CN116167438A - Transformer fault diagnosis method based on improved quantum genetic algorithm optimized SVM - Google Patents

Transformer fault diagnosis method based on improved quantum genetic algorithm optimized SVM Download PDF

Info

Publication number
CN116167438A
CN116167438A CN202310169047.XA CN202310169047A CN116167438A CN 116167438 A CN116167438 A CN 116167438A CN 202310169047 A CN202310169047 A CN 202310169047A CN 116167438 A CN116167438 A CN 116167438A
Authority
CN
China
Prior art keywords
data
svm
genetic algorithm
quantum
fault diagnosis
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
Application number
CN202310169047.XA
Other languages
Chinese (zh)
Inventor
颜宏文
周潭
马瑞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Changsha University of Science and Technology
Original Assignee
Changsha University of Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Changsha University of Science and Technology filed Critical Changsha University of Science and Technology
Priority to CN202310169047.XA priority Critical patent/CN116167438A/en
Publication of CN116167438A publication Critical patent/CN116167438A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N10/00—Quantum computing, i.e. information processing based on quantum-mechanical phenomena
    • G06N10/60—Quantum algorithms, e.g. based on quantum optimisation, quantum Fourier or Hadamard transforms
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
    • 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

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Biophysics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computational Linguistics (AREA)
  • Condensed Matter Physics & Semiconductors (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Genetics & Genomics (AREA)
  • Physiology (AREA)
  • Computational Mathematics (AREA)
  • Molecular Biology (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Testing Or Measuring Of Semiconductors Or The Like (AREA)

Abstract

The transformer fault diagnosis method based on the improved quantum genetic algorithm optimization SVM comprises the following steps: firstly, obtaining relevant data of dissolved gas in transformer oil and transformer fault information as sample data, and aiming at the unbalanced data problem, processing few sample data by using an SMOTE algorithm to increase few sample data; secondly, carrying out normalization processing on the amplified sample data; then, optimizing parameters of a support vector machine by using an improved quantum genetic algorithm to obtain an optimal support vector machine model; finally, testing the performance of the support vector machine model by using a test set; the method can solve the problem of unbalanced data and improve the validity of the evaluation data; meanwhile, the improved quantum genetic algorithm has higher convergence rate and stronger searching capability of parameter optimization, and finally improves the accuracy and reliability of transformer fault diagnosis.

Description

Transformer fault diagnosis method based on improved quantum genetic algorithm optimized SVM
Technical Field
The invention belongs to the technical field of oil immersed transformer equipment state detection, and particularly relates to a transformer fault diagnosis method based on an improved quantum genetic algorithm optimization SVM.
Background
The power transformer is one of important equipment in the power system, and the safe operation of the power transformer ensures the safety and stability of the power system. The oil-immersed transformer is a widely adopted transformer type, so that the fault of the oil-immersed power transformer can be accurately diagnosed, and the oil-immersed power transformer can be accurately maintained according to the fault type, so that the stability of a power system is ensured, and the damage to society is reduced.
At present, intelligent diagnosis of the fault type of the transformer is mainly performed based on the gas component dissolved in the transformer oil when the transformer fault occurs, namely, the gas component dissolved in the transformer oil when the fault occurs is taken as a characteristic vector, a nonlinear mapping relation between the characteristic vector and the fault type of the transformer is established, and the corresponding fault type is diagnosed by detecting and analyzing the gas component (Dissolved Gasses Analysis, DGA) dissolved in the transformer oil when the transformer fault occurs. However, this method is limited to the scope of threshold diagnosis, and it is often required to diagnose the result when the content of some characteristic gases exceeds the threshold value, so that it is difficult to diagnose the fault type in time at the early stage of fault occurrence. In recent years, with the development of artificial intelligence research, methods such as an artificial neural network, a Bayesian classifier, a support vector machine and the like are widely used in the field of transformer faults, but the methods generally have the problems of low convergence speed, easy sinking of local minima, low fault diagnosis rate and the like in use.
Disclosure of Invention
The invention aims to provide a transformer fault diagnosis method based on an improved quantum genetic algorithm optimized SVM, which can improve the validity of sample data, has higher diagnosis efficiency and accuracy, and can effectively and accurately identify transformer faults.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a transformer fault diagnosis method based on improved quantum genetic algorithm optimization SVM comprises the following steps:
s1, acquiring relevant data of dissolved gas in transformer oil and transformer fault information as sample data;
s2, aiming at the problem of unbalanced collection of fault data, the SMOTE algorithm can be utilized to amplify the data of a small amount of samples;
s3, carrying out normalization processing on the 5 DGA characteristic gas data subjected to data amplification, and dividing the normalized data into test sample data and training sample data;
s4, improving a traditional quantum genetic algorithm, optimizing two parameters of an SVM penalty factor C and a nuclear parameter alpha by using the improved quantum genetic algorithm, and finding out an optimal penalty factor C and a nuclear parameter alpha;
s5, training the optimized SVM model again by using a training set to obtain a final SVM fault diagnosis model;
s6, testing the performance of a final SVM fault diagnosis model by using the normalized test set sample data;
preferably, data of dissolved gas content in 5 kinds of oil of H2, C2H2, CH4, C2H6, C2H4 are collected in S1, wherein the fault types include: five typical fault types of medium-low temperature overheat T1, high-temperature overheat T2, low-energy discharge D1, high-energy discharge D2 and partial discharge PD, and no fault state O1.
Preferably, in S2, all sample data are counted, and data amplification is performed on the fault data by using SMOTE algorithm on the data with a smaller number of fault type samples.
Preferably, in S3, the sample data is normalized using an arctangent function to project 5 DGA-characteristic gas data into the [0,1] interval, taking into account the large differences between the various gas component contents.
Preferably, the method for improving the quantum genetic algorithm in S4 is as follows: introducing quantum mutation operation and quantum mutation operation, preventing the algorithm from converging prematurely and avoiding sinking into local extremum; the quantum revolving door dynamic adjustment strategy is implemented, and the rotation angle is not determined according to the adjustment strategy designed in advance any more, but is calculated through a formula.
Preferably, the optimization of the SVM parameter algorithm based on the improved quantum genetic algorithm is as follows:
step one: initializing quantum genetic parameters such as population size, chromosome length, variation probability Pm, crossover probability Pc, etc. to generate initial population
Figure BDA0004097243010000021
Wherein->
Figure BDA0004097243010000022
The ith quantum chromosome of the t generation is represented, and n is the number of quantum chromosomes. At the same time, the qubit probability amplitude of each quantum chromosome is initially +.>
Figure BDA0004097243010000023
Wherein (j=1, 2, m), m is the length of the quantum chromosome.
Step two: performing one measurement on the population Q (t) to obtain a group of binary individuals
Figure BDA0004097243010000024
An ith individual that is a t generation population; the measuring method comprises the following steps: for each qubit, a number between 0 and 1 is randomly generated, if larger than |alpha> 2 The corresponding binary bit is taken as 1, otherwise, 0 is taken;
step three: and evaluating the fitness, calculating the fitness value of each individual in the population, finding out the individual with the largest current fitness value and the global optimal value, and reserving the global optimal value.
Step four: and (5) calculating a rotation angle by rotation angle selection, and updating the population by using the quantum rotation gate.
Step five: and carrying out quantum mutation operation according to the mutation probability.
Step six: and performing quantum crossover operation according to the crossover probability.
Step seven: judging whether the algorithm can be ended, if so, outputting an optimal solution, and ending the algorithm; otherwise, returning to the second step to continue execution.
Preferably, the optimized parameters are used for retraining to obtain a final SVM model, and the test set data is used for testing the performance of the final SVM fault diagnosis model.
The technical scheme of the invention has the following beneficial technical effects:
the improved quantum genetic algorithm is used for optimizing parameters in the SVM, so that blindness of the SVM algorithm during parameter selection can be effectively overcome, and the diagnosis accuracy of the SVM algorithm is improved.
The invention improves the quantum genetic algorithm, so that the quantum genetic algorithm can dynamically adjust the quantum rotation angle, and mutation operation and crossover operation are introduced, thereby avoiding the algorithm from sinking into local extremum and converging with global optimal solution more quickly.
The invention solves the problem of unbalanced fault sample data by using the SMOTE algorithm, performs normalization processing on the data by using an arctangent function, projects the data into the [0,1] interval, and improves the effectiveness of the original data.
Drawings
FIG. 1 is a flow chart of fault diagnosis of an improved quantum genetic algorithm optimized SVM transformer of the invention.
FIG. 2 is a flow chart of an improved quantum genetic algorithm in the present invention.
Detailed Description
The objects, technical solutions and advantages of the present invention will become more apparent, and the present invention will be further described in detail with reference to the accompanying drawings in conjunction with the detailed description. It should be understood that the invention is not limited to the specific embodiments, but is capable of numerous modifications within the spirit and scope of the invention as hereinafter defined and defined by the appended claims as will be apparent to those skilled in the art all falling within the true spirit and scope of the invention as hereinafter claimed.
According to one embodiment of the present application, referring to fig. 1, the transformer fault diagnosis method of the improved quantum genetic algorithm-based optimized SVM of the present solution includes the following steps:
s1, acquiring relevant data of dissolved gas in transformer oil and transformer fault information as sample data;
s2, aiming at the problem of unbalanced collection of fault data, the SMOTE algorithm can be utilized to amplify the data of a small amount of samples;
s3, carrying out normalization processing on the 5 DGA characteristic gas data subjected to data amplification, and dividing the normalized data into test sample data and training sample data;
s4, improving a traditional quantum genetic algorithm, optimizing two parameters of an SVM penalty factor C and a nuclear parameter alpha by using the improved quantum genetic algorithm, and finding out an optimal penalty factor C and a nuclear parameter alpha;
s5, training the optimized SVM model again by using a training set to obtain a final SVM fault diagnosis model;
s6, testing the performance of a final SVM fault diagnosis model by using the normalized test set sample data;
the above steps will be described in detail below according to one embodiment of the present application.
In step S1, data related to dissolved gas in transformer oil and fault information of a transformer are obtained as sample data, specifically including five kinds of data related to gas, i.e. H2, C2H2, CH4, C2H6, and C2H4, where the fault types include: five typical fault types of medium-low temperature overheat T1, high-temperature overheat T2, low-energy discharge D1, high-energy discharge D2 and partial discharge PD, and no fault state O1.
In step S2, data with a smaller number of fault type samples are subjected to data amplification by using SMOTE algorithm.
In step S3, taking into account the great differences between the contents of the various gas components, the sample data is normalized by using an arctangent function, 5 DGA characteristic gas data are projected into the [0,1] interval, and the normalized data are randomly divided into training test data and test training data.
The normalization operation is specifically as follows:
SUM＝∑x i
Figure BDA0004097243010000041
Figure BDA0004097243010000042
Figure BDA0004097243010000043
wherein x is i ' is the relative content of the gas;
Figure BDA0004097243010000044
average the relative content of the i-th gas in all samples; u (u) ij The normalized result of the ith gas in the jth sample. After the characteristic gas is normalized, training, testing, parameter optimization and fault diagnosis of the SVM model are facilitated.
In step S4, the modification is performed on the conventional quantum genetic algorithm, and two parameters, namely, the penalty factor C and the nuclear parameter α, in the SVM are optimized by using the modified quantum genetic algorithm.
The improvement of the quantum genetic algorithm is that quantum mutation operation and quantum mutation operation are introduced, so that the algorithm is prevented from being converged prematurely, and a local extremum is avoided; implementing a quantum revolving door dynamic adjustment strategy, wherein the rotation angle is not determined according to a pre-designed adjustment strategy, but is calculated through a formula, so that the convergence speed of an algorithm is increased;
the rotation angle selection expression of the quantum rotation gate in the improved quantum genetic algorithm is as follows:
Figure BDA0004097243010000045
in the above formula, Δθ∈ [ 0.01. Pi., 0.05. Pi ]]，θ min Representing the minimum value of the interval, i.e. 0.01 pi, theta max Representing the maximum value of this interval. f (f) x Representing the fitness value, f, of the individual currently to be updated max Representing the currently optimal individual is the fitness value. From the above equation, when the current individual is far from the optimal individual, the value of Δθ is larger, the adjustment amplitude is larger, which is beneficial to accelerating the convergence rate, and when the current individual is near to the optimal individual, the value of Δθ is smaller, the adjustment amplitude is smaller, which is more beneficial to finding the optimal solution.
In step S4, the process of optimizing the penalty factor C and the kernel parameter α in the SVM by using the improved quantum genetic algorithm is shown in fig. 2:
step one: initializing quantum genetic parameters such as population size, chromosome length, variation probability Pm, crossover probability Pc, etc. to generate initial population
Figure BDA0004097243010000051
Wherein->
Figure BDA0004097243010000052
The ith quantum chromosome of the t generation is represented, and n is the number of quantum chromosomes. At the same time, the qubit probability amplitude of each quantum chromosome is initially +.>
Figure BDA0004097243010000053
Wherein (j=1, 2, m), m is the length of the quantum chromosome;
step two: performing one measurement on the population Q (t) to obtain a group of binary individuals
Figure BDA0004097243010000054
An ith individual that is a t generation population; the measuring method comprises the following steps: for each qubit, a number between 0 and 1 is randomly generated, if larger than |alpha> 2 The corresponding binary bit is taken as 1, otherwise, 0 is taken;
step three: the fitness evaluation is carried out, the fitness value of each individual in the population is calculated, the individual with the largest current fitness value and the global optimal value are found out, and the global optimal value is reserved;
step four: the rotation angle is calculated by rotation angle selection, and the population is updated by quantum rotation gates;
step five: carrying out quantum mutation operation according to mutation probability;
step six: quantum cross operation is carried out according to the cross probability;
step seven: judging whether the algorithm can be ended, if so, outputting an optimal solution, and ending the algorithm; otherwise, returning to the second step to continue execution;
in the steps S5 and S6, the optimized parameters are utilized to retrain to obtain a final SVM model, and the test set data is used for testing the performance of the final SVM fault diagnosis model.
Finally, the transformer fault example is analyzed, and the final experimental result shows that the improved quantum genetic algorithm has high convergence rate, can effectively perform global optimization, and can diagnose the transformer fault by using the SVM method optimized by the improved quantum genetic algorithm, so that the fault of the oil-immersed transformer can be more accurately identified.
Although specific embodiments of the invention have been described in detail with reference to the accompanying drawings, it should not be construed as limiting the scope of protection of the present patent. Various modifications and variations which may be made by those skilled in the art without the creative effort are within the scope of the patent described in the claims.

Claims (7)

1. The transformer fault diagnosis method based on the improved quantum genetic algorithm optimization SVM is characterized by comprising the following steps of:
s1, acquiring relevant data of dissolved gas in transformer oil and transformer fault information as sample data;
s2, aiming at the problem of unbalanced sample data, the SMOTE algorithm can be utilized to amplify the data of a small amount of samples;
s3, carrying out normalization processing on the 5 DGA characteristic gas data subjected to data amplification, and dividing the normalized data into test sample data and training sample data;
s4, improving a traditional quantum genetic algorithm, optimizing two parameters of an SVM penalty factor C and a nuclear parameter alpha by using the improved quantum genetic algorithm, and finding out an optimal penalty factor C and a nuclear parameter alpha;
s5, training the optimized SVM model again by using a training set to obtain a final SVM fault diagnosis model;
s6, testing the performance of the final SVM fault diagnosis model by using the normalized test set sample data.
2. The method for transformer fault diagnosis of the optimized SVM based on the improved quantum genetic algorithm according to claim 1, wherein the data of the dissolved gas content in the 5 kinds of oils of H2, C2H2, CH4, C2H6, C2H4 are collected based on the S1, wherein the fault types include: five typical fault types of medium-low temperature overheat T1, high-temperature overheat T2, low-energy discharge D1, high-energy discharge D2 and partial discharge PD, and no fault state O1.
3. The transformer fault diagnosis method based on the improved quantum genetic algorithm optimization SVM according to claim 1, wherein all sample data are counted, and the data with a smaller number of fault type samples are subjected to data amplification by the SMOTE algorithm.
4. The transformer fault diagnosis method for optimizing SVM based on improved quantum genetic algorithm according to claim 1, wherein the sample data is normalized by means of an arctangent function in consideration of a great difference between contents of various gas components, and 5 DGA characteristic gas data are projected into [0,1] interval.
5. The transformer fault diagnosis method for optimizing an SVM based on the improved quantum genetic algorithm according to claim 1, wherein the improved method of the quantum genetic algorithm in S4 is as follows: introducing quantum mutation operation and quantum mutation operation, preventing the algorithm from converging prematurely and avoiding sinking into local extremum; and the quantum revolving door dynamic adjustment strategy is implemented, and the rotation angle is not determined according to the adjustment strategy designed in advance, but the convergence rate of the algorithm is increased through formula calculation.
6. The transformer fault diagnosis method for optimizing SVM based on improved quantum genetic algorithm according to claim 1, wherein the optimization SVM parameter algorithm based on improved quantum genetic algorithm comprises the following steps:
step one: initializing quantum genetic parameters such as population size, chromosome length, variation probability Pm, crossover probability Pc and the like to generate an initial population Q (t) = { Q 1 t ,q t 2 ,...q t n }, where q i t (i=1, 2,..n) represents the ith quantum chromosome of the t-th generation, n being the number of quantum chromosomes;
step two: performing one measurement on the population Q (t) to obtain a group of binary individuals P (t) = (P) 1 t ,p 1 t ,...,p t n ),p i t An ith individual that is a t generation population;
step three: the fitness evaluation is carried out, the fitness value of each individual in the population is calculated, the individual with the largest current fitness value and the global optimal value are found out, and the global optimal value is reserved;
step four: calculating a rotation angle by using the rotation angle selection, and updating the population by using the quantum rotation gate;
step five: carrying out quantum mutation operation according to mutation probability;
step six: quantum cross operation is carried out according to the cross probability;
step seven: judging whether the algorithm can be ended, if so, outputting an optimal solution, and ending the algorithm; otherwise, returning to the second step to continue execution.
7. The transformer fault diagnosis method for optimizing SVM based on improved quantum genetic algorithm according to claim 1, wherein preferably, the final SVM model is retrained using the optimized parameters and the performance of the final SVM fault diagnosis model is tested using the test set data.
CN202310169047.XA 2023-02-27 2023-02-27 Transformer fault diagnosis method based on improved quantum genetic algorithm optimized SVM Pending CN116167438A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310169047.XA CN116167438A (en) 2023-02-27 2023-02-27 Transformer fault diagnosis method based on improved quantum genetic algorithm optimized SVM

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310169047.XA CN116167438A (en) 2023-02-27 2023-02-27 Transformer fault diagnosis method based on improved quantum genetic algorithm optimized SVM

Publications (1)

Publication Number Publication Date
CN116167438A true CN116167438A (en) 2023-05-26

Family

ID=86416111

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310169047.XA Pending CN116167438A (en) 2023-02-27 2023-02-27 Transformer fault diagnosis method based on improved quantum genetic algorithm optimized SVM

Country Status (1)

Country Link
CN (1) CN116167438A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117555287A (en) * 2024-01-12 2024-02-13 中国机械总院集团云南分院有限公司 CAE-based numerical control machine tool machining dynamic performance monitoring method and system

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117555287A (en) * 2024-01-12 2024-02-13 中国机械总院集团云南分院有限公司 CAE-based numerical control machine tool machining dynamic performance monitoring method and system
CN117555287B (en) * 2024-01-12 2024-04-09 中国机械总院集团云南分院有限公司 CAE-based numerical control machine tool machining dynamic performance monitoring method and system

Similar Documents

Publication Publication Date Title
CN111562108A (en) Rolling bearing intelligent fault diagnosis method based on CNN and FCMC
CN113312447B (en) Semi-supervised log anomaly detection method based on probability label estimation
CN112529341B (en) Drilling well leakage probability prediction method based on naive Bayesian algorithm
CN111598179B (en) Power monitoring system user abnormal behavior analysis method, storage medium and equipment
CN116304820B (en) Bearing fault type prediction method and system based on multi-source domain transfer learning
Yang et al. Enhanced hierarchical symbolic dynamic entropy and maximum mean and covariance discrepancy-based transfer joint matching with Welsh loss for intelligent cross-domain bearing health monitoring
CN116167438A (en) Transformer fault diagnosis method based on improved quantum genetic algorithm optimized SVM
CN111478314A (en) Transient stability assessment method for power system
CN114818809B (en) Fault diagnosis method for SCA-SVM motor rolling bearing based on cross wavelet
CN112714130A (en) Big data-based adaptive network security situation sensing method
CN115165366A (en) Variable working condition fault diagnosis method and system for rotary machine
CN108763926B (en) Industrial control system intrusion detection method with safety immunity capability
CN113343123B (en) Training method and detection method for generating confrontation multiple relation graph network
CN111260029A (en) Credibility analysis method for air quality data
CN116611003A (en) Transformer fault diagnosis method, device and medium
Chao et al. Research on network intrusion detection technology based on dcgan
CN116048036A (en) Fault detection method based on dynamic non-stationary projection structure
CN116150687A (en) Fluid pipeline leakage identification method based on multi-classification G-WLSTSVM model
CN115543702A (en) Multi-source solid state disk collaborative fault diagnosis method, system, equipment and medium
CN115659323A (en) Intrusion detection method based on information entropy theory and convolution neural network
CN110017989B (en) Method for diagnosing bearing fault of wind turbine
CN113657520A (en) Intrusion detection method based on deep confidence network and long-time and short-time memory network
Song et al. Research and Application on Anomaly Detection of Dynamic Baseline Performance Time Series Data Based on Machine Learning
Liu et al. Effective open intent classification with K-center contrastive learning and adjustable decision boundary
CN112883539A (en) Wind power transformer fault diagnosis method based on improved fuzzy clustering algorithm

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