storage medium and computer equipment | |
CN116627804A (en) | Test method, system, electronic equipment and storage medium based on artificial intelligence | |
Valueian et al. | Constructing automated test oracle for low observable software | |
Wohlin et al. | Reliability certification of software components | |
CN115165332A (en) | Integrated design method and system for built-in test and comprehensive test of equipment | |
CN113282504A (en) | Incremental code coverage rate detection method and service development method and device | |
CN110865939A (en) | Application program quality monitoring method and device, computer equipment and storage medium | |
CN111913872A (en) | Software static inspection warning sequencing optimization method based on defect prediction | |
CN113434408B (en) | Unit test case sequencing method based on test prediction |
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 |