CN116503710A - GIS partial discharge type identification method based on self-adaptive convolutional neural network - Google Patents
GIS partial discharge type identification method based on self-adaptive convolutional neural network Download PDFInfo
- Publication number
- CN116503710A CN116503710A CN202310408132.7A CN202310408132A CN116503710A CN 116503710 A CN116503710 A CN 116503710A CN 202310408132 A CN202310408132 A CN 202310408132A CN 116503710 A CN116503710 A CN 116503710A
- Authority
- CN
- China
- Prior art keywords
- partial discharge
- image
- layer
- discharge type
- self
- 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.)
- Withdrawn
Links
- 238000013527 convolutional neural network Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000004927 fusion Effects 0.000 claims description 14
- 238000011176 pooling Methods 0.000 claims description 13
- 210000002569 neuron Anatomy 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 238000013178 mathematical model Methods 0.000 claims description 3
- 238000003786 synthesis reaction Methods 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims 4
- 238000001514 detection method Methods 0.000 abstract description 7
- 238000002474 experimental method Methods 0.000 abstract description 3
- 230000007547 defect Effects 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 230000008901 benefit Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 239000012212 insulator Substances 0.000 description 3
- 238000007500 overflow downdraw method Methods 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 2
- 238000009413 insulation Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 239000002923 metal particle Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 239000000725 suspension Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000012567 pattern recognition method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1209—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing using acoustic measurements
-
- 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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
- G06V10/765—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Evolutionary Biology (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Acoustics & Sound (AREA)
- Feedback Control In General (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to the technical field of partial discharge identification of power equipment, in particular to a GIS partial discharge type identification method based on a self-adaptive convolutional neural network. The invention avoids the accidental of a single detection result, can automatically screen to obtain the optimal model parameters according to the change of the detection environment, avoids the holding of subjective factors or the low-efficiency repeated experiments, reduces the interference of external signals and improves the identification accuracy.
Description
Technical Field
The invention relates to the technical field of partial discharge identification of power equipment, in particular to a GIS partial discharge type identification method based on a self-adaptive convolutional neural network.
Background
The gas insulated switch (Gas Insulated Switchgear, GIS) is widely applied to the power system by virtue of the unique advantages of small occupied area, high operation reliability, convenient maintenance and the like. However, various defects occur in the process of manufacturing, transporting and assembling the GIS, and mainly include four types: corona discharge, suspended matter discharge, insulator surface defect discharge and free particle discharge, which may cause various forms of partial discharge, and further cause insulation failure or power system failure, so that GIS partial discharge type identification has important significance.
With the progress of intelligent algorithms and image recognition technologies, a GIS partial discharge type recognition method based on multi-information fusion becomes a trend of GIS partial discharge type recognition research at present. Non-patent literature (GIS partial discharge pattern recognition based on double-attention mechanism optimization CNN architecture) (publication month: 2022,37 (2): 22-28) discloses construction of a characteristic space formed by common fusion of a partial discharge ultra-high frequency PRPD spectrogram and ultrasonic gram angular field density distribution, characteristic extraction of the spectrogram and the distribution is carried out through a convolution neural network optimized by the double-attention mechanism, and result prediction is carried out by a Softmax classifier at the tail end of the network. Patent literature (application number: 202110326051.3) discloses a partial discharge pattern recognition method based on spectrum feature and information fusion, which is implemented by acquiring a discharge repetition rate feature matrix, slope coding feature integral feature, second order differential feature and the like in a partial discharge PRPD spectrum; constructing a map characteristic parameterization matrix of each partial discharge fault defect; inputting parameterized matrixes of the partial discharge fault defects into an information fusion model based on variable weight; calculating to obtain the type identification score result of each partial discharge fault defect; establishing a corresponding relation database between the type identification scoring area and the discharge type; calculating the type identification score of the partial discharge to be detected, inputting the score into a database, and outputting a corresponding partial discharge type judgment result. Patent literature (application number: 202010885616.7) discloses a GIS insulator defect identification method based on partial discharge multi-information fusion, which is characterized in that by detecting signals such as ultrahigh frequency and ultrasonic waves of partial discharge under the defect of a GIS insulator, effective characteristics (such as time domain waveform characteristics, power spectrum characteristics, map statistical characteristics and the like) of various information are extracted, and then the partial discharge types are identified by fusing the information characteristics. However, the feature level fusion related in the partial discharge type recognition method based on the multi-information fusion has certain requirements and high dependence on the quality and the variability of the input image, and when the signal is interfered by the outside, the singular phenomenon of the input image is caused, so that the phenomenon of the reduction of the recognition accuracy rate occurs.
In view of this, it is needed to find a new method for identifying the partial discharge type of the GIS based on multi-information fusion, which can reduce the interference signal and improve the identification accuracy.
Disclosure of Invention
In order to solve the technical problems in the prior art, the invention provides a GIS partial discharge type identification method based on a self-adaptive convolutional neural network.
In order to achieve the above purpose, the present invention is realized by the following technical scheme:
a GIS partial discharge type identification method based on a self-adaptive convolutional neural network comprises the following steps:
step 1: the UHF sensor and the ultrasonic signal sensor are used for respectively acquiring the ultrahigh frequency signals and the ultrasonic signals of different partial discharge models;
step 2: processing the ultrahigh frequency signal by adopting a partial discharge phase analysis method to obtain a PRPD image;
step 3: processing the ultrasonic signal by using a gram angle field to obtain a GAF image;
step 4: respectively inputting the PRPD image and the GAF image set into a CNN model based on a PSO algorithm, searching for optimal super parameters of the CNN model, and obtaining self-adaptive CNN models respectively corresponding to the PRPD image and the GAF image;
step 5: extracting features of the PRPD image and the GAF image through the self-adaptive CNN model, and classifying and identifying the partial discharge type to obtain an identification result of the self-adaptive CNN model;
step 6: and obtaining a category comprehensive value of the partial discharge type based on decision-level multi-information fusion through the comprehensive recognition rate function.
Further, the CNN model comprises an input layer, a convolution layer, a pooling layer, a full-connection layer and an output layer, the PRPD image and the GAF image respectively enter the convolution layer after passing through the input layer, then alternately enter the pooling layer and the convolution layer to extract features of the PRPD image and the GAF image, and finally, the full-connection layer is used for completing classification and identification and outputting classification results.
Further, the convolution layer convolution process is expressed as:
wherein:output of the jth neuron which is the kth layer; />An output for the ith neuron of the k-1 th layer; m is M j Is an input feature map; k is a k-th network; omega is a weight matrix; />Bias for the kth layer of jth neurons; sigma is the activation function.
Further, the mathematical model of the pooling layer is expressed as:
wherein: down () is a pooling function; beta is the network multiplicative bias.
Aiming at the characteristics of GIS partial discharge signal characteristic images, the invention adopts maximum value pooling to better exert the advantage of strong sparse characteristic extraction capability, and is more suitable for vibration signals.
Further, the integrated recognition rate function is expressed as:
wherein: c () is a category synthesis value; m and n are respectively different partial discharge types.
Compared with the prior art, the invention has the following beneficial effects:
(1) The invention fully excavates the signal image characteristics based on the CNN algorithm, automatically searches the optimal super parameters (such as the number of training samples, the learning rate, the iteration rounds and the like) of the GIS partial discharge type recognition model based on the CNN algorithm by utilizing the PSO algorithm, avoids the holding of subjective factors or the low-efficiency repeated experiments, and enhances the recognition efficiency;
(2) The decision-level multi-information fusion method provided by the invention has the advantages that the recognition results generated by two paths of signals are fused, the error recognition results generated by the singular images are removed, the influence of interference signals on the recognition results can be effectively reduced, the accuracy of the recognition results is ensured, and meanwhile, the accidental of single signal detection results is avoided.
(3) The identification method has stronger anti-interference capability, smaller communication quantity and smaller dependence on the requirements of the sensors, and the sensors are not necessarily required to be of the same type, so that the fusion cost is lower.
Drawings
FIG. 1 is a decision level multi-information fusion framework diagram;
FIG. 2 is a partial discharge model diagram;
fig. 3 is a schematic diagram of a partial discharge monitoring test.
Detailed Description
The present invention will be described more fully hereinafter in order to facilitate an understanding of the present invention. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Examples
The method comprises the following specific steps of constructing a typical architecture of a GIS partial discharge experiment operation platform, and carrying out GIS partial discharge type identification:
(1) 4 kinds of insulation defect models are designed for simulating partial discharge phenomena of GIS equipment, and the method comprises the following steps: hole discharge, metal particle discharge, suspension discharge, and corona discharge;
(2) The partial discharge defect model is placed in a test cavity, the UHF sensor and the ultrasonic signal sensor are used for respectively collecting the ultrahigh frequency signals and the ultrasonic signals of different partial discharge models, the ultrahigh frequency sensor is used for collecting the signals of 300 MHz-1.5 GHz, and the detection frequency of the ultrasonic signal sensor is 40kHz;
(3) Processing the ultrahigh frequency signal by adopting a partial discharge phase analysis method to obtain a PRPD image; processing the ultrasonic signal by using a gram angle field to obtain a GAF image;
(4) Respectively inputting the PRPD image and the GAF image set into a CNN model based on a PSO algorithm, searching for the optimal super parameters of the CNN model, and obtaining a self-adaptive CNN_1 model and a self-adaptive CNN_2 model;
the CNN model comprises an input layer, a convolution layer, a pooling layer, a full connection layer and an output layer, wherein a PRPD image and a GAF image respectively enter the convolution layer after passing through the input layer, then alternately enter the pooling layer and the convolution layer to extract characteristics of the PRPD image and the GAF image, and finally, the full connection layer is used for finishing classification and identification and outputting classification results;
the convolution layer convolution process is expressed as:
wherein:output of the jth neuron which is the kth layer; />Output for the (k-1) th layer (i) th neuron；M j Is an input feature map; k is a k-th network; omega is a weight matrix; />Bias for the kth layer of jth neurons; sigma is the activation function.
The mathematical model of the pooling layer is expressed as:
wherein: down () is a pooling function; beta is the network multiplicative bias.
(5) The PRPD image and the GAF image are respectively subjected to feature extraction through the self-adaptive CNN_1 model and the self-adaptive CNN_2 model, and the partial discharge type is classified and identified, so that identification results of the self-adaptive CNN_1 model and the self-adaptive CNN_2 model are obtained;
(6) Acquiring a category comprehensive value of the partial discharge type based on decision-level multi-information fusion through a comprehensive recognition rate function;
the integrated recognition rate function is expressed as:
wherein: c () is a category synthesis value; m and n are respectively different partial discharge types.
Recognition result: the GIS cavity discharge type identification accuracy based on decision-level multi-information fusion is highest and reaches 100%; the identification accuracy of corona discharge reaches 99%; the identification accuracy of the metal particle discharge and the suspension discharge is the lowest, but the identification accuracy is as high as 98%.
According to the invention, the situation that a single detection method is greatly influenced by the environment is considered, the multiple detection information results are fused, and the accuracy of the obtained GIS partial discharge type identification result is obviously improved. Compared with single detection methods such as an ultrahigh frequency method and an ultrasonic method and a characteristic level multi-information fusion method, the decision level information fusion method provided by the invention obtains the optimal value of the model super parameter through PSO algorithm optimization, obtains the self-adaptive convolutional neural network model and the optimal network layer number, avoids artificial experience setting or repeated attempts, and improves the model calculation efficiency and the recognition accuracy.
It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (5)
1. The GIS partial discharge type identification method based on the self-adaptive convolutional neural network is characterized by comprising the following steps of:
step 1: the UHF sensor and the ultrasonic signal sensor are used for respectively acquiring the ultrahigh frequency signals and the ultrasonic signals of different partial discharge models;
step 2: processing the ultrahigh frequency signal by adopting a partial discharge phase analysis method to obtain a PRPD image;
step 3: processing the ultrasonic signal by using a gram angle field to obtain a GAF image;
step 4: respectively inputting the PRPD image and the GAF image set into a CNN model based on a PSO algorithm, searching for optimal super parameters of the CNN model, and obtaining self-adaptive CNN models respectively corresponding to the PRPD image and the GAF image;
step 5: extracting features of the PRPD image and the GAF image through the self-adaptive CNN model, and classifying and identifying the partial discharge type to obtain an identification result of the self-adaptive CNN model;
step 6: and obtaining a category comprehensive value of the partial discharge type based on decision-level multi-information fusion through the comprehensive recognition rate function.
2. The GIS partial discharge type identification method based on the adaptive convolutional neural network according to claim 1, wherein the method comprises the following steps: the CNN model comprises an input layer, a convolution layer, a pooling layer, a full connection layer and an output layer, wherein the PRPD image and the GAF image respectively enter the convolution layer after passing through the input layer, then enter the pooling layer and the convolution layer alternately to extract the characteristics of the PRPD image and the GAF image, and finally, the full connection layer is used for completing classification and identification and outputting classification results.
3. The GIS partial discharge type identification method based on the adaptive convolutional neural network as set forth in claim 2, wherein the method is characterized in that: the convolution layer convolution process is expressed as:
wherein:output of the jth neuron which is the kth layer; a, a i k-1 An output for the ith neuron of the k-1 th layer; m is M j Is an input feature map; k is a k-th network; omega is a weight matrix; />Bias for the kth layer of jth neurons; sigma is the activation function.
4. The GIS partial discharge type identification method based on the adaptive convolutional neural network as set forth in claim 2, wherein the method is characterized in that: the mathematical model of the pooling layer is expressed as:
wherein: down () is a pooling function; beta is the network multiplicative bias.
5. The GIS partial discharge type identification method based on the adaptive convolutional neural network according to claim 1, wherein the method comprises the following steps: the integrated recognition rate function is expressed as:
wherein: c () is a category synthesis value; m and n are respectively different partial discharge types.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310408132.7A CN116503710A (en) | 2023-04-17 | 2023-04-17 | GIS partial discharge type identification method based on self-adaptive convolutional neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310408132.7A CN116503710A (en) | 2023-04-17 | 2023-04-17 | GIS partial discharge type identification method based on self-adaptive convolutional neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116503710A true CN116503710A (en) | 2023-07-28 |
Family
ID=87327732
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310408132.7A Withdrawn CN116503710A (en) | 2023-04-17 | 2023-04-17 | GIS partial discharge type identification method based on self-adaptive convolutional neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116503710A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117347796A (en) * | 2023-09-28 | 2024-01-05 | 国网四川省电力公司电力科学研究院 | Intelligent gateway-based switching equipment partial discharge diagnosis system and method |
-
2023
- 2023-04-17 CN CN202310408132.7A patent/CN116503710A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117347796A (en) * | 2023-09-28 | 2024-01-05 | 国网四川省电力公司电力科学研究院 | Intelligent gateway-based switching equipment partial discharge diagnosis system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112327219B (en) | Distribution transformer fault diagnosis method with automatic feature mining and parameter automatic optimizing functions | |
| CN108765373B (en) | Insulator abnormity automatic detection method based on integrated classifier online learning | |
| CN103076547B (en) | Method for identifying GIS (Gas Insulated Switchgear) local discharge fault type mode based on support vector machines | |
| CN109932627A (en) | A kind of localization method and system of GIS pressure test shelf depreciation | |
| CN110929847A (en) | Converter transformer fault diagnosis method based on deep convolutional neural network | |
| CN109061426B (en) | Transformer partial discharge fault diagnosis method and online monitoring device | |
| CN112686093A (en) | Fusion partial discharge type identification method based on DS evidence theory | |
| CN103558519A (en) | GIS partial discharge ultrasonic signal identification method | |
| CN116503710A (en) | GIS partial discharge type identification method based on self-adaptive convolutional neural network | |
| CN111008641B (en) | Power transmission line tower external force damage detection method based on convolutional neural network | |
| CN114417926A (en) | Power equipment partial discharge pattern recognition method and system based on deep convolution generation countermeasure network | |
| CN116229380A (en) | Method for identifying bird species related to bird-related faults of transformer substation | |
| CN113541834B (en) | Abnormal signal semi-supervised classification method and system and data processing terminal | |
| CN111025100A (en) | Transformer ultrahigh frequency partial discharge signal mode identification method and device | |
| CN108304567A (en) | High-tension transformer regime mode identifies and data classification method and system | |
| CN115600088A (en) | Distribution transformer fault diagnosis method based on vibration signals | |
| CN117076955A (en) | Fault detection method and system for high-voltage frequency converter | |
| CN113076920A (en) | Intelligent fault diagnosis method based on asymmetric domain confrontation self-adaptive model | |
| CN116452542A (en) | GIS partial discharge defect diagnosis method based on nerve supervision decision tree | |
| CN112200000A (en) | Welding stability recognition model training method and welding stability recognition method | |
| CN115526258A (en) | Power system transient stability evaluation method based on Spearman correlation coefficient feature extraction | |
| CN115015719A (en) | Sleeve partial discharge recognition algorithm based on optical fiber ultrasonic sensing signal | |
| CN114563671A (en) | High-voltage cable partial discharge diagnosis method based on CNN-LSTM-Attention neural network | |
| CN117031194B (en) | Ultrasonic hidden danger detection method and system for power distribution network | |
| CN112883639A (en) | GIS equipment service life prediction device and method based on machine learning |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230728 |