CN115934393A - Equipment defect correlation analysis method and device, computer equipment and storage medium - Google Patents
Equipment defect correlation analysis method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN115934393A CN115934393A CN202211447799.XA CN202211447799A CN115934393A CN 115934393 A CN115934393 A CN 115934393A CN 202211447799 A CN202211447799 A CN 202211447799A CN 115934393 A CN115934393 A CN 115934393A
- Authority
- CN
- China
- Prior art keywords
- defect
- equipment
- data
- equipment defect
- rule base
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 755
- 238000000034 method Methods 0.000 title claims abstract description 85
- 238000003860 storage Methods 0.000 title claims abstract description 20
- 238000010219 correlation analysis Methods 0.000 title claims description 16
- 238000004458 analytical method Methods 0.000 claims abstract description 66
- 230000006870 function Effects 0.000 claims description 48
- 238000004590 computer program Methods 0.000 claims description 35
- 238000011156 evaluation Methods 0.000 claims description 25
- 230000011218 segmentation Effects 0.000 claims description 19
- 238000005314 correlation function Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 11
- 238000012216 screening Methods 0.000 claims description 9
- 238000012706 support-vector machine Methods 0.000 claims description 9
- 238000013075 data extraction Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000003745 diagnosis Methods 0.000 abstract description 20
- 238000003066 decision tree Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 14
- 238000009411 base construction Methods 0.000 description 12
- 238000012423 maintenance Methods 0.000 description 12
- 238000004891 communication Methods 0.000 description 11
- 230000005540 biological transmission Effects 0.000 description 10
- 230000005856 abnormality Effects 0.000 description 7
- 238000012098 association analyses Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000001816 cooling Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000013500 data storage Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 4
- 239000000835 fiber Substances 0.000 description 4
- 238000010438 heat treatment Methods 0.000 description 4
- 239000013307 optical fiber Substances 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 102000003712 Complement factor B Human genes 0.000 description 3
- 108090000056 Complement factor B Proteins 0.000 description 3
- 238000012097 association analysis method Methods 0.000 description 3
- 230000002950 deficient Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000000739 chaotic effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000013138 pruning Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2431—Multiple classes
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application relates to a method and a device for analyzing relevance of equipment defects, computer equipment and a storage medium. The method comprises the following steps: and acquiring equipment defect data, and matching the equipment defect data in an equipment defect data rule base to obtain an equipment defect analysis result. The method can improve the accuracy of fault diagnosis. The application also provides a method and a device for constructing the equipment defect data rule base, computer equipment and a storage medium, wherein the method comprises the following steps: the method comprises the steps of obtaining an original equipment defect data set, extracting an equipment defect feature set from the original equipment defect data set, conducting defect grading prediction on the equipment defect feature set to obtain an equipment defect grade prediction result, conducting relevance analysis on the equipment defect feature set and the equipment defect grade prediction result to obtain relevance among defect features, defect influence factors and element modules, and constructing an equipment defect data rule base based on the relevance. The method can provide accurate basis for equipment fault diagnosis.
Description
Technical Field
The present application relates to the field of power transmission safety technologies, and in particular, to a method and an apparatus for constructing an equipment defect data rule base, a computer device, a storage medium, and a computer program product, and a method and an apparatus for analyzing an equipment defect association, a computer device, a storage medium, and a computer program product.
Background
The converter valve control equipment is used as core equipment of a direct current transmission system, and normal opening, closing and state monitoring of the converter valve control equipment play an important role in stable operation of the direct current transmission system. The converter valve control equipment is used as core equipment of a direct current transmission system, and normal opening, closing and state monitoring of the converter valve control equipment play an important role in stable operation of the direct current transmission system.
However, in the direct current transmission project, the valve base electronic equipment often has faults, and the fault type and the fault occurrence reason are different. In fact, in the fault diagnosis process of the converter valve control equipment, some faults can be processed after the direct-current system is stopped, most fault defects are manually eliminated and recorded by operation and maintenance personnel, and the fault occurrence reasons are not deeply analyzed.
Therefore, the fault diagnosis result of the existing converter valve control device has the problem of low accuracy.
Disclosure of Invention
Based on this, it is necessary to provide an equipment defect data rule base construction method, an apparatus, a computer device, a storage medium and a computer program product capable of supporting accurate diagnosis of the fault of the converter valve control equipment, and an equipment defect correlation analysis method, an apparatus, a computer device, a storage medium and a computer program product capable of improving the fault diagnosis accuracy of the converter valve control equipment.
In a first aspect, the application provides a method for constructing a device defect data rule base. The method comprises the following steps:
acquiring a defect data set of original equipment;
extracting the equipment defect characteristics of the original equipment defect data set to obtain an equipment defect characteristic set, wherein the equipment defect characteristic set comprises defect characteristics, defect influence factors and an element module;
performing defect grading prediction on the equipment defect feature set to obtain an equipment defect grade prediction result;
performing relevance analysis on the equipment defect feature set and the equipment defect grade prediction result to obtain the relevance relation among the defect features, the defect influence factors and the element modules;
and constructing an equipment defect data rule base based on the association relation.
In one embodiment, extracting the device defect feature of the original device defect data set to obtain a device defect feature set includes:
constructing a characteristic evaluation function of the original equipment defect data set;
evaluating the equipment defect characteristics in the original equipment defect data set according to a characteristic evaluation function, and screening out an initial equipment defect characteristic set;
constructing a characteristic correlation function of the initial equipment defect feature set, and determining the correlation between every two characteristics in the initial equipment defect feature set according to the characteristic correlation function;
clustering the initial equipment defect feature set according to the correlation between every two features in the initial equipment defect feature set to obtain a clustering result;
and extracting the equipment defect characteristics in the clustering result to obtain an equipment defect characteristic set.
In one embodiment, constructing the feature evaluation function for the raw equipment defect data set comprises:
determining the information gain of the defect characteristics of the original equipment defect data set;
constructing an influence factor function of the defect characteristics and the influence factors of the equipment;
constructing a characteristic evaluation function of the original equipment defect data set based on the information gain and the influence factor function;
the method further comprises the following steps:
and screening out the defect characteristics of the target equipment according to the information gain of the defect characteristics of the equipment, and adding the defect characteristics of the target equipment to the defect characteristic set of the initial equipment so as to update the defect characteristic set of the initial equipment.
In one embodiment, the step of performing defect classification prediction on the device defect feature set to obtain a device defect classification prediction result includes:
performing word segmentation processing on the equipment defect description characteristics in the equipment defect characteristic set to obtain word segmentation results;
determining the importance of the keywords in the word segmentation result;
and based on the importance of the keywords, performing defect grading prediction on the equipment defect feature set by using a support vector machine to obtain an equipment defect grade prediction result.
In a second aspect, the application further provides a device for constructing the device defect data rule base. The device comprises:
the data acquisition module is used for acquiring a defect data set of the original equipment;
the data extraction module is used for extracting the equipment defect characteristics of the original equipment defect data set to obtain an equipment defect characteristic set, and the equipment defect characteristic set comprises defect characteristics, defect influence factors and an element module;
the defect grading module is used for carrying out defect grading prediction on the equipment defect feature set to obtain an equipment defect grade prediction result;
the relevance analysis module is used for carrying out relevance analysis on the equipment defect feature set and the equipment defect grade prediction result to obtain the relevance relation among the defect features, the defect influence factors and the element modules;
and the rule base building module is used for building the equipment defect data rule base based on the incidence relation.
In a third aspect, the present application also provides a computer device. The computer equipment comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps in the equipment defect data rule base construction method when executing the computer program.
In a fourth aspect, the present application further provides a computer-readable storage medium. The computer readable storage medium has a computer program stored thereon, and the computer program, when executed by a processor, implements the steps in the above-mentioned device defect data rule base construction method.
In a fifth aspect, the present application further provides a computer program product. The computer program product comprises a computer program which realizes the steps of the device defect data rule base building method when being executed by a processor.
According to the method, the device, the computer equipment, the storage medium and the computer program product for constructing the equipment defect data rule base, the equipment defect feature set is obtained by extracting the equipment defect features of the original equipment defect data set, the equipment defect feature set is subjected to defect grading prediction to obtain an equipment defect grade prediction result, then the equipment defect feature set and the equipment defect grade prediction result are subjected to relevance analysis to obtain the relevance among the defect features, defect influence factors and element modules, and finally the equipment defect data rule base is constructed based on the relevance. In the whole process, accurate basis can be provided for the subsequent association analysis of the equipment defects, the fault tracing and the fault diagnosis through the equipment defect data rule base, and the accuracy of the fault diagnosis is further improved.
In a sixth aspect, the present application provides a method for analyzing device defect association. The method comprises the following steps:
acquiring equipment defect data;
matching the equipment defect data in the established equipment defect data rule base to obtain an equipment defect analysis result;
the equipment defect data rule base is constructed by the method for constructing the equipment defect data rule base, and the equipment defect analysis result comprises defect influence factors, a fault element module and a defect grade prediction result.
In one embodiment, the device defect data includes an initial defect level;
matching the equipment defect data in the established equipment defect data rule base to obtain an equipment defect analysis result, wherein the equipment defect analysis result comprises the following steps:
sorting the equipment defect data according to the initial defect grade;
extracting characteristic data of the sorted equipment defect data;
carrying out keyword matching on the characteristic data in an equipment defect data rule base in sequence to match corresponding equipment defect rule data, wherein the equipment defect rule data comprises confidence coefficients of equipment defect rules;
and sequencing the equipment defect rule data according to the confidence coefficient to obtain an equipment defect analysis result.
In a seventh aspect, the present application provides an apparatus for correlation analysis of device defects. The device comprises:
the data acquisition module is used for acquiring equipment defect data;
the defect analysis module is used for matching the equipment defect data in the established equipment defect data rule base to obtain an equipment defect analysis result;
the equipment defect data rule base is constructed by the method for constructing the equipment defect data rule base, and the equipment defect analysis result comprises defect influence factors, a fault element module and a defect grade prediction result.
In an eighth aspect, the present application further provides a computer device. The computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the device defect correlation analysis method when executing the computer program.
In a ninth aspect, the present application further provides a computer-readable storage medium. The computer readable storage medium has a computer program stored thereon, and the computer program when executed by a processor implements the steps in the above-mentioned device defect correlation analysis method.
In a tenth aspect, the present application further provides a computer program product. The computer program product comprises a computer program, and the computer program realizes the steps of the equipment defect correlation analysis method when being executed by a processor.
The equipment defect relevance analysis method, the equipment defect relevance analysis device, the computer equipment, the storage medium and the computer program product are used for acquiring equipment defect data, matching the equipment defect data in the established equipment defect data rule base to obtain an equipment defect analysis result, wherein the equipment defect analysis result comprises defect influence factors, a fault element module and a defect grade prediction result. In the whole process, the equipment defect data is matched in the established equipment defect data rule base, so that the automatic association analysis and fault location diagnosis of the equipment defects can be realized, and the accuracy of fault diagnosis is improved.
Drawings
FIG. 1 is a diagram of an application environment of a method for building a rule base of device defect data or a method for analyzing relevance of device defects according to an embodiment;
FIG. 2 is a flowchart illustrating a method for building a rule base of device defect data according to an embodiment;
FIG. 3 is a flowchart illustrating the steps of extracting a set of device defect features according to an embodiment;
FIG. 4 is a flowchart illustrating the step of extracting a defect feature set of a device according to another embodiment;
FIG. 5 is a flowchart illustrating a detailed method for building a rule base of device defect data according to an embodiment;
FIG. 6 is a flowchart illustrating a method for device defect correlation analysis in one embodiment;
FIG. 7 is a flowchart illustrating the step of matching device defect data in one embodiment;
FIG. 8 is a block diagram showing the construction of an apparatus for building a rule base for device defect data according to an embodiment;
FIG. 9 is a block diagram showing a structure of an apparatus for analyzing a defect correlation of a device according to an embodiment;
fig. 10 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.
The method for constructing the device defect data rule base provided by the embodiment of the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104, or may be located on the cloud or other network server. Specifically, the operation and maintenance personnel uploads an original equipment defect data set to the server 104 through the terminal 102 and sends a rule base construction message to the server 104, the server 104 responds to the message to obtain the original equipment defect data set, extracts equipment defect characteristics of the original equipment defect data set to obtain an equipment defect characteristic set, the equipment defect characteristic set comprises defect characteristics, defect influence factors and element modules, carries out defect grading prediction on the equipment defect characteristic set to obtain an equipment defect grade prediction result, carries out relevance analysis on the equipment defect characteristic set and the equipment defect grade prediction result to obtain relevance relations among the defect characteristics, the defect influence factors and the element modules, and constructs an equipment defect data rule base based on the relevance relations. The terminal 102 may be but not limited to a personal computer, a notebook computer, a smart phone, a tablet computer, an internet of things device and a portable wearable device, and the internet of things device may be a smart sound box, a smart television, a smart air conditioner, a smart car device, and the like. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, and the like. The server 104 may be implemented as a stand-alone server or a server cluster comprised of multiple servers.
In one embodiment, as shown in fig. 2, a method for constructing a device defect data rule base is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
and step S100, acquiring a defect data set of the original equipment.
The original equipment defect data set refers to the defect data set of the equipment which is uploaded by the terminal and obtained through the previous data preparation work. The original equipment defect data set comprises data such as defect types of equipment, artificially judged initial defect levels, influence factors, fault elements, fault description characteristics, time information and weather conditions. In practical applications, the original device defect data set may be obtained by using the following method: and (3) constructing a physical model of the valve base electronic equipment, analyzing the composition and the function of each element of the valve base electronic equipment according to the principle of the direct-current power transmission system, and analyzing the defect characteristics and the influence factors of the equipment. Then, acquiring defect data of local valve base electronic equipment, carrying out induction analysis on related information such as various defect alarms and influence factors of the equipment according to characteristics to obtain a multi-dimensional influence factor system of the defects of the valve base electronic equipment and a mapping relation between the multi-dimensional influence factor system and the influence factor system, and obtaining an original equipment defect data set. Specifically, a physical model of the valve-based electronic device may be established, and typical defects, including signal abnormality, optical power overload, excessive far-end error code, abnormal magnetic circuit, serious network packet loss, abnormal frequency/voltage of a Central Processing Unit (CPU), and reduced cooling efficiency, may be selected by classifying defect influencing factors. The method comprises the steps of collecting defect data of local valve base electronic equipment, taking each piece of data as a sample, selecting n data samples, analyzing defect characteristics and influence factors of the defect characteristics, wherein the defect characteristics and the influence factors comprise optical fiber connector heating, tail fiber interruption, communication instantaneous interference, software problems, equipment running time, internal communication interruption, manual misoperation, external temperature change and other influence factors, generating a multi-dimensional influence factor system, and obtaining an original equipment defect data set of the valve base electronic equipment defects.
Step S200, extracting the equipment defect characteristics of the original equipment defect data set to obtain an equipment defect characteristic set, wherein the equipment defect characteristic set comprises defect characteristics, defect influence factors and element modules.
In practical applications, the amount of data in the raw device defect data set is very large, and the data is chaotic. Therefore, after the original equipment defect feature set is obtained, data preprocessing such as data cleaning can be performed on the original equipment defect data set, then the features in the data set are evaluated based on a feature correlation function, and the features in the original equipment defect data set, including defect type features, defect influence factors and element modules, are extracted in parallel by combining a MapReduce framework. And obtaining a device defect feature set. For example, typical defect types of valve-based electronic devices include signal abnormality, optical power overload, far-end bit error excess, magnetic circuit abnormality, network packet loss severity, CPU frequency/voltage abnormality, and cooling efficiency reduction. The defect influence factors of the valve base electronic equipment are obtained by analyzing the information such as the performance and the operation parameters of the valve base electronic equipment, wherein the defect influence factors comprise optical fiber joint heating, tail fiber interruption, communication instantaneous interference, software problems, equipment operation time, internal communication interruption and the like, and the element module comprises elements such as a light emitting plate, a light receiving plate, a signal relay and the like.
And step S300, performing defect grading prediction on the equipment defect feature set to obtain an equipment defect grade prediction result.
After the device defect feature set is extracted, the device defect feature set can be subjected to defect grading prediction to obtain a device defect grade prediction result. Specifically, the device defect feature set may be subjected to defect grading prediction by using a classifier, so as to obtain a device defect grade prediction result. In this embodiment, the defects may be classified into 5 classes, respectively "very urgent", "significant", "general", and "other". It is understood that in other embodiments, the defect levels may be performed in other manners.
And step S400, performing relevance analysis on the equipment defect feature set and the equipment defect grade prediction result to obtain the relevance relation among the defect features, the defect influence factors and the element modules.
After the device defect feature set and the device defect grade prediction result are obtained, the device defect feature set can be subjected to quantitative coding, and then relevance analysis is performed on the device defect type, the defect influence factors and the component modules. Specifically, the characteristics affecting the generation of the defect alarm can be determined, and the incidence relation among the defect influence factors, the defect type characteristics and the element module is formed by calculating the support degree and the confidence degree of the defect database, wherein if the strong correlation among the incidence relation among the defect influence factors, the defect type characteristics and the element module is a strong incidence relation (hereinafter, may be referred to as a strong rule), the defect type is characterized in that when the defect occurs, the cause causing the defect generation is largely related to the corresponding defect influence factors in the incidence relation, and the element with the fault is also likely to be the corresponding element module in the incidence relation. It is understood that the number of the association relations may be many, and the association relations may include one-to-many, many-to-one, and many-to-many relations, each of which corresponds to the corresponding support degree and confidence degree to characterize the defect type characteristics, the defect influencing factors, and the degree of correlation between the component modules. For example, defect influencing factors a, b, c, and d may correspond to defect type characteristic A, and component modules 1,2,3, and 4 may correspond to defect type characteristic A.
And step S500, constructing an equipment defect data rule base based on the association relation.
After the embodiment is carried out, after the incidence relations among the defect influence factors, the defect type characteristics and the element modules are obtained, because the obtained incidence relations are very large in number, in order to facilitate data search and matching, a plurality of incidence relations, confidence degrees, defect levels and integration can be carried out to construct an equipment defect data rule base. Specifically, the association relationship may be integrated according to the confidence to obtain the device defect rule database.
In the method for constructing the equipment defect data rule base, the equipment defect feature set is obtained by extracting the equipment defect features of the original equipment defect data set, the equipment defect feature set is subjected to defect grading prediction to obtain an equipment defect grade prediction result, then the equipment defect feature set and the equipment defect grade prediction result are subjected to relevance analysis to obtain the relevance among the defect features, the defect influence factors and the element modules, and finally the equipment defect data rule base is constructed based on the relevance. In the whole process, accurate basis can be provided for the subsequent association analysis of the equipment defects, the fault tracing and the fault diagnosis through the equipment defect data rule base, and the accuracy of the fault diagnosis is further improved.
As shown in FIG. 3, in one embodiment, step 200 includes:
step S202, a characteristic evaluation function of the original equipment defect data set is constructed.
And S204, evaluating the equipment defect characteristics in the original equipment defect data set according to the characteristic evaluation function, and screening out an initial equipment defect characteristic set.
Step S206, a characteristic correlation function of the initial equipment defect feature set is constructed, and the correlation between every two characteristics in the initial equipment defect feature set is determined according to the characteristic correlation function.
And S208, clustering the initial equipment defect feature set according to the correlation between every two features in the initial equipment defect feature set to obtain a clustering result.
And step S210, extracting the equipment defect characteristics in the clustering result to obtain an equipment defect characteristic set.
The feature evaluation function may also be referred to as a feature evaluation function for evaluating a correlation between features. The feature correlation function is a function that evaluates the degree of similarity between two features. In another embodiment, the feature evaluation function F (x) may be constructed in the following manner: and (3) based on the equipment defect feature strategy of the information theory, measuring the influence degree between the defect feature-label and the equipment defect-influence factor by using the relevant knowledge of the information theory, and constructing a feature evaluation function. And then, evaluating the equipment defect characteristics in the original equipment defect data set by using a characteristic evaluation function, adding the characteristics corresponding to the maximum value of the characteristic evaluation value F (i) into the initial equipment defect characteristic set F, and iteratively executing the steps until the number of the characteristics in the F reaches a preset threshold value, and adding the remaining secondary characteristics into the characteristic set F 'by itself, wherein the characteristic set F' can be processed or deleted. Then, a feature correlation function of the initial device defect feature set F is constructed:
wherein x is a ,x b For any two different features in the initial device defect feature set F, I (x) a ；Y|x b ) Is characterized by a feature x b Under the condition of (1), characteristic x a Correlation with label Y, i.e. x b Presence of (2) to x a Degree of influence of correlation with Y. And determining the correlation between every two characteristics in the initial equipment defect characteristic set through a characteristic correlation function. C (x) a ,x b ) The smaller the value of (A), the feature x is characterized a And feature x b The greater the similarity between them, and vice versa, the characterization feature x a And characteristic x b The smaller the degree of similarity therebetween. If x a Represents a defect type characteristic, and x b Representing the characteristics of the influencing factor, function C (x) a ,x b ) A smaller value of (a) indicates that the defect type characteristic is more similar to the influencer characteristic. Based on this, initial device defect characteristics can be obtained according to the correlation between two characteristicsPerforming collection and clustering, and collecting similar characteristics of equipment defects in the same cluster, wherein I = { I = { (I) 1 ，I 2 ，……，I k And obtaining a set of clusters returned after clustering. For the cluster set I, calling a MapReduce framework, uniformly distributing clusters according to the number of nodes in the framework, and extracting features in the clusters by calling a Map function and utilizing a Principal Component Analysis (PCA) algorithm by each node to obtain an equipment defect feature set G. In the embodiment, the initial equipment defect feature set is screened out through the feature evaluation function, and the feature extraction is performed on the initial equipment defect feature set through the feature correlation function, so that originally scattered and disordered features become closely related, and a relationship is established among the features.
As shown in fig. 4, in one embodiment, step S202 includes:
step S222, determining information gain of the defect characteristics of the original equipment in the defect data set, constructing an influence factor function of the defect characteristics of the equipment and the influence factors, and constructing a characteristic judgment function of the defect data set of the original equipment based on the information gain and the influence factor function.
Step S204 further includes: step S224, evaluating the device defect feature in the original device defect dataset according to the feature evaluation function, screening out an initial device defect feature set, screening out a target device defect feature according to the information gain of the device defect feature, and adding the target device defect feature to the initial device defect feature set to update the initial device defect feature set.
In specific implementation, the construction process of the feature evaluation function may be: preprocessing the raw device defect data set, x i Obtaining the defect feature x of the device for any feature in the defect data set of the original device, including defect type feature, influencing factor feature, location feature, component module feature, etc., wherein the above features can be collectively referred to as device defect features, and Y is the corresponding category label (i.e. the category of the defect), and i information gain G (x) i (ii) a Y) is represented by the formula (1).
G(x i ；Y)＝H(Y)-H(Y|x i ) (1)
In the formula, H (Y) is the information entropy about the class label Y, and H (Y | x) i ) For device defect feature x i And the conditional entropy of category Y.
Then, an influence factor function Q between the defect-defect influence factors of the apparatus is constructed, as shown in equation (2). Wherein S is the original equipment defect data set, Y is the category label, x j Are characteristic elements in the data set S.
In the formula, I (x) j (ii) a ) For mutual information, I (x) j ；Y|x i ) To relate to variable x j And the conditional mutual information of the category label Y.
Then, based on the above information gain and the influence factor function, and considering the shadow degree between the defect feature-label and the defect-influence factor, a feature evaluation function F (i) of the original equipment defect data set is constructed, which can be specifically expressed as:
F(i)＝Q(i)+CG(x i ；Y)(0≤C≤1) (3)
wherein C is a function G (x) i (ii) a Y) weight parameter.
Furthermore, a default file Block strategy in Hadoop can be used for dividing the feature space of the original data set into file blocks with the same size; then, the file Block is used as input data, and the Mapper node calls the Map function to use the key value pair<key，value>Counting the information gain of each feature (key is a feature name, value is the information gain of the corresponding feature), and combining each key value pair to obtain a feature information gain set A; finally, the elements in the set A are arranged in a descending order according to the information gain values corresponding to the features, the features in the set A which are ranked more later are removed, and a new defect feature matrix X of the defective equipment is obtained by recombination * . Then X is put in * Adding the characteristic with the maximum information gain value to the initial equipment defect characteristic set, sequentially calculating the characteristic judgment function F (i) value of the alternative characteristic, putting the characteristic corresponding to the maximum value of F (i) into F, and iteratively executing the steps until the characteristic is added to the initial equipment defect characteristic setAnd D, when the number of the features in the F reaches a preset threshold value, obtaining an initial equipment defect feature set. In this embodiment, the feature evaluation function is constructed through the information gain and the influence factor function, so that the feature evaluation function can accurately measure the influence degree between the defect feature-tag and the equipment defect-influence factor, and the extracted equipment defect feature set can be more representative.
As shown in fig. 5, in one embodiment, step S300 includes:
step 302, performing word segmentation on the device defect description features in the device defect feature set to obtain a word segmentation result, determining the importance of the keywords in the word segmentation result, and performing defect grading prediction on the device defect feature set by using a support vector machine based on the importance of the keywords to obtain a device defect grade prediction result.
In practical applications, the device defect feature set includes a device defect description document, and the document includes device defect description features. The operation and maintenance personnel pre-construct a user-defined dictionary, and in the embodiment, the defect classification of the equipment defect feature set may be as follows: based on a user-defined dictionary, performing word segmentation processing on each equipment defect description feature, then, processing each keyword after word segmentation in the equipment defect description feature by adopting a TF-IDF algorithm, and determining the importance of the keyword in a word segmentation result. Specifically, the calculation formula of the TF-IDF is as follows:
TI ij ＝tf i,j ×idf i (5)
wherein the content of the first and second substances,
in the formula, tf ij Is the word frequency, n i,j To describe the word t i In the defect description document d j Number of occurrences, Σ k n k,j Describing document d for defects j All describe the sum of the number of words.idf i For inverse document frequency, | D | is the total number of description documents in the device defect feature data set, | j: t i ∈d j I is the word t containing information i The number of data sets.
After the importance of the keyword is determined, defect grading prediction can be performed on the device defect feature set by using an SVM (Support Vector Machine) classifier to obtain a device defect grade prediction result. Specifically, a hyperplane can be searched from the high-dimensional plane to serve as two types of segmentation planes, so that the minimum classification error rate is ensured. And then, selecting one piece of equipment defect description characteristic, inputting the equipment defect description characteristic into an SVM classifier, performing defect grading prediction, and comparing and matching the extracted characteristics in the equipment defect characteristic data set with the input defect description characteristic, thereby performing grading prediction on each piece of equipment defect description text to obtain an equipment defect grade prediction result TI. It is understood that in other embodiments, other types of classifiers may be used for performing the defect classification prediction, which is not limited herein. In the embodiment, the importance of the keywords in the defect description characteristics of the equipment is calculated, and the SVM classifier is combined, so that accurate defect grading prediction can be realized.
As shown in fig. 5, in one embodiment, step S400 includes: step S402, a decision tree model is built, and relevance analysis is carried out on the equipment defect feature set and the equipment defect grade prediction result according to the built decision tree model, so that the relevance relation among defect features, defect influence factors and element modules is obtained.
In specific implementation, the device defect feature set G, the defect level prediction result TI, and the class label Y may be fused to obtain a defect alarm data set S, and the defect alarm data set S is normalized to obtain S = { G, TI, Y }. The device defect feature set G comprises defect feature information extracted by a device defect type, an influence factor, an influence on the device, an influence on the service, a device manufacturer, a defect area, alarm logic classification, a defect element module and the like, TI comprises five defect grade prediction results of 'emergency', 'important', 'general' and 'other', and Y is a defect alarm source information label. Because the information contained in the device defect feature set G is discrete and independent, the feature information can be digitally processed based on One-Hot coding.
Introducing the device defect feature set G subjected to quantitative coding into an association rule mining algorithm, and calculating the association relation, namely confidence coefficient, among the features in the feature set G through an equation (8) to form factors such as influence factors
Device is defective>
Such a strong association of a faulty element. And traversing the device defect feature set G in sequence, presetting minimum support degree and confidence degree, pruning feature items lower than a minimum threshold value, and then arranging the candidate frequent item sets in a descending order. And (3) creating a root node of a tree structure, continuously scanning the device defect feature set G for the second time, processing the feature items in each item set in sequence, and creating a branch for each feature item set to form the tree structure. And if the root node of the tree structure is empty, recursively calling the tree structure, continuously pruning items which do not meet the minimum threshold index, and judging whether the tree structure of a single path is finally formed, if so, listing all feature item set combinations, and if not, continuously calling the tree structure until the tree structure of the single path is formed.
Wherein, count (x) a ∪x b ) Represents the influencing factor x a And device defect x b The number of simultaneous occurrences; count (x) a ) Representing the influencing factor x a Number of occurrences in the feature set.
The key of constructing the decision tree is to select the optimal division characteristics in the characteristic categories, and the high purity of the nodes is required to be realized as far as possible. And measuring the defect alarm purity by using the information entropy and the Gini index. Assuming that the proportion of the kth type sample in the equipment defect alarm data set S is p k And the Gini value of S is:
the smaller the value of Gini (S), the higher the purity of the alarm data set S representing the equipment defect, as the information entropy is. There may be multiple values for the extracted discrete feature f, if there are N different values, N branch nodes will be generated when f is used to divide S, and S is used to divide S n All values f of the extracted features f contained in the device defect data set S are expressed as f n The resulting kini index is expressed as:
selecting the value with the smallest Gini index as the optimized sub-feature, i.e.
f * ＝arg f∈F min G ini(S，f) (11)
And then, inputting a device defect alarm characteristic multidimensional data set { S, f }, and constructing a decision tree model. And calculating the value of Gini (S, f) through an expression (9) based on the attribute of the discrete characteristic variable f in the defect data set S, and if the calculated result satisfies an expression (10), storing the { S, f } in a partition mode until all partitions are processed, so that the support degree and the confidence degree of the defect database are calculated, and the strong association relationship among the defect characteristic, the defect influence factor and the element module is formed.
Furthermore, after the decision tree model is constructed, the accuracy of the decision tree model needs to be verified. The specific verification process may be: creating a training score and a test score scoring function, setting an initial best score to 0, creating two libraries for storing a currently calculated score and a best score, and setting the score as the best score if the calculated score is less than the currently best score. The classification accuracy of the performance indexes of the decision tree is used as the evaluation index of the decision tree classifier on the defect characteristics of the equipment, and the calculation accuracy is as follows:
in the formula (I), the compound is shown in the specification,
indicating that the parameter is true equals 1, otherwise equals 0./>
Respectively representing the real value and the decision tree classification value of the ith equipment defect alarm data.
In the embodiment, the relevance analysis is performed on the equipment defect feature set and the equipment defect grade prediction result by constructing the decision tree model, so that the accurate relevance relation among the defect feature, the defect influence factor and the element module can be obtained.
For the sake of making clear description of the method for constructing the device defect data rule base provided by the present application, the following description is made with reference to a detailed embodiment, which includes the following contents:
step 1: taking a valve base electronic device as an example, a physical model is established, and typical defects are selected through defect influence factor classification. The method comprises the steps of collecting defect data of local valve base electronic equipment, analyzing defect characteristics and influence factors of the defect characteristics, generating a multi-dimensional influence factor system, and obtaining an original equipment defect data set of the valve base electronic equipment.
Step 2: preprocessing the original data, determining the information gain of the characteristic xi, constructing an influence factor function between the equipment defect and the factor, and constructing a characteristic judgment function of the original equipment defect data set according to the information gain and the influence factor function.
And step 3: and evaluating the equipment defect characteristics in the original equipment defect data set according to the characteristic evaluation function, and screening out an initial equipment defect characteristic set.
And 4, step 4: and constructing a feature correlation function of the initial equipment defect feature set, and determining the correlation between every two features in the initial equipment defect feature set according to the feature correlation function.
And 5: and clustering the initial equipment defect feature set according to the correlation between every two features in the initial equipment defect feature set to obtain a clustering result.
Step 6: and extracting the equipment defect characteristics in the clustering result to obtain an equipment defect characteristic set.
And 7: and performing word segmentation processing on the equipment defect description characteristics in the equipment defect characteristic set to obtain word segmentation results.
And step 8: and determining the importance of the keywords in the word segmentation result.
And step 9: and based on the importance of the keywords, performing defect grading prediction on the equipment defect feature set by using a support vector machine to obtain an equipment defect grade prediction result.
Step 10: and fusing the equipment defect grade prediction result and the equipment defect characteristic set, constructing a decision tree model, and performing relevance analysis on the equipment defect characteristic set and the equipment defect grade prediction result according to the constructed decision tree model to obtain the relevance relation among the defect characteristics, the defect influence factors and the element modules.
Operation and maintenance personnel collect defect data of valve base electronic equipment of a direct current transmission system in a certain area to perform example simulation, and a decision tree model is constructed by utilizing a characteristic correlation function and combining a MapReduce framework to perform correlation analysis on a database.
In practical application, the influence factors of the valve base electronic equipment, such as optical fiber connector heating, tail fiber interruption, communication instantaneous interference, software problems, equipment running time, internal communication interruption, manual misoperation, external temperature change and the like, are obtained by analyzing information such as the performance and the running parameters of the valve base electronic equipment. The defective elements of the valve-based electronic equipment, which cause the VBE (VBScript Encoded Script) system to lose redundancy and never affect the dc operation, include elements such as a light emitting board, a light receiving board, a CPU board, a VBE system power supply, a CLC (Central Logic Controller) interface board, a VBE cabinet cooling system, and a signal relay.
And analyzing the effectiveness of the collected original data of the valve base electronic equipment of the direct current transmission system. Classifying and inducing defect types mainly comprise 8 types, including signal abnormality, light power overload, far-end error code excess, magnetic circuit abnormality, serious network packet loss, ESD damage, CPU frequency/voltage abnormality and cooling efficiency reduction, and numbering by using A-H; the influencing factors mainly comprise 9 types, namely optical fiber joint heating, tail fiber interruption, instantaneous communication interference, software problems, equipment running time, internal communication interruption, improper manual operation and external temperature change, and are numbered by 1-9. The fault element mainly comprises a light emitting board, a light receiving board, a CPU board card, a VBE system power supply, a CLC interface board card, a VBE screen cabinet cooling system and a signal relay 7, and is numbered by alpha-eta. After quantization coding, 900 effective device defect sets are obtained.
The device defect database after the integration and numbering is analyzed through a decision tree algorithm to obtain a corresponding strong rule result, and the result of the accuracy of the added features is obtained according to the minimum threshold condition and is shown in table 1.
The embodiment of the application also provides an equipment defect correlation analysis method, which can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be placed on the cloud or other network server. Specifically, the operation and maintenance personnel may upload acquired device defect data to the server 104 through the terminal 102 and send a device defect analysis message to the server 104, the server 104 responds to the message to acquire device defect data, and the device defect data is matched in a constructed device defect data rule base to obtain a device defect analysis result, where the device defect analysis result includes defect influence factors, a faulty element module, and a defect level prediction result, and the device defect data rule base is constructed by using the device defect data rule base construction method. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices and portable wearable devices, and the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart car-mounted devices, and the like. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, and the like. The server 104 may be implemented as a stand-alone server or as a server cluster comprised of multiple servers.
Table 1 accuracy of the defect data strong rule results and the added features of the valve-based electronic device of the dc power transmission system
In an embodiment, as shown in fig. 6, there is provided a method for analyzing device defect association, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
in step S600, device defect data is obtained.
In practical applications, the device defect data includes data such as defect type characteristics, influencing factor characteristics, location characteristics, and component module characteristics. Similarly, the equipment defect data may be obtained by collecting defect data of local equipment by operation and maintenance personnel. The defect data of the equipment can be a plurality of pieces, and each piece of data comprises defect type characteristics, influence factor characteristics, position characteristics, component module characteristics and the like.
Step S700, matching the device defect data in the established device defect data rule base to obtain a device defect analysis result, where the device defect data rule base is established by using the device defect data rule base establishing method, and the device defect analysis result includes defect influencing factors, a faulty component module, and a defect level prediction result.
After the server obtains the equipment defect data, the server can extract the features in the equipment defect data, and the extracted features are compared and matched in the established equipment defect data rule base to obtain an equipment defect analysis result. For example, for a piece of equipment defect data, the extracted features include a defect type a, a defect level is "very urgent", and a defect influence factor B, and then, since the defect level is "very urgent", the priority of the equipment defect data should be the maximum among a plurality of pieces of equipment defect data, the defect type a and the defect influence factor B are compared and matched in an equipment defect data rule base, and the association relationship, i.e., the strong rule, related to the defect type a and the defect influence factor B is matched. And then, the matched incidence relation is taken as an equipment defect analysis result and pushed to operation and maintenance personnel, so that the operation and maintenance personnel can check the component modules and related influence factors one by one according to the defect type characteristics, defect influence factors and component modules in the equipment defect analysis result and eliminate defects in time.
In the method for analyzing the relevance of the equipment defect, the equipment defect data is obtained, the equipment defect data is matched in the established equipment defect data rule base, and an equipment defect analysis result is obtained, wherein the equipment defect analysis result comprises defect influence factors, a fault element module and a defect grade prediction result. In the whole process, the equipment defect data is matched in the established equipment defect data rule base, so that the automatic association analysis and fault location diagnosis of the equipment defects can be realized, and the accuracy of fault diagnosis is improved.
As shown in FIG. 7, in one embodiment, the device defect data includes an initial defect level;
step S700 includes:
step S702, sorting the device defect data according to the initial defect level.
Step S704, extracting feature data of the sorted device defect data.
Step S706, the feature data is subjected to keyword matching in the equipment defect data rule base in sequence, and corresponding equipment defect rule data is matched, wherein the equipment defect rule data comprises the confidence coefficient of the equipment defect rule.
Step S708, sorting the equipment defect rule data according to the confidence coefficient to obtain an equipment defect analysis result.
The initial defect grade is a preliminary defect grade judgment made by operation and maintenance personnel according to actual defect conditions, and similarly, the initial defect grade comprises five defect grade prediction results of ' very urgent ', ' important ', ' general ', other ' and the like. In a specific implementation, the device defect data may be sorted in a descending order according to the initial defect level, such as "very urgent", "significant", "general", and "other", where the initial defect level is the highest priority of "very urgent", and the order is the first, that is, the device defect data with the highest priority should be matched first. After the sorting processing, the feature data of the equipment defect data, such as defect type features, influence factor features, defect grade features and the like, can be extracted, and then, according to the sequence of the sorted equipment defect data, the feature data extracted from each piece of equipment defect data is subjected to keyword matching in an equipment defect data rule base to match corresponding equipment defect rule data. Because each piece of equipment defect data corresponds to a corresponding confidence coefficient, the equipment defect rule data can be sorted according to the confidence coefficient, namely, sorted in a descending order according to the confidence coefficient, and further, the influence factors with high confidence coefficient and the fault element modules thereof are preferentially matched to obtain an equipment defect analysis result. It is to be understood that the sorting manner mentioned in the above embodiments may also be ascending sorting or other sorting manners, and is not limited herein. In the embodiment, the specific sequence and process of comparison and matching are determined through the initial defect grade and the confidence coefficient, so that the defect analysis result with the highest accuracy can be arranged at the top, the accuracy of fault positioning and diagnosis can be improved, operation and maintenance personnel can find out the fault reason in the fastest time, corresponding measures are taken, the normal operation of the system is guaranteed, and the energy utilization rate of the system is improved.
In one embodiment, after step S700, the method further includes: and receiving equipment defect analysis result feedback data, and optimizing an equipment defect data rule base according to the equipment defect analysis result feedback data.
The equipment defect analysis result feedback data comprises feedback data obtained by operation and maintenance personnel according to the equipment defect analysis result in field investigation and corresponding defect elimination measures and according to whether the defects are completely eliminated, wherein the feedback data comprises specific equipment defect rule data serial numbers, fields with errors such as defect influence factors and component modules, correct influence factor-equipment defect-component module association relation and the like. Because the actual equipment defect condition may have an intricate condition, and the constructed equipment defect data rule base may not accurately and comprehensively cover all types of equipment defects, the equipment defect data rule base needs to be optimized, and the accuracy of defect data matching correlation is improved. Specifically, an equipment defect data fusion model based on a bird swarm optimization algorithm is constructed, new defect data are matched with a generated equipment defect data rule base, the most adaptive degree and corresponding parameters are updated and recorded according to a regression error adaptive degree value, equipment defect analysis result feedback data are received, the confidence degree of the equipment defect rule data is further adjusted, and the accuracy and efficiency of matching prediction between defect characteristics, defect influence factors and element modules are continuously improved. For example, if there is an error in the defect influencing factor in the matched equipment defect rule data a fed back by the operation and maintenance personnel, or there is an error in the component module, and the like, the confidence of the equipment defect rule data a is correspondingly adjusted downward according to the error between the actual condition and the matched result.
In specific implementation, the optimization training of the equipment defect data rule base based on the intelligent bird swarm optimization algorithm may be as follows: dividing the equipment defect rule data into a training set and a test set, carrying out chaotic initialization on a bird group, inputting weight and bias composition, calculating a regression error fitness value according to the parameters of each bird, and recording the optimal fitness value and weight bias. And continuously calculating and updating the fitness value, and optimizing the corresponding parameters to improve the accuracy of the decision tree model. In the embodiment, the equipment defect data rule base is used for continuous training, so that the matching accuracy of the equipment defect data rule base can be continuously improved, and the accuracy of fault positioning and fault diagnosis is improved.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the above embodiments may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the present application further provides an apparatus defect data rule base constructing device for implementing the apparatus defect data rule base constructing method, and an apparatus defect association analyzing device for implementing the apparatus defect association analyzing method. The implementation scheme for solving the problem provided by the apparatus is similar to the implementation scheme described in the above method, so that the specific limitations in the following one or more apparatus defect data rule base construction apparatus embodiments may refer to the limitations on the apparatus defect data rule base construction method in the above description, and are not described herein again.
In one embodiment, as shown in fig. 8, there is provided an apparatus for building a device defect data rule base, including: a data acquisition module 810, a data extraction module 820, a defect classification module 830, a correlation analysis module 840, and a rule base construction module 850, wherein:
a data obtaining module 810, configured to obtain an original device defect data set;
a data extraction module 820, configured to extract device defect features of the original device defect data set to obtain a device defect feature set, where the device defect feature set includes defect features, defect influence factors, and component modules;
the defect grading module 830 is configured to perform defect grading prediction on the device defect feature set to obtain a device defect grade prediction result;
the relevance analysis module 840 is used for performing relevance analysis on the equipment defect feature set and the equipment defect grade prediction result to obtain the relevance relation among the defect features, the defect influence factors and the element modules;
and a rule base building module 850, configured to build the device defect data rule base based on the association relationship.
The device defect data rule base construction device obtains a device defect feature set by extracting device defect features of an original device defect data set, carries out defect grading prediction on the device defect feature set to obtain a device defect grade prediction result, carries out relevance analysis on the device defect feature set and the device defect grade prediction result to obtain relevance relations among defect features, defect influence factors and element modules, and finally constructs a device defect data rule base based on the relevance relations. In the whole process, accurate basis can be provided for the subsequent association analysis of the equipment defects, the fault tracing and the fault diagnosis through the equipment defect data rule base, and the accuracy of the fault diagnosis is further improved.
In an embodiment, the data extraction module 820 is further configured to construct a feature evaluation function of the original device defect data set, evaluate the device defect features in the original device defect data set according to the feature evaluation function, screen out an initial device defect feature set, construct a feature correlation function of the initial device defect feature set, determine a correlation between every two features in the initial device defect feature set according to the feature correlation function, cluster the initial device defect feature set according to the correlation between every two features in the initial device defect feature set to obtain a clustering result, and extract the device defect features in the clustering result to obtain the device defect feature set.
In one embodiment, the data extraction module 820 is further configured to determine an information gain of the defect feature of the original device in the defect data set, construct an influencing factor function of the defect feature of the device and the influencing factor, and construct a feature evaluation function of the defect data set of the original device based on the information gain and the influencing factor function; and screening out the defect characteristics of the target equipment according to the information gain of the defect characteristics of the equipment, and adding the defect characteristics of the target equipment to the defect characteristic set of the initial equipment so as to update the defect characteristic set of the initial equipment.
In an embodiment, the defect classification module 830 is further configured to perform word segmentation on the device defect description features in the device defect feature set to obtain word segmentation results, and determine the importance of the keywords in the word segmentation results;
and based on the importance of the keywords, performing defect grading prediction on the equipment defect feature set by using a support vector machine to obtain an equipment defect grade prediction result.
In one embodiment, as shown in fig. 9, there is provided an apparatus for analyzing a device defect correlation, including: a data acquisition module 910 and a defect analysis module 920, wherein:
a data obtaining module 910, configured to obtain device defect data.
And the defect analysis module 920 is configured to match the device defect data in the established device defect data rule base to obtain a device defect analysis result.
The equipment defect data rule base is constructed by the method for constructing the equipment defect data rule base, and the equipment defect analysis result comprises defect influence factors, a fault element module and a defect grade prediction result.
The device defect correlation analysis device obtains device defect data, matches the device defect data in the established device defect data rule base to obtain a device defect analysis result, wherein the device defect analysis result comprises defect influence factors, a fault element module and a defect grade prediction result. In the whole process, the equipment defect data is matched in the established equipment defect data rule base, so that the automatic association analysis and fault positioning diagnosis of the equipment defects can be realized, and the accuracy of the fault diagnosis is improved.
In an embodiment, the defect analysis module 920 is further configured to sort the device defect data according to the initial defect level, extract feature data of the sorted device defect data, sequentially perform keyword matching on the feature data in the device defect data rule base, match corresponding device defect rule data to obtain device defect rule data, where the device defect rule data includes a confidence level of the device defect rule, and sort the device defect rule data according to the confidence level to obtain a device defect analysis result.
The modules in the device defect data rule base building device and the device defect correlation analysis device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 10. The computer device includes a processor, a memory, an Input/Output interface (I/O for short), and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used to store device defect data. The input/output interface of the computer device is used for exchanging information between the processor and an external device. The communication interface of the computer device is used for connecting and communicating with an external terminal through a network. The computer program is executed by a processor to implement a device defect data rule base construction method and a device defect association analysis method.
Those skilled in the art will appreciate that the architecture shown in fig. 10 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the steps in the device defect data rule base building method or the device defect correlation analysis method when executing the computer program.
In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and the computer program is executed by a processor to implement the steps of the above-mentioned device defect data rule base construction method or device defect association analysis method.
In one embodiment, a computer program product is provided, which includes a computer program, and when being executed by a processor, the computer program implements the steps of the above-mentioned device defect data rule base construction method or device defect association analysis method.
It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) referred to in the present application are information and data authorized by the user or fully authorized by the party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), magnetic Random Access Memory (MRAM), ferroelectric Random Access Memory (FRAM), phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases involved in the embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (10)
1. A method for constructing a device defect data rule base is characterized by comprising the following steps:
acquiring a defect data set of original equipment;
extracting the equipment defect characteristics of the original equipment defect data set to obtain an equipment defect characteristic set, wherein the equipment defect characteristic set comprises defect characteristics, defect influence factors and an element module;
performing defect grading prediction on the equipment defect feature set to obtain an equipment defect grade prediction result;
performing relevance analysis on the equipment defect feature set and the equipment defect grade prediction result to obtain the relevance relationship among the defect features, the defect influence factors and the element modules;
and constructing the equipment defect data rule base based on the incidence relation.
2. The method for constructing the equipment defect data rule base according to claim 1, wherein the extracting the equipment defect features of the original equipment defect data set to obtain an equipment defect feature set comprises:
constructing a characteristic judgment function of the original equipment defect data set;
evaluating the characteristics in the original equipment defect data set according to the characteristic evaluation function, and screening out an initial equipment defect characteristic set;
constructing a feature correlation function of the initial equipment defect feature set, and determining the correlation between every two features in the initial equipment defect feature set according to the feature correlation function;
clustering the initial equipment defect feature set according to the correlation between every two features in the initial equipment defect feature set to obtain a clustering result;
and extracting the equipment defect characteristics in the clustering result to obtain an equipment defect characteristic set.
3. The method of claim 2, wherein the constructing the feature evaluation function of the original equipment defect data set comprises:
determining information gain of the defect characteristics of the original equipment in the defect data set;
constructing an influence factor function of the defect characteristics and the influence factors of the equipment;
constructing a characteristic judgment function of the original equipment defect data set based on the information gain and the influence factor function;
the method further comprises the following steps:
and screening out a target device defect characteristic according to the information gain of the device defect characteristic, and adding the target device defect characteristic to the initial device defect characteristic set to update the initial device defect characteristic set.
4. The method for constructing the equipment defect data rule base according to claim 1, wherein the step of performing defect grade prediction on the equipment defect feature set to obtain an equipment defect grade prediction result comprises the following steps:
performing word segmentation processing on the equipment defect description characteristics in the equipment defect characteristic set to obtain word segmentation results;
determining the importance of the keywords in the word segmentation result;
and based on the importance of the keywords, performing defect grading prediction on the equipment defect feature set by using a support vector machine to obtain an equipment defect grade prediction result.
5. An apparatus defect correlation analysis method, the method comprising:
acquiring equipment defect data;
matching the equipment defect data in a constructed equipment defect data rule base to obtain an equipment defect analysis result;
the equipment defect data rule base is constructed by the method for constructing the equipment defect data rule base according to any one of claims 1 to 4, and the equipment defect analysis result comprises a defect influence factor, a fault element module and a defect grade prediction result.
6. The device defect correlation analysis method of claim 5, wherein the device defect data comprises an initial defect level;
the matching of the equipment defect data in the established equipment defect data rule base to obtain an equipment defect analysis result comprises the following steps:
sorting the equipment defect data according to the initial defect grade;
extracting the characteristic data of the sorted equipment defect data;
carrying out keyword matching on the characteristic data in the equipment defect data rule base in sequence to match corresponding equipment defect rule data, wherein the equipment defect rule data comprises confidence coefficients of equipment defect rules;
and sequencing the equipment defect rule data according to the confidence coefficient to obtain an equipment defect analysis result.
7. An apparatus for building a rule base of device defect data, the apparatus comprising:
the data acquisition module is used for acquiring a defect data set of the original equipment;
the data extraction module is used for extracting the equipment defect characteristics of the original equipment defect data set to obtain an equipment defect characteristic set, and the equipment defect characteristic set comprises defect characteristics, defect influence factors and an element module;
the defect grading module is used for carrying out defect grading prediction on the equipment defect feature set to obtain an equipment defect grade prediction result;
the relevance analysis module is used for carrying out relevance analysis on the equipment defect feature set and the equipment defect grade prediction result to obtain the relevance relation among the defect features, the defect influence factors and the element modules;
and the rule base building module is used for building the equipment defect data rule base based on the incidence relation.
8. An apparatus for analyzing correlation between device defects, the apparatus comprising:
the data acquisition module is used for acquiring equipment defect data;
the defect analysis module is used for matching the equipment defect data in a constructed equipment defect data rule base to obtain an equipment defect analysis result;
the equipment defect data rule base is constructed by the method for constructing the equipment defect data rule base according to any one of claims 1 to 4, and the equipment defect analysis result comprises a defect influence factor, a fault element module and a defect grade prediction result.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211447799.XA CN115934393A (en) | 2022-11-18 | 2022-11-18 | Equipment defect correlation analysis method and device, computer equipment and storage medium |
| PCT/CN2022/134353 WO2024103436A1 (en) | 2022-11-18 | 2022-11-25 | Device defect data rule base construction method and device defect correlation analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211447799.XA CN115934393A (en) | 2022-11-18 | 2022-11-18 | Equipment defect correlation analysis method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115934393A true CN115934393A (en) | 2023-04-07 |
Family
ID=86650003
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211447799.XA Pending CN115934393A (en) | 2022-11-18 | 2022-11-18 | Equipment defect correlation analysis method and device, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115934393A (en) |
| WO (1) | WO2024103436A1 (en) |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10043264B2 (en) * | 2012-04-19 | 2018-08-07 | Applied Materials Israel Ltd. | Integration of automatic and manual defect classification |
| CN112949874B (en) * | 2021-03-04 | 2022-10-04 | 国网江苏省电力有限公司南京供电分公司 | Power distribution terminal defect characteristic self-diagnosis method and system |
| CN113313409A (en) * | 2021-06-16 | 2021-08-27 | 中国南方电网有限责任公司 | Power system secondary equipment defect analysis method and system based on data association |
| CN114090647A (en) * | 2021-10-22 | 2022-02-25 | 国家电网公司西南分部 | Power communication equipment defect relevance analysis method and defect checking method |
| CN114169406A (en) * | 2021-11-17 | 2022-03-11 | 西安理工大学 | Feature selection method based on symmetry uncertainty joint condition entropy |
| CN114860931A (en) * | 2022-04-26 | 2022-08-05 | 华北电力大学 | Relay protection defect text grading method based on Voting Classifier model |
| CN115329144A (en) * | 2022-08-09 | 2022-11-11 | 中国银行股份有限公司 | Root cause determination method and device for product defects |
-
2022
- 2022-11-18 CN CN202211447799.XA patent/CN115934393A/en active Pending
- 2022-11-25 WO PCT/CN2022/134353 patent/WO2024103436A1/en unknown
Also Published As
| Publication number | Publication date |
|---|---|
| WO2024103436A1 (en) | 2024-05-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107168995B (en) | Data processing method and server | |
| CN105471647B (en) | A kind of power communication network fault positioning method | |
| WO2023226423A1 (en) | Auxiliary chip design method and apparatus, device and nonvolatile storage medium | |
| CN111078512A (en) | Alarm record generation method and device, alarm equipment and storage medium | |
| CN110544047A (en) | Bad data identification method | |
| CN114048318A (en) | Clustering method, system, device and storage medium based on density radius | |
| CN112308173A (en) | Multi-target object evaluation method based on multi-evaluation factor fusion and related equipment thereof | |
| CN111027841A (en) | Low-voltage transformer area line loss calculation method based on gradient lifting decision tree | |
| WO2024131524A1 (en) | Depression diet management method based on food image segmentation | |
| CN117290404A (en) | Method and system for rapidly searching and practical main distribution network fault processing method | |
| CN117221087A (en) | Alarm root cause positioning method, device and medium | |
| WO2024103436A1 (en) | Device defect data rule base construction method and device defect correlation analysis method | |
| CN116304721A (en) | Data standard making method and system for big data management based on data category | |
| CN115035966A (en) | Superconductor screening method, device and equipment based on active learning and symbolic regression | |
| CN115494431A (en) | Transformer fault warning method, terminal equipment and computer readable storage medium | |
| CN115619245A (en) | Portrait construction and classification method and system based on data dimension reduction method | |
| CN115221955A (en) | Multi-depth neural network parameter fusion system and method based on sample difference analysis | |
| CN116842936A (en) | Keyword recognition method, keyword recognition device, electronic equipment and computer readable storage medium | |
| CN113689036A (en) | Thermal imager quality problem reason prediction method based on decision tree C4.5 algorithm | |
| CN113779248A (en) | Data classification model training method, data processing method and storage medium | |
| CN113641823A (en) | Text classification model training method, text classification device, text classification equipment and medium | |
| Chareka et al. | A study of fitness functions for data classification using grammatical evolution | |
| CN114330090A (en) | Defect detection method and device, computer equipment and storage medium | |
| CN112101414A (en) | ICT supply chain network key node identification attribute extraction method | |
| CN112529319A (en) | Grading method and device based on multi-dimensional features, computer equipment and storage medium |
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 |