CN116541748A - Power grid fault diagnosis method and system based on artificial intelligence technology - Google Patents
Power grid fault diagnosis method and system based on artificial intelligence technology Download PDFInfo
- Publication number
- CN116541748A CN116541748A CN202310493011.7A CN202310493011A CN116541748A CN 116541748 A CN116541748 A CN 116541748A CN 202310493011 A CN202310493011 A CN 202310493011A CN 116541748 A CN116541748 A CN 116541748A
- Authority
- CN
- China
- Prior art keywords
- fault
- power grid
- model
- diagnosis
- artificial intelligence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 104
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 43
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000005516 engineering process Methods 0.000 title claims abstract description 33
- 238000012549 training Methods 0.000 claims abstract description 24
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 14
- 238000013136 deep learning model Methods 0.000 claims description 35
- 238000003062 neural network model Methods 0.000 claims description 18
- 239000013598 vector Substances 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 10
- 230000009471 action Effects 0.000 claims description 7
- 238000004088 simulation Methods 0.000 claims description 7
- 238000000265 homogenisation Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000011176 pooling Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 4
- 238000012795 verification Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 230000007257 malfunction Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000033228 biological regulation Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- 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
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Economics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to the field of fault diagnosis of a power grid system, in particular to a power grid fault diagnosis method and a system based on an artificial intelligence technology, wherein when a complex power grid is subjected to fault diagnosis, the method and the system divide the acquired fault information into numerical information and text information according to different types of the fault information, and respectively input the two different types of information into different artificial intelligence models, so that the situations of large training amount of the artificial intelligence models and high requirement on hardware caused by oversized dimension of the input information are avoided; meanwhile, according to different application degrees of the model to data types, a convolutional neural network model is adopted for fault diagnosis aiming at numerical information, a BP convolutional neural network model is adopted for fault diagnosis aiming at text information, and then a final diagnosis conclusion is determined according to two diagnosis results, so that the accuracy of fault diagnosis is greatly improved.
Description
Technical Field
The invention relates to the field of power system fault diagnosis, in particular to a power grid fault diagnosis method and system based on an artificial intelligence technology.
Background
In recent years, with the continuous expansion of the power grid scale in China, the interconnection among different areas is more and more compact, and the power supply reliability and the operation economy can be improved. Meanwhile, as the power grid structure becomes more and more complex, the influence on the system is larger and larger when the power grid breaks down, the regulation and control center receives a large amount of alarm information, the actual action conditions of the fault element and the field relay protection are judged only by the working experience of operators on duty, omission is unavoidable, if the faults cannot be isolated rapidly and accurately, the faults possibly develop into cascading faults, the fault area is enlarged, and huge economic losses are caused. When the faults cause tripping or multiple faults to cause the alarm of various devices almost simultaneously and the problems of refusal, misoperation, loss of action information and the like of the protection or circuit breaker exist, the diagnosis process becomes more complex, and the problems of misjudgment of staff, prolonged maintenance time and even personal safety accidents can be caused. Therefore, a diagnostic method is needed to quickly distinguish between faulty components and false alarm information to achieve quick fault removal and safe and stable operation of the power grid.
In the prior art, when a complex power grid is subjected to fault diagnosis, two main ideas exist, namely, the fault diagnosis is realized by utilizing a built rule model, and the fault diagnosis is realized on the basis of a data driving model, for example, chinese patent (CN 112000923A) discloses a power grid fault diagnosis method, a system and equipment, and tidal current data is formed into a two-dimensional computer visual tidal current data matrix CVPFM; mapping the CVPFM to the HSV color space to obtain a computer visual trend picture CVPFI; and combining CVPFI before and after the fault into DCVPFI. The DCVPFI is used for replacing the numerical grid power flow data as the input of the CNN, so that the space and time information contained in the power flow can be better extracted, and the position of the system fault is judged; however, when the grid fault diagnosis method based on the rule model faces a more complex grid, the logic constraint is complicated, the knowledge representation is difficult, the model complexity is high, a large amount of alarm information needs to be screened and classified in the rule model building process, and the workload of the rule model is large.
In addition, in the fault diagnosis method driven by data, the prior art is more oriented to diagnosis of electrical quantity information collected by a wide area measurement system, a power management system and the like, and text information in alarm information is lack of research, so that the fault diagnosis accuracy is low, the high-quality development of a modern complex power grid cannot be met, and therefore, the prior art is in urgent need of a technical scheme for improving the fault diagnosis accuracy in the face of a complex power grid topological structure.
Disclosure of Invention
Aiming at the defects of the technical scheme, the invention provides a power grid fault diagnosis method and system based on an artificial intelligence technology, which are used for diagnosing faults by adopting different artificial intelligence models according to different types of fault information after the power grid has faults, and judging a final fault conclusion according to the results, so that the accuracy of fault diagnosis is improved.
To achieve the above object, according to one aspect of the present invention, there is provided a power grid fault diagnosis method based on artificial intelligence technology, comprising the steps of: an artificial intelligence technology-based power grid fault diagnosis method comprises the following steps:
step 1: the alarm information of the power grid after the fault occurs is classified, and the alarm information is divided into two types according to different signal types: one type is numerical information, and the other type is text information;
step 2: performing fault diagnosis on the numerical information by adopting a first artificial intelligent model;
step 3: performing fault diagnosis on the power grid by adopting a second artificial intelligent model;
step 4: judging whether the power grid diagnosis conclusion obtained in the step 2 is the same as the power grid diagnosis conclusion obtained in the step 3; if the fault is the same, determining the fault as the final fault of the final power grid, and if the fault is different, performing diagnosis of the power grid fault by expert intervention.
Preferably, the numerical information includes: fault voltage amplitude, fault voltage phase, fault current amplitude, fault current phase, etc.; because of the complexity of the topological structure of the power grid, the switching value information is likely to be refused to operate, malfunction and the like, and therefore, the switching value information is not used as input data for power grid fault diagnosis;
preferably, the text-type information includes: fault description text reported by a monitoring system;
preferably, the first artificial intelligence model is a first deep learning model;
preferably, the first deep learning model is a convolutional neural network model, and the specific process of performing fault diagnosis on the power grid by using the first deep learning model is as follows:
step 2.1: building a power grid topological structure model through a simulation system, and setting different fault points so as to obtain a plurality of fault sample sets;
specifically, the grid topology model can be built through a Simulink platform;
step 2.2: data preprocessing of a fault sample set;
specifically, the formula of the homogenization treatment is:
wherein x is i ' is the normalized electrical magnitude, xi is the i-th electrical magnitude, x min And x max Respectively minimum and maximum values in the column of data;
step 2.3: constructing a first deep learning model;
preferably, the first deep learning model is a convolutional neural network model, and the convolutional neural network model comprises an input layer, a convolutional layer, a pooling layer, a full-connection layer and a classification layer;
step 2.4: dividing the fault sample set into a training set and a testing set according to the proportion of 8:2; training the first deep learning model so as to obtain optimal network parameters;
preferably, by constructing a loss function for judging occurrence of an optimal network parameter, a specific formula of the loss function is the prior art, and detailed description is omitted herein, and meanwhile, a test set is input into a trained model to verify validity of the model.
Step 2.5: preprocessing the actually collected numerical information, and inputting the preprocessed numerical information into the first deep learning model so as to obtain a power grid diagnosis conclusion;
preferably, the grid diagnosis conclusion of the present invention includes the fault type and fault location.
Preferably, the second artificial intelligence model is a second deep learning model, and the second deep learning model is a BP neural network model;
preferably, the specific process of performing fault diagnosis on the power grid by using the second deep learning model is as follows:
step 3.1: acquiring text type information in a history fault acquired by a system as a sample set;
step 3.2: vectorizing the sample set by adopting a word segmentation model;
preferably, each piece of text information is segmented according to factory stations, equipment descriptions and action descriptions, and word vectors are generated; then generating text vectors according to the word vectors, so that each piece of text type information is converted into the text vectors;
step 3.3: attaching a fault event label to each sample set for obtaining a fault sample set for training the second deep learning model;
step 3.4: building and training the second deep learning model;
specifically, the second deep learning model is a BP neural network model; the network structure of the BP neural network model comprises 3 input layers, 3 hidden layers and 3 output layers, wherein the forward propagation process of the BP neural network is used for calculating the output of the network, the backward propagation process is used for adjusting the weight of the network according to error feedback, the input of the BP neural network is the text vector, and the output is the result of power grid fault diagnosis;
preferably, the sample set is divided into a training sample set, a validation sample set and a test sample set;
inputting a training sample set into the BP neural network model, training the BP neural network model, and simultaneously evaluating the error of the BP neural network model by using a verification sample set, and if the error continuously decreases, continuing training until the preset error precision is met; after training, verifying the trained BP neural network model by using a test sample set, and judging whether the accuracy requirement is met;
step 3.5: the actually collected text information is processed in the step 3.2 and then is input into the second deep learning model, so that a power grid diagnosis conclusion is obtained;
preferably, the power grid diagnosis conclusion of the embodiment is the same as the first deep learning network model, and includes the fault type and the fault position.
According to another aspect of the invention, an artificial intelligence technology-based power grid fault diagnosis system is provided, and is used for diagnosing power grid faults, and the artificial intelligence technology-based power grid fault diagnosis method is adopted; the system further comprises:
the alarm information classification module is used for classifying the alarm information of the power grid after the fault occurs;
the first fault diagnosis module is used for carrying out fault diagnosis on the power grid by adopting a first artificial intelligent model;
the second fault diagnosis module is used for carrying out fault diagnosis on the power grid by adopting a second artificial intelligent model;
the final fault determining module is used for judging whether the power grid diagnosis conclusion obtained in the step 2 is the same as the power grid diagnosis conclusion obtained in the step 3; if the fault is the same, determining the fault as the final fault of the final power grid, and if the fault is different, performing diagnosis of the power grid fault by expert intervention.
According to another aspect of the present invention, there is also provided a computer readable storage medium having a data processing program stored thereon, the data processing program being executed by a processor to perform the above-described grid fault diagnosis method based on artificial intelligence technology.
Based on the technical scheme, the power grid fault diagnosis method and system based on the artificial intelligence technology have the following technical effects:
according to the invention, when the fault diagnosis of the complex power grid is carried out, the complex power grid is divided into numerical information and text information according to different types of the acquired fault information, so that the situations of large training amount of an artificial intelligent model and high requirement on hardware caused by overlarge dimension of input information are avoided; meanwhile, aiming at the same fault, according to different application degrees of the model to the data types, a convolutional neural network model is adopted for fault diagnosis aiming at numerical information, a BP convolutional neural network model is adopted for fault diagnosis aiming at text information, and then a final diagnosis conclusion is determined according to two diagnosis results, so that the accuracy of fault diagnosis is greatly improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a power grid fault diagnosis method based on an artificial intelligence technology according to an embodiment of the present application;
fig. 2 is a flowchart of a first deep learning model provided in an embodiment of the present application for performing fault diagnosis on a power grid;
fig. 3 is a flowchart of fault diagnosis of a power grid by using a second deep learning model according to an embodiment of the present application;
fig. 4 is a schematic diagram of a power grid fault diagnosis system based on an artificial intelligence technology according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings of the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The concepts related to the present application will be described with reference to the accompanying drawings. It should be noted that the following descriptions of the concepts are only for making the content of the present application easier to understand, and do not represent a limitation on the protection scope of the present application.
In order to achieve the above object, in a first embodiment, in an example of the present embodiment, a method for diagnosing a power grid fault based on an artificial intelligence technology is provided, a deep learning model is used as an artificial intelligence model for diagnosing a fault on a complex power grid, conventional fault diagnosis is a labor-intensive process, and requires expertise and experience of relevant features related to a system, which sometimes costs high, while deep learning is used as an artificial intelligence technology for performing fault diagnosis intelligently by adopting an artificial intelligence mode, so that the precision of fault diagnosis can be effectively improved.
As shown in fig. 1, a power grid fault diagnosis method based on artificial intelligence technology includes the following steps:
step 1: classifying the alarm information of the power grid after the fault occurs;
for a complex power grid, when faults occur, because various monitoring devices are contained in different topological structures of the power grid, a lot of alarm information can be generated in the power grid, for example, a data acquisition and monitoring control system can generate fault description, protection action signals, SOE signals and the like, and a wide area measurement system can generate amplitude of accident voltage, phase angle of the accident voltage, amplitude of accident current, phase angle of the accident current and the like; the relay protection fault information management system can generate fault wave recording signals, protection action signals and the like; in the face of such huge signals, if the signals are completely input into the artificial intelligence model, huge calculation amount is definitely generated, and signals of different types need to be converted into signals of the same type, and a part of implicit information is lost in no matter what is, so that fault diagnosis is not accurate enough, therefore, according to different signal types, the embodiment classifies alarm information into two types: one type is numerical information, and the other type is text information;
further, in the present embodiment, the numerical information includes: fault voltage amplitude, fault voltage phase, fault current amplitude, fault current phase, etc.; because of the complexity of the power grid topological structure, the switching value information is likely to be refused to operate, malfunction and the like, and therefore, the embodiment does not adopt the switching value information as input data of power grid fault diagnosis;
further, in this embodiment, the text type information includes: fault description text reported by a monitoring system;
step 2: performing fault diagnosis on the numerical information by adopting a first artificial intelligent model;
further, the first artificial intelligence model is a first deep learning model;
further, the first deep learning model is a convolutional neural network model, as shown in fig. 2, and the specific flow of the first deep learning model for fault diagnosis of the power grid is as follows:
step 2.1: building a power grid topological structure model through a simulation system, and setting different fault points so as to obtain a plurality of fault sample sets;
specifically, a grid topological structure model can be built through a Simulink platform; the Simulink platform is a visual simulation tool in MATLAB proposed by Mathworks company in the United states, and is a modular graph environment for multi-domain simulation and model-based design. The system supports system design, simulation, automatic code generation and continuous test and verification of an embedded system, and provides a graphic editor, a customizable module library and a solver, so that dynamic system modeling and simulation can be performed.
The power grid topological structure model of 6 areas, 25 buses and 12 power transmission sources is built in the Simulink platform, wherein the 25 buses are 110kv buses, the 12 power transmission sources comprise 6 direct current power transmission systems and 6 alternating current power transmission systems, and the set fault types are single-phase ground faults, three-phase ground faults, single-phase short circuit faults, three-phase pipeline faults and the like; 1024 fault sample data sets are provided;
step 2.2: data preprocessing of a fault sample set;
because the fault sample set contains a plurality of data samples, each column of data in the fault sample needs to be subjected to homogenization treatment; specifically, the formula of the homogenization treatment is:
′
wherein x is i For normalized electrical magnitude, xi is the i-th electrical magnitude, x min And x max Respectively minimum and maximum values in the column of data;
step 2.3: constructing a first deep learning model;
specifically, the first deep learning model is a convolutional neural network model, and the convolutional neural network model comprises an input layer, a convolutional layer, a pooling layer, a full-connection layer and a classification layer;
step 2.4: dividing a fault sample set into a training set and a testing set according to the proportion of 8:2; training the first deep learning model so as to obtain optimal network parameters;
specifically, by constructing a loss function for judging occurrence of an optimal network parameter, a specific formula of the loss function is the prior art, detailed description is omitted herein, and meanwhile, a test set is input into a trained model to verify validity of the model.
Step 2.5: preprocessing the actually collected numerical information, and inputting the preprocessed numerical information into a first deep learning model so as to obtain a power grid diagnosis conclusion;
specifically, the power grid diagnosis conclusion of the embodiment includes a fault type and a fault location, and illustratively, the power grid fault diagnosis conclusion includes a single-phase earth fault of a certain section of bus, a single-phase earth fault of a certain section of line, a three-phase earth fault of a certain section of bus, a three-phase earth fault of a certain section of line, and the like.
Step 3: performing fault diagnosis on the power grid by adopting a second artificial intelligent model;
specifically, the second artificial intelligence model is a second deep learning model, and the second deep learning model is a BP neural network model;
specifically, as shown in fig. 3, the specific flow of the second deep learning model for fault diagnosis of the power grid is as follows:
step 3.1: acquiring text type information in a history fault acquired by a system as a sample set;
step 3.2: vectorizing the sample set by adopting a word segmentation model;
specifically, each piece of text information is segmented according to factory stations, equipment descriptions and action descriptions, and word vectors are generated; then generating text vectors according to the word vectors, so that each piece of text type information is converted into the text vectors;
step 3.3: attaching a fault event label to each sample set for obtaining a fault sample set for training a second deep learning model;
step 3.4: building and training a second deep learning model;
specifically, the second deep learning model is a BP neural network model; the network structure of the BP neural network model comprises 3 input layers, 3 hidden layers and 3 output layers, wherein the forward propagation process of the BP neural network is used for calculating the output of the network, the backward propagation process is used for adjusting the weight of the network according to error feedback, the input of the BP neural network is a text vector, and the output is the result of power grid fault diagnosis;
further, the sample set is divided into a training sample set, a verification sample set and a test sample set;
inputting a training sample set into the BP neural network model, training the BP neural network model, and simultaneously, evaluating the error of the BP neural network model by using a verification sample set, and if the error continuously drops, continuing training until the preset error precision is met; after training, verifying the trained BP neural network model by using a test sample set, and judging whether the accuracy requirement is met;
step 3.5: the actually collected text information is processed in the step 3.2 and then is input into a second deep learning model, so that a power grid diagnosis conclusion is obtained;
specifically, the power grid diagnosis conclusion of the embodiment is the same as the first deep learning network model, and includes the fault type and the fault position.
Step 4: judging whether the power grid diagnosis conclusion obtained in the step 2 is the same as the power grid diagnosis conclusion obtained in the step 3; if the faults are the same, determining the faults as final faults of a final power grid, and if the faults are different, performing manual intervention to diagnose the faults of the power grid.
In a second embodiment, in an example of the present embodiment, as shown in fig. 4, an artificial intelligence technology-based power grid fault diagnosis system is provided for diagnosing a power grid fault, and the artificial intelligence technology-based power grid fault diagnosis method in the first embodiment is adopted; the system further comprises:
the alarm information classification module is used for classifying the alarm information of the power grid after the fault occurs;
the first fault diagnosis module is used for carrying out fault diagnosis on the power grid by adopting a first artificial intelligent model;
the second fault diagnosis module is used for carrying out fault diagnosis on the power grid by adopting a second artificial intelligent model;
the final fault determining module is used for judging whether the power grid diagnosis conclusion obtained in the step 2 is the same as the power grid diagnosis conclusion obtained in the step 3; if the faults are the same, determining the faults as final faults of a final power grid, and if the faults are different, performing manual intervention to diagnose the faults of the power grid.
In a third embodiment, the present embodiment includes a computer readable storage medium having a data processing program stored thereon, where the data processing program is executed by a processor to perform the method for diagnosing a power grid fault based on the artificial intelligence technology of the first embodiment.
It will be apparent to one of ordinary skill in the art that embodiments herein may be provided as a method, apparatus (device), or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Including but not limited to RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer, and the like. Furthermore, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.
The description herein is with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices) and computer program products according to embodiments herein. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
The above examples and/or embodiments are merely illustrative of preferred embodiments and/or implementations for implementing the technology of the present invention, and are not intended to limit the implementation of the technology of the present invention in any way, and any person skilled in the art should consider the technology or embodiments substantially the same as the present invention when making minor changes or modifications to other equivalent embodiments without departing from the scope of the technical means disclosed in the present invention.
Claims (10)
1. The utility model provides a power grid fault diagnosis method based on artificial intelligence technology, which is characterized by comprising the following steps:
step 1: the alarm information of the power grid after the fault occurs is classified, and the alarm information is divided into two types according to different signal types: one type is numerical information, and the other type is text information;
step 2: performing fault diagnosis on the numerical information by adopting a first artificial intelligent model;
step 3: performing fault diagnosis on the power grid by adopting a second artificial intelligent model;
step 4: judging whether the power grid diagnosis conclusion obtained in the step 2 is the same as the power grid diagnosis conclusion obtained in the step 3; if the fault is the same, determining the fault as the final fault of the final power grid, and if the fault is different, performing diagnosis of the power grid fault by expert intervention.
2. The method for diagnosing a power grid fault based on artificial intelligence technology according to claim 1, wherein the numerical information comprises: fault voltage amplitude, fault voltage phase, fault current amplitude, fault current phase; the text-type information includes: and fault description text reported by the monitoring system.
3. The method for diagnosing a power grid fault based on artificial intelligence technology as claimed in claim 1, wherein the first artificial intelligence model is a convolutional neural network model.
4. The method for diagnosing a power grid fault based on artificial intelligence technology as set forth in claim 3, wherein the specific process of the first artificial intelligence model for diagnosing a power grid fault is as follows:
step 2.1: building a power grid topological structure model through a simulation system, and setting different fault points so as to obtain a plurality of fault sample sets;
step 2.2: carrying out homogenization pretreatment on the data of the fault sample set;
the homogenization pretreatment formula is as follows:
wherein x' i For normalized electrical magnitude, xi is the i-th electrical magnitude, x min And x max Respectively minimum and maximum values in the data;
step 2.3: constructing a first deep learning model; the first deep learning model is a convolutional neural network model, and the convolutional neural network model comprises an input layer, a convolutional layer, a pooling layer, a full-connection layer and a classification layer;
step 2.4: dividing the fault sample set into a training set and a testing set according to the proportion of 8:2; training the first deep learning model so as to obtain optimal network parameters;
step 2.5: and preprocessing the actually collected numerical information, and inputting the preprocessed numerical information into the first deep learning model, so as to obtain a power grid diagnosis conclusion.
5. The method for diagnosing power grid faults based on artificial intelligence technology as claimed in claim 4, wherein the power grid topological structure model is built through a Simulink platform.
6. The method for diagnosing a power grid fault based on artificial intelligence technology as claimed in claim 1 or 4, wherein the power grid diagnosis conclusion includes a fault type and a fault location.
7. The method for diagnosing a power grid fault based on artificial intelligence technology as claimed in claim 1, wherein the second artificial intelligence model is a BP neural network model.
8. The method for diagnosing power grid faults based on artificial intelligence technology as claimed in claim 7, wherein the specific flow of the second artificial intelligence model for diagnosing power grid faults is as follows:
step 3.1: acquiring text type information in a history fault acquired by a system as a sample set;
step 3.2: vectorizing the sample set by adopting a word segmentation model;
step 3.3: attaching a fault event label to each sample set for obtaining a fault sample set for training the BP neural network model;
step 3.4: building and training the BP neural network model;
step 3.5: and 3.2, processing the actually collected text information and inputting the processed text information into the BP neural network model, thereby obtaining a power grid diagnosis conclusion.
9. The method for diagnosing a power grid fault based on artificial intelligence technology according to claim 8, wherein the step 3.2 specifically comprises: dividing each piece of text information into words according to factory station, equipment description and action description, and generating word vectors; text vectors are then generated from the word vectors, thereby converting each piece of text-type information into a text vector.
10. A power grid fault diagnosis system based on artificial intelligence technology, employing the power grid fault diagnosis method of any one of claims 1-9, the system further comprising:
the alarm information classification module is used for classifying the alarm information of the power grid after the fault occurs;
the first fault diagnosis module is used for carrying out fault diagnosis on the power grid by adopting a first artificial intelligent model;
the second fault diagnosis module is used for carrying out fault diagnosis on the power grid by adopting a second artificial intelligent model;
the final fault determining module is used for judging whether the power grid diagnosis conclusion obtained in the step 2 is the same as the power grid diagnosis conclusion obtained in the step 3; if the fault is the same, determining the fault as the final fault of the final power grid, and if the fault is different, performing diagnosis of the power grid fault by expert intervention.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310493011.7A CN116541748A (en) | 2023-05-05 | 2023-05-05 | Power grid fault diagnosis method and system based on artificial intelligence technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310493011.7A CN116541748A (en) | 2023-05-05 | 2023-05-05 | Power grid fault diagnosis method and system based on artificial intelligence technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116541748A true CN116541748A (en) | 2023-08-04 |
Family
ID=87442936
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310493011.7A Pending CN116541748A (en) | 2023-05-05 | 2023-05-05 | Power grid fault diagnosis method and system based on artificial intelligence technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116541748A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117714193A (en) * | 2023-12-28 | 2024-03-15 | 中国电子技术标准化研究院 | Diagnostic method, diagnostic device, electronic equipment and storage medium |
-
2023
- 2023-05-05 CN CN202310493011.7A patent/CN116541748A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117714193A (en) * | 2023-12-28 | 2024-03-15 | 中国电子技术标准化研究院 | Diagnostic method, diagnostic device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112202736B (en) | Communication network anomaly classification method based on statistical learning and deep learning | |
| CN106786560B (en) | Method and device for automatically extracting stability characteristics of power system | |
| CN112508442B (en) | Transient stability assessment method and system based on automatic and interpretable machine learning | |
| CN108776855A (en) | A kind of smart machine health status evaluation method and system | |
| CN112330488B (en) | Power grid frequency situation prediction method based on transfer learning | |
| CN116541748A (en) | Power grid fault diagnosis method and system based on artificial intelligence technology | |
| CN101833324A (en) | Intelligent fault diagnosis system in tread extrusion process and diagnosis method thereof | |
| CN115453356B (en) | Power equipment operation state monitoring and analyzing method, system, terminal and medium | |
| CN109061391B (en) | Power grid fault diagnosis method and system based on computer vision tidal current diagram | |
| CN116401532B (en) | Method and system for recognizing frequency instability of power system after disturbance | |
| CN116205265A (en) | Power grid fault diagnosis method and device based on deep neural network | |
| CN113092900A (en) | State detection method and device of photovoltaic inverter and computer readable storage medium | |
| CN108053332A (en) | A kind of fault-tree auto-synthesis method and system based on configuration file | |
| CN115684792A (en) | Electrical automation equipment detecting system based on artificial intelligence | |
| CN117411192B (en) | Monitoring method and system for uninterruptible power supply parallel operation system | |
| CN112285484B (en) | Power system fault diagnosis information fusion method and device based on deep neural network | |
| US9529042B2 (en) | Device for and method of estimating error point in logic diagram | |
| CN117526561A (en) | Digital twinning-based transformer substation equipment abnormality monitoring and early warning method and system | |
| CN115983714A (en) | Static security assessment method and system for edge graph neural network power system | |
| CN116400670A (en) | Simulation test method and system for coal mining machine control system | |
| Pisica et al. | Feature selection filter for classification of power system operating states | |
| Olaru et al. | Data mining tools and application in power system engineering | |
| CN115907526A (en) | Power grid voltage sag evaluation method and system, storage medium and computing device | |
| CN112862211A (en) | Method and device for assigning orders of dynamic ring defects of communication management system | |
| CN107194594B (en) | IEC 61850-based back-to-back converter station physical information system reliability evaluation method |
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 |