CN119961810A - High-voltage switchgear fault diagnosis method and system based on deep learning - Google Patents
High-voltage switchgear fault diagnosis method and system based on deep learning Download PDFInfo
- Publication number
- CN119961810A CN119961810A CN202510417833.6A CN202510417833A CN119961810A CN 119961810 A CN119961810 A CN 119961810A CN 202510417833 A CN202510417833 A CN 202510417833A CN 119961810 A CN119961810 A CN 119961810A
- Authority
- CN
- China
- Prior art keywords
- fault
- data
- deep learning
- model
- switch cabinet
- 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.)
- Granted
Links
Classifications
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Testing Electric Properties And Detecting Electric Faults (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明提供一种基于深度学习的高压开关柜故障诊断方法及系统，基于开关柜运行功能划分为若干区域，基于分区结果采集若干区域的运行数据；其中，运行数据包括自变数据和因变数据；基于各区域运行工况公开对各区域的运行数据分别进行划分；构建开关柜仿真模型，将开关柜各区域运行数据输入仿真模型进行仿真训练，得到仿真结果数据，通过比对仿真结果数据和运行数据，得到开关柜故障信息；基于所述故障信息构建数据集，构建神经网络模型并通过故障信息对深度学习模型进行训练，得到故障诊断模型。本发明实现了基于故障对不同区域的影响，反推不同区域的异常信息对故障的影响系数，进一步保证开关柜故障判定的精准度。
The present invention provides a high-voltage switchgear fault diagnosis method and system based on deep learning, which is divided into several areas based on the switchgear operation function, and the operation data of several areas are collected based on the partition results; wherein the operation data includes independent variable data and dependent variable data; the operation data of each area is divided based on the public operation conditions of each area; a switchgear simulation model is constructed, and the operation data of each area of the switchgear is input into the simulation model for simulation training to obtain simulation result data, and the switchgear fault information is obtained by comparing the simulation result data and the operation data; a data set is constructed based on the fault information, a neural network model is constructed, and the deep learning model is trained through the fault information to obtain a fault diagnosis model. The present invention realizes the influence coefficient of abnormal information in different areas on the fault based on the impact of the fault on different areas, and further ensures the accuracy of the switchgear fault judgment.
Description
Technical Field
The invention relates to the technical field of fault diagnosis of switch cabinets, in particular to a fault diagnosis method and system of a high-voltage switch cabinet based on deep learning.
Background
High voltage switchgear is a critical device in electrical power systems for controlling, protecting and distributing electrical energy. Its proper operation is critical to the stability, reliability and safety of the power system. However, the high voltage switchgear is susceptible to various faults such as insulation aging, poor contact, partial discharge, mechanical faults, etc. due to long-term operation, environmental factors, improper operation, etc. These faults not only affect the normal operation of the power system, but may also cause serious safety accidents.
Currently, fault diagnosis of a high-voltage switch cabinet mainly depends on periodic inspection, off-line testing and simple on-line monitoring. These methods have the following limitations:
periodic inspection relies on manual experience, has low efficiency, and is difficult to find early faults.
Offline test, namely, power failure is needed to be carried out, and the normal operation of the power system is affected.
Simple on-line monitoring, which is to monitor only a single parameter (such as temperature and current) and difficult to comprehensively reflect the operation state of the switch cabinet.
The data analysis is insufficient, fusion and depth analysis of multi-source data are lacked, and the accuracy and timeliness of fault diagnosis are low.
Therefore, a method for accurately diagnosing the faults of the switch cabinet is needed.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a fault diagnosis method and system for a high-voltage switch cabinet based on deep learning, which are used for solving the problems in the background art.
In order to achieve the purpose, the invention is realized through the following technical scheme that the fault diagnosis method of the high-voltage switch cabinet based on deep learning comprises the following steps:
Dividing the operation function of the switch cabinet into a plurality of areas, and collecting operation data of the areas based on the partition result;
Wherein the operation data comprises self-variable data and factor variable data;
dividing the operation data of each region based on the operation condition disclosure of each region;
Constructing a simulation model of the switch cabinet, inputting operation data of each area of the switch cabinet into the simulation model for simulation training to obtain simulation result data, and comparing the simulation result data with the operation data to obtain fault information of the switch cabinet;
constructing a data set based on the fault information, constructing a neural network model, and training a deep learning model through the fault information to obtain a fault diagnosis model;
And inputting the operation data of the switch cabinet into a fault diagnosis model to obtain a fault diagnosis result of the target switch cabinet.
As a preferred embodiment, the method for establishing the switch cabinet simulation model includes:
Establishing a physical model of the switch cabinet, and ensuring that parameters of the model of the switch cabinet are consistent with the properties of the reagent of the switch cabinet;
Setting environmental parameters of a switch cabinet model according to the working environment of the switch cabinet;
after setting all parameters, carrying out simulation calculation, calculating working parameters and running states of the switch cabinet, and after calculation, carrying out analysis and evaluation of simulation results.
As a preferred embodiment of the present invention, the comparing the simulation result data with the operation data to obtain the fault information of the switch cabinet includes:
arranging and identifying simulation result data and self-data in operation data of each region according to time sequence and corresponding the simulation result data and the self-data;
extracting key parameters in simulation result data and regional operation data;
comparing key parameters of self-variable data to corresponding strain data in the region operation data with key parameters of corresponding simulation result data;
Determining a fault node, analyzing key parameter characteristics of other areas based on time sequence characteristics of the fault node, and judging a fault type corresponding to the fault node to obtain fault information.
As a preference of the present embodiment, the process of constructing the deep learning model based on the fault information and training the deep learning model by the fault information includes:
Extracting characteristic data in the fault data to obtain a characteristic data set;
Dividing the feature data set into a training set and a verification set;
Constructing a deep learning model, and inputting a training set into the deep learning model for training;
The verification set verifies the trained model, classifies all verification records of all areas according to the number distribution of the areas in the switch cabinet, which are judged to be faulty, in the verification records, extracts area combinations which are formed by different areas and can cause fault diagnosis influence on the model, and evaluates the fault diagnosis influence index of the area combinations on the deep learning model;
And optimizing the deep learning model based on the region distribution condition that the fault diagnosis influence index in the region combination is larger than a preset threshold value.
As a preferable mode of the present embodiment, the step of evaluating the failure diagnosis influence index of the region combination on the deep learning model specifically includes:
acquiring only a certain area in the verification record as a fault area and judging as a fault a;
acquiring an area combination which is judged to be a fault a at least once in a verification record, wherein the set of the area combination is M, the total number of areas in the area combination is I, and the set M which influences the fault a in the set M is judged;
Acquiring all region combinations which are judged to be a fault a and contain M in a set in a verification record, wherein the total number of regions in all region combinations is J;
Calculating characteristic influence factors in the fault diagnosis influence process of the fault region of the fault a on the deep learning model:
;
Wherein γ represents a correction coefficient;
evaluation of the fault diagnosis impact index of region combinations on the deep learning model:
;
wherein, Each of the areas 1,2, and 3 in the area combination of the failure a, and i >2.
The invention further provides a high-voltage switch cabinet fault diagnosis system based on deep learning, which is used for realizing the high-voltage switch cabinet fault diagnosis method based on deep learning, and comprises the following steps:
The regional division module is used for dividing the operation function of the switch cabinet into a plurality of regions and collecting operation data of the regions based on a partitioning result;
Wherein the operation data comprises self-variable data and factor variable data;
the region dividing module is also used for dividing the operation data of each region respectively based on the operation condition disclosure of each region;
The system comprises a model construction module, a fault diagnosis module, a simulation module and a simulation module, wherein the model construction module is used for constructing a simulation model of the switch cabinet, inputting operation data of each region of the switch cabinet into the simulation model for simulation training to obtain simulation result data, and comparing the simulation result data with the operation data to obtain fault information of the switch cabinet;
the fault diagnosis module is used for inputting the operation data of the switch cabinet into the fault diagnosis model to obtain a fault diagnosis result of the target switch cabinet.
As a preferred embodiment, the method for establishing the switch cabinet simulation model includes:
Establishing a physical model of the switch cabinet, and ensuring that parameters of the model of the switch cabinet are consistent with the properties of the reagent of the switch cabinet;
Setting environmental parameters of a switch cabinet model according to the working environment of the switch cabinet;
after setting all parameters, carrying out simulation calculation, calculating working parameters and running states of the switch cabinet, and after calculation, carrying out analysis and evaluation of simulation results.
As a preferred embodiment of the present invention, the comparing the simulation result data with the operation data to obtain the fault information of the switch cabinet includes:
arranging and identifying simulation result data and self-data in operation data of each region according to time sequence and corresponding the simulation result data and the self-data;
extracting key parameters in simulation result data and regional operation data;
comparing key parameters of self-variable data to corresponding strain data in the region operation data with key parameters of corresponding simulation result data;
Determining a fault node, analyzing key parameter characteristics of other areas based on time sequence characteristics of the fault node, and judging a fault type corresponding to the fault node to obtain fault information.
As a preference of the present embodiment, the process of constructing the deep learning model based on the fault information and training the deep learning model by the fault information includes:
Extracting characteristic data in the fault data to obtain a characteristic data set;
Dividing the feature data set into a training set and a verification set;
Constructing a deep learning model, and inputting a training set into the deep learning model for training;
The verification set verifies the trained model, classifies all verification records of all areas according to the number distribution of the areas in the switch cabinet, which are judged to be faulty, in the verification records, extracts area combinations which are formed by different areas and can cause fault diagnosis influence on the model, and evaluates the fault diagnosis influence index of the area combinations on the deep learning model;
And optimizing the deep learning model based on the region distribution condition that the fault diagnosis influence index in the region combination is larger than a preset threshold value.
As a preferable mode of the present embodiment, the step of evaluating the failure diagnosis influence index of the region combination on the deep learning model specifically includes:
acquiring only a certain area in the verification record as a fault area and judging as a fault a;
acquiring an area combination which is judged to be a fault a at least once in a verification record, wherein the set of the area combination is M, the total number of areas in the area combination is I, and the set M which influences the fault a in the set M is judged;
Acquiring all region combinations which are judged to be a fault a and contain M in a set in a verification record, wherein the total number of regions in all region combinations is J;
Calculating characteristic influence factors in the fault diagnosis influence process of the fault region of the fault a on the deep learning model:
;
Wherein γ represents a correction coefficient;
evaluation of the fault diagnosis impact index of region combinations on the deep learning model:
;
wherein, Each of the areas 1,2, and 3 in the area combination of the failure a, and i >2.
The invention provides a fault diagnosis method and system for a high-voltage switch cabinet based on deep learning, which have the advantages that the region division is carried out on the switch cabinet, meanwhile, the region division is carried out on the switch cabinet according to different working conditions, the simulation model is carried out on different working conditions of different regions of the switch cabinet in a mode of establishing a simulation model, the simulation result and actual operation data are compared, abnormal data are obtained through analysis, the authenticity and the accuracy of the data are ensured, meanwhile, the deep learning model is trained and verified through the obtained abnormal data, in verification records, the number distribution of the region in the switch cabinet, which is judged to be faulty, is respectively classified on all verification records of each region, the region combination which is formed by different regions and can cause fault diagnosis influence on the model is extracted, the fault diagnosis influence index of the region combination on the deep learning model is evaluated, the influence on the fault of different regions based on the fault is realized, the influence coefficient of the abnormal information of different regions on the fault is reversely pushed, and the fault judgment accuracy of the switch cabinet is further ensured.
Drawings
FIG. 1 is a flow chart of a fault diagnosis method of a high-voltage switch cabinet based on deep learning;
fig. 2 is a block diagram of a fault diagnosis system of a high-voltage switch cabinet based on deep learning.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for explaining the present invention and are not to be construed as limiting the present invention.
The following disclosure provides many different embodiments, or examples, for implementing different features of the invention. In order to simplify the present disclosure, components and arrangements of specific examples are described below. They are, of course, merely examples and are not intended to limit the invention. Furthermore, the present invention may repeat reference numerals and/or letters in the various examples, which are for the purpose of brevity and clarity, and which do not themselves indicate the relationship between the various embodiments and/or arrangements discussed. In addition, the present invention provides examples of various specific processes and materials, but one of ordinary skill in the art will recognize the application of other processes and/or the use of other materials.
As shown in fig. 1, the embodiment of the invention provides a fault diagnosis method for a high-voltage switch cabinet based on deep learning, which comprises the following steps:
S1, dividing the operation function of the switch cabinet into a plurality of areas, and collecting operation data of the areas based on a partition result;
Wherein the operation data comprises self-variable data and factor variable data;
in this embodiment, dividing a plurality of areas according to an operation function includes:
the incoming line area is used for connecting an external power supply or an upper power grid and introducing electric energy into the switch cabinet;
The bus area is used as a core part for distributing electric energy and is connected with the incoming line area and the outgoing line area to realize collection and distribution of the electric energy;
an outlet area for distributing the electric energy from the switch cabinet to the subordinate equipment or load;
The protection and control area is used for realizing the monitoring, protection and control of the running state of the switch cabinet;
the grounding and safety area ensures the safe operation of equipment and prevents overvoltage and leakage accidents;
auxiliary equipment areas for providing auxiliary support for the switch cabinet, such as power supply, communication and heat dissipation;
the isolation and maintenance area is used for equipment isolation and maintenance and ensures the safety of operators;
8 regions are obtained based on the executive function.
The operation specifically comprises current data, temperature data, humidity data, vibration frequency data, historical maintenance repair data and the like, and also comprises environment physical quantities such as humidity, temperature and the like inside and outside the switch cabinet.
S2, dividing the operation data of each region based on the operation condition disclosure of each region;
it can be appreciated that the operation states of the switch cabinet can be classified into a normal operation state, a load operation state, a standby operation state, and the like according to the operation states.
S3, constructing a simulation model of the switch cabinet, inputting operation data of each area of the switch cabinet into the simulation model for simulation training to obtain simulation result data, and comparing the simulation result data with the operation data to obtain fault information of the switch cabinet;
the fault information comprises fault information of different operation conditions of each region and the connection between the fault information and each region;
in this embodiment, the method for establishing the switch cabinet simulation model includes:
Establishing a physical model of the switch cabinet, and ensuring that parameters of the model of the switch cabinet are consistent with the properties of the reagent of the switch cabinet;
Setting environmental parameters of a switch cabinet model according to the working environment of the switch cabinet;
after setting all parameters, carrying out simulation calculation, calculating working parameters and running states of the switch cabinet, and after calculation, carrying out analysis and evaluation of simulation results.
Comparing the simulation result data with the operation data to obtain the fault information of the switch cabinet comprises the following steps:
arranging and identifying simulation result data and self-data in operation data of each region according to time sequence and corresponding the simulation result data and the self-data;
extracting key parameters in simulation result data and regional operation data;
comparing key parameters of self-variable data to corresponding strain data in the region operation data with key parameters of corresponding simulation result data;
Determining a fault node, analyzing key parameter characteristics of other areas based on time sequence characteristics of the fault node, and judging a fault type corresponding to the fault node to obtain fault information.
Specifically, the fault node may be a single-area fault, and by determining the fault node of the key parameters of other areas in the time sequence, the change condition of the key parameters of other areas after the single-area fault, namely, the association of the area fault, can be determined.
It will be appreciated that the switch cabinet's self-variable data includes temperature data (temperature of key parts inside the switch cabinet such as bus bars, circuit breakers, cable connectors, etc.), current data (current values through the switch cabinet reflecting load conditions), voltage data (input and output voltages of the switch cabinet), vibration data (vibration signals of mechanical components inside the switch cabinet such as circuit breakers, disconnectors), as the variable data includes ambient temperature (temperature of the environment in which the switch cabinet is located, influence the internal temperature), ambient humidity (humidity of the environment in which the switch cabinet is located, influence the internal humidity), load variations (load variations of the power system, influence the current and voltage of the switch cabinet), external vibrations (vibrations caused by nearby devices or traffic, for example, may influence the mechanical components of the switch cabinet).
In the embodiment, the switch cabinet is divided into different areas according to functions, the different areas are further refined and analyzed according to different working conditions, so that the refined control of the switch cabinet is realized, meanwhile, the simulation model of the switch cabinet is constructed, the working parameter performance of the switch cabinet under different working conditions can be accurately represented, the depth analysis of different areas can be further performed, the accuracy of fault diagnosis is improved, the correlation of key data of each area is further analyzed based on the analysis of area faults, and the accuracy of fault analysis of the switch cabinet can be further improved.
In order to realize the diagnosis of fault points of different areas and different working conditions of the switch cabinet, firstly, the operation data of the switch cabinet in the period preset time is collected, the switch cabinet is subjected to area classification, the operation working conditions are relied on to carry out further refined classification, the fault points can be independent or can be caused by the mutual influence of the areas, the operation working conditions of the different areas of the switch cabinet are simulated based on the self-variable data through the simulation of the switch cabinet, the independent faults of the different areas of the switch cabinet are reflected, the influence of the independent faults on the other areas is determined through the operation data in the time sequence of the other areas, the influence of a certain fault on the different areas can be screened, namely, the important characterization of the fault point is diagnosed, otherwise, the specific reasons of the fault point can be diagnosed through the important characterization, and the accurate diagnosis and identification of the specific position of the fault point of the switch cabinet are realized.
In other embodiments, by identifying the operation data immediately before the failure occurs, the position of the failure of the switch cabinet can be predicted in advance based on the analysis of the operation data of the switch cabinet, so that maintenance can be performed in advance.
S4, constructing a data set based on fault information, constructing a neural network model, and training a deep learning model through the fault information to obtain a fault diagnosis model;
in this embodiment, the process of constructing the deep learning model based on the fault information and training the deep learning model by the fault information includes:
s41, extracting characteristic data in fault data to obtain a characteristic data set;
s42, dividing the characteristic data set into a training set and a verification set;
s43, constructing a deep learning model, and inputting a training set into the deep learning model for training;
S44, verifying the trained model by a verification set, classifying all verification records of all areas according to the number distribution of the areas in the switch cabinet judged to be faulty in the verification records, extracting area combinations which are formed by different areas and can cause fault diagnosis influence on the model, and evaluating fault diagnosis influence indexes of the area combinations on the deep learning model;
And S45, optimizing the deep learning model based on the region distribution condition that the fault diagnosis influence index in the region combination is larger than a preset threshold value.
The step of S44 specifically includes:
acquiring only a certain area in the verification record as a fault area and judging as a fault a;
acquiring a region combination which is judged to be a fault a at least once in a verification record, wherein the set of the region combination is M, the total number of regions in the region combination is I, and judging a set M which influences the fault a in the set M;
Acquiring all region combinations which are judged to be a fault a and contain M in a set in a verification record, wherein the total number of regions in all region combinations is J;
Calculating characteristic influence factors in the fault diagnosis influence process of the fault region of the fault a on the deep learning model:
;
Wherein γ represents a correction coefficient;
evaluation of the fault diagnosis impact index of region combinations on the deep learning model:
;
wherein, Each of the areas 1,2, and 3 in the area combination of the failure a, and i >2.
It should be noted that, before extracting the feature data in the fault data, the method further includes processing the fault data, where the processing includes data cleaning and noise cancellation, and the specific process is a prior art means, which is not described herein in detail.
S5, inputting the operation data of the switch cabinet into a fault diagnosis model to obtain a fault diagnosis result of the target switch cabinet.
According to the method, the switch cabinet is divided into areas, the areas of the switch cabinet are further divided according to different working conditions, the simulation model is built according to different working conditions of different areas of the switch cabinet, the simulation model is compared according to simulation results and actual operation data, abnormal data are obtained through analysis, the authenticity and the accuracy of the data are guaranteed, meanwhile, the deep learning model is trained and verified through the obtained abnormal data, in verification records, the number of the areas in the switch cabinet which are judged to be faulty is distributed, all verification records of the areas are respectively classified, the area combination which is formed by the different areas and can cause fault diagnosis influence on the model is extracted, the fault diagnosis influence index of the area combination on the deep learning model is estimated, the influence of faults on the different areas based on faults is achieved, the influence coefficient of abnormal information of the different areas on the faults is reversely pushed, and the accuracy of fault judgment of the switch cabinet is further guaranteed.
As shown in fig. 2, this embodiment further provides a fault diagnosis system of a high-voltage switch cabinet based on deep learning, which is configured to implement the above fault diagnosis method of a high-voltage switch cabinet based on deep learning, and includes:
The regional division module is used for dividing the operation function of the switch cabinet into a plurality of regions and collecting operation data of the regions based on a partitioning result;
Wherein the operation data comprises self-variable data and factor variable data;
the regional division module is also used for dividing the operation data of each region respectively based on the operation condition disclosure of each region;
The system comprises a model construction module, a neural network model, a fault diagnosis model, a simulation model generation module and a simulation model generation module, wherein the model construction module is used for constructing a simulation model of the switch cabinet, inputting operation data of each region of the switch cabinet into the simulation model for simulation training to obtain simulation result data, and comparing the simulation result data with the operation data to obtain fault information of the switch cabinet;
the fault diagnosis module is used for inputting the operation data of the switch cabinet into the fault diagnosis model to obtain a fault diagnosis result of the target switch cabinet.
Further, the method for establishing the switch cabinet simulation model comprises the following steps:
Establishing a physical model of the switch cabinet, and ensuring that parameters of the model of the switch cabinet are consistent with the properties of the reagent of the switch cabinet;
Setting environmental parameters of a switch cabinet model according to the working environment of the switch cabinet;
after setting all parameters, carrying out simulation calculation, calculating working parameters and running states of the switch cabinet, and after calculation, carrying out analysis and evaluation of simulation results.
Further, comparing the simulation result data with the operation data to obtain the fault information of the switch cabinet includes:
arranging and identifying simulation result data and self-data in operation data of each region according to time sequence and corresponding the simulation result data and the self-data;
extracting key parameters in simulation result data and regional operation data;
comparing key parameters of self-variable data to corresponding strain data in the region operation data with key parameters of corresponding simulation result data;
Determining a fault node, analyzing key parameter characteristics of other areas based on time sequence characteristics of the fault node, and judging a fault type corresponding to the fault node to obtain fault information.
Further, constructing a data set based on the fault information, and constructing a deep learning model and training the deep learning model through the fault information includes:
Extracting characteristic data in the fault data to obtain a characteristic data set;
Dividing the feature data set into a training set and a verification set;
Constructing a deep learning model, and inputting a training set into the deep learning model for training;
the verification set verifies the trained model, classifies all verification records of all areas according to the number distribution of the areas in the switch cabinet, which are judged to be faulty, in the verification records, extracts area combinations which are formed by different areas and can cause fault diagnosis influence on the model, and evaluates the fault diagnosis influence index of the area combinations on the deep learning model;
And optimizing the deep learning model based on the region distribution condition that the fault diagnosis influence index in the region combination is larger than a preset threshold value.
Further, the step of evaluating the fault diagnosis influence index of the region combination on the deep learning model specifically includes:
acquiring only a certain area in the verification record as a fault area and judging as a fault a;
acquiring a region combination which is judged to be a fault a at least once in a verification record, wherein the set of the region combination is M, the total number of regions in the region combination is I, and judging a set M which influences the fault a in the set M;
Acquiring all region combinations which are judged to be a fault a and contain M in a set in a verification record, wherein the total number of regions in all region combinations is J;
Calculating characteristic influence factors in the fault diagnosis influence process of the fault region of the fault a on the deep learning model:
;
Wherein γ represents a correction coefficient;
evaluation of the fault diagnosis impact index of region combinations on the deep learning model:
;
wherein, Each of the areas 1,2, and 3 in the area combination of the failure a, and i >2
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510417833.6A CN119961810B (en) | 2025-04-03 | 2025-04-03 | High-voltage switch cabinet fault diagnosis method and system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510417833.6A CN119961810B (en) | 2025-04-03 | 2025-04-03 | High-voltage switch cabinet fault diagnosis method and system based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119961810A true CN119961810A (en) | 2025-05-09 |
| CN119961810B CN119961810B (en) | 2025-08-15 |
Family
ID=95601473
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510417833.6A Active CN119961810B (en) | 2025-04-03 | 2025-04-03 | High-voltage switch cabinet fault diagnosis method and system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119961810B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200387785A1 (en) * | 2019-06-05 | 2020-12-10 | Wuhan University | Power equipment fault detecting and positioning method of artificial intelligence inference fusion |
| US20210101502A1 (en) * | 2019-10-08 | 2021-04-08 | Lg Electronics Inc. | Apparatus and method for predicting failure of electric car charger |
| CN113640633A (en) * | 2021-08-12 | 2021-11-12 | 贵州大学 | A fault location method for gas-insulated combined electrical equipment |
| CN115688880A (en) * | 2022-10-26 | 2023-02-03 | 湖北兴和电力新材料股份有限公司 | Method and device for open-circuit fault diagnosis of switching devices in modular multilevel converters |
| CN115906693A (en) * | 2022-11-11 | 2023-04-04 | 国网辽宁省电力有限公司盘锦供电公司 | A method and device for predicting and diagnosing switchgear overheating faults based on convolutional neural network |
| CN118233339A (en) * | 2024-03-26 | 2024-06-21 | 国网山西省电力公司信息通信分公司 | A communication equipment fault diagnosis method and system based on deep learning |
| CN119134313A (en) * | 2024-09-10 | 2024-12-13 | 国网北京市电力公司 | A method for emergency rescue of power grid failure |
| CN119202952A (en) * | 2024-11-25 | 2024-12-27 | 珠海思达美科技有限公司 | A motor operation fault analysis method based on electrical variable analysis |
| CN119520314A (en) * | 2024-11-06 | 2025-02-25 | 中徽建技术有限公司 | An intelligent operation and maintenance management system and method for a data center |
| CN119728452A (en) * | 2025-02-18 | 2025-03-28 | 广东科明环境仪器工业有限公司 | Remote monitoring and fault diagnosis method and system for environmental simulation system |
-
2025
- 2025-04-03 CN CN202510417833.6A patent/CN119961810B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200387785A1 (en) * | 2019-06-05 | 2020-12-10 | Wuhan University | Power equipment fault detecting and positioning method of artificial intelligence inference fusion |
| US20210101502A1 (en) * | 2019-10-08 | 2021-04-08 | Lg Electronics Inc. | Apparatus and method for predicting failure of electric car charger |
| CN113640633A (en) * | 2021-08-12 | 2021-11-12 | 贵州大学 | A fault location method for gas-insulated combined electrical equipment |
| CN115688880A (en) * | 2022-10-26 | 2023-02-03 | 湖北兴和电力新材料股份有限公司 | Method and device for open-circuit fault diagnosis of switching devices in modular multilevel converters |
| CN115906693A (en) * | 2022-11-11 | 2023-04-04 | 国网辽宁省电力有限公司盘锦供电公司 | A method and device for predicting and diagnosing switchgear overheating faults based on convolutional neural network |
| CN118233339A (en) * | 2024-03-26 | 2024-06-21 | 国网山西省电力公司信息通信分公司 | A communication equipment fault diagnosis method and system based on deep learning |
| CN119134313A (en) * | 2024-09-10 | 2024-12-13 | 国网北京市电力公司 | A method for emergency rescue of power grid failure |
| CN119520314A (en) * | 2024-11-06 | 2025-02-25 | 中徽建技术有限公司 | An intelligent operation and maintenance management system and method for a data center |
| CN119202952A (en) * | 2024-11-25 | 2024-12-27 | 珠海思达美科技有限公司 | A motor operation fault analysis method based on electrical variable analysis |
| CN119728452A (en) * | 2025-02-18 | 2025-03-28 | 广东科明环境仪器工业有限公司 | Remote monitoring and fault diagnosis method and system for environmental simulation system |
Non-Patent Citations (2)
| Title |
|---|
| 傅涛;王茂励;张恒旭;: "针对双馈感应风力发电机的PSASP与PSS/E仿真一致性分析", 电力系统自动化, no. 06, 25 March 2017 (2017-03-25), pages 72 - 77 * |
| 王太勇;王廷虎;王鹏;乔卉卉;徐明达;: "基于注意力机制BiLSTM的设备智能故障诊断方法", 天津大学学报(自然科学与工程技术版), no. 06, 27 April 2020 (2020-04-27), pages 55 - 62 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119961810B (en) | 2025-08-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110006645B (en) | Multi-source fusion high-voltage circuit breaker mechanical fault diagnosis method | |
| CN107203816B (en) | Fault maintenance method and system for secondary equipment of power system | |
| CN117526561A (en) | Substation equipment abnormality monitoring and early warning method and system based on digital twin | |
| CN105425768B (en) | Power secondary equipment monitoring device and method | |
| CN117310353B (en) | A method and system for testing the primary and secondary circuit current and pressurization faults of a substation | |
| CN112418053B (en) | System and method for monitoring abnormal state based on progressive recognition | |
| CN105467971B (en) | A kind of second power equipment monitoring system and method | |
| CN118731675B (en) | Fault detection early warning method and system for circuit breaker | |
| CN117590130A (en) | A digital twin-based situational awareness method for transmission lines | |
| GB2476246A (en) | Diagnosing an operation mode of a machine | |
| CN117640218B (en) | A power network security simulation method and system | |
| CN118380979B (en) | Relay protection method and system for transformer substation | |
| CN115345466A (en) | Power distribution network online evaluation system based on network frame topology and multi-source data fusion | |
| CN119051991B (en) | A dynamic safety assessment method and system for a flexible DC energy router | |
| CN119961810B (en) | High-voltage switch cabinet fault diagnosis method and system based on deep learning | |
| CN118154171B (en) | Fault detection early warning method and system for new energy charging pile | |
| CN116467633B (en) | Online automatic analysis system and method for power grid faults and protection actions | |
| CN119151524A (en) | Auxiliary decision-making system and method for state maintenance of power transformation equipment | |
| CN115932564A (en) | High voltage circuit breaker fault assessment method, device, equipment and readable storage medium | |
| CN113933038A (en) | GIS mechanical performance monitoring method based on multi-source information fusion algorithm | |
| CN120630093B (en) | Electric energy meter precision degradation evaluation system and equipment based on sampling unit fault characteristics | |
| CN119340913B (en) | A Data-Driven Control Method for Intelligent Measuring Circuit Breakers | |
| CN119010365B (en) | Monitoring and protection methods and platforms for the safe operation of power distribution cabinets | |
| CN120528109B (en) | A smart dispatching system for distribution network circuit breaker groups based on the Internet of Things | |
| US20250036828A1 (en) | Simulation system and method for real-time tracking of power plant status based on power plant field values |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |