CN116091501B - Method, device, equipment and medium for identifying partial discharge type of high-voltage electrical equipment - Google Patents
Method, device, equipment and medium for identifying partial discharge type of high-voltage electrical equipment Download PDFInfo
- Publication number
- CN116091501B CN116091501B CN202310367157.7A CN202310367157A CN116091501B CN 116091501 B CN116091501 B CN 116091501B CN 202310367157 A CN202310367157 A CN 202310367157A CN 116091501 B CN116091501 B CN 116091501B
- Authority
- CN
- China
- Prior art keywords
- image data
- discharge
- historical
- partial discharge
- discharge type
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000013210 evaluation model Methods 0.000 claims abstract description 30
- 238000012423 maintenance Methods 0.000 claims abstract description 13
- 238000010586 diagram Methods 0.000 claims description 25
- 238000004422 calculation algorithm Methods 0.000 claims description 20
- 238000002474 experimental method Methods 0.000 claims description 18
- 238000001914 filtration Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 13
- 230000004927 fusion Effects 0.000 claims description 10
- 238000003062 neural network model Methods 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 239000000463 material Substances 0.000 claims description 6
- 238000003702 image correction Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 abstract description 5
- 238000012545 processing Methods 0.000 abstract description 5
- 230000008030 elimination Effects 0.000 abstract description 3
- 238000003379 elimination reaction Methods 0.000 abstract description 3
- 238000004891 communication Methods 0.000 description 7
- 230000007547 defect Effects 0.000 description 4
- 238000009413 insulation Methods 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- 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
- G01R31/1218—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 optical methods; using charged particle, e.g. electron, beams or X-rays
-
- 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
- G01R31/1227—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 of components, parts or materials
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- 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
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
- G06V10/54—Extraction of image or video features relating to texture
-
- 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
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
-
- 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)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Testing Relating To Insulation (AREA)
Abstract
The invention relates to the technical field of electric variable measurement, in particular to a method, a device, equipment and a medium for identifying the partial discharge type of high-voltage electric equipment, wherein the method comprises the following steps: acquiring partial discharge signal data images fed back by a partial discharge signal collector; image processing to obtain second image data; extracting a feature set in the second image data; inputting the feature set into a discharge type evaluation model to obtain a first discharge type corresponding to the first image data, carrying out definition enhancement (noise elimination) on the effective image data, extracting image features to obtain contour feature data and texture feature data which can represent partial discharge detail information, combining the trained discharge type evaluation model to obtain the discharge type corresponding to the partial discharge signal data image, further realizing partial discharge measurement and discharge type identification of the power equipment, enabling relevant power maintenance personnel to be free from accumulating relevant identification experience, and reducing talent culture cost.
Description
Technical Field
The invention relates to the technical field of electric variable measurement, in particular to a method, a device, equipment and a medium for identifying partial discharge type of high-voltage electric equipment.
Background
In an electrical power system, insulation defect detection of electrical power equipment, particularly high voltage equipment, is critical to improving safe operation of the electrical power system. When high voltage equipment has insulation defects, partial discharge phenomenon often occurs. Partial discharge refers to a phenomenon in which a discharge occurs in a partial region of an insulating medium in a high-voltage apparatus, but the discharge does not penetrate between conductors to which a voltage is applied. Although the partial discharge signal is weak, the partial discharge signal contains a large amount of insulation defect information, and the type of the insulation defect which causes the partial discharge can be determined by carrying out pattern recognition or discharge type recognition on the partial discharge signal, so that convenience is brought to subsequent maintenance.
The partial discharge of the existing high-voltage power equipment can easily obtain corresponding discharge signal image data through a special partial discharge signal collector, but the existing recognition of the signal image still needs experienced technicians/specialists to judge the corresponding discharge type, so that the culture cost of maintenance personnel is increased, and a new idea is provided for solving the problem along with the popularization of image recognition and deep learning algorithms.
Disclosure of Invention
The invention aims to provide a method, a device and equipment for identifying partial discharge type of high-voltage electrical equipment and a readable storage medium, so as to solve the problem that the manually identified discharge signal image data causes higher culture cost of related power maintenance personnel.
In order to achieve the above purpose, the embodiment of the present application provides the following technical solutions:
in one aspect, an embodiment of the present application provides a method for identifying a partial discharge type of a high-voltage electrical apparatus, where the method includes: acquiring partial discharge signal data images fed back by a partial discharge signal collector, and recording the partial discharge signal data images as first image data, wherein the partial discharge signal collector is used for collecting discharge signals of power equipment; judging the equipment temperature of the partial discharge signal collector, under the condition that the equipment temperature is in a first temperature difference range, enabling the expansion convolution of the first image data to highlight noise characteristics in the first image data through long-path fusion shallow layer and deep layer information in a characteristic enhancement module, removing peak noise in the first image data through wavelet hard threshold filtering to obtain second image data, wherein the first temperature difference range is the normal working temperature of the partial discharge signal collector and is used for guaranteeing the signal collection precision of the collector; extracting a feature set in the second image data, wherein the feature set comprises contour features and texture features of the second image data; and constructing a discharge type evaluation model, inputting the feature set into the discharge type evaluation model to obtain a first discharge type corresponding to the first image data, wherein the discharge type evaluation model is a BP neural network algorithm for judging the discharge type corresponding to the image data according to the contour features and the texture features in the image data.
Optionally, after the determining the device temperature of the partial discharge signal collector, the method further includes:
if the equipment temperature is not in the first temperature difference range, finding a temperature difference compensation coefficient corresponding to the equipment temperature according to historical temperature difference experiment compensation data, wherein the historical temperature difference experiment data is a distortion compensation coefficient of a collector under different recorded experiment environment temperatures;
correcting the first image data through a temperature compensation coefficient, enabling the expansion convolution of the corrected first image data to highlight noise characteristics in the first image data through long-path fusion shallow layer and deep layer information in a characteristic enhancement module, and removing peak noise in the first image data through wavelet hard threshold filtering to obtain second image data.
Optionally, the constructing the discharge type evaluation model includes:
acquiring first data, wherein the first data comprises historical second image data collected by a plurality of partial discharge signal collectors and corresponding discharge types; further obtaining a historical second image data set corresponding to each discharge type;
and training the BP neural network model based on the historical second image data sets of all the discharge types to obtain a trained model, and recording the trained model as a discharge type evaluation model.
Optionally, after the obtaining the first discharge type corresponding to the first image data, the method further includes:
obtaining a historical occurrence frequency distribution map corresponding to each discharge type based on historical acquisition data of all partial discharge signal collectors in a detection area, wherein the historical acquisition data comprises position information, discharge time and discharge types of power equipment, and the historical occurrence frequency distribution map reflects corresponding discharge positions, discharge time and discharge times of the same discharge type;
clustering a plurality of partial discharge signal collectors with close discharge positions in the historical occurrence frequency distribution map based on a distance type clustering algorithm to obtain a plurality of partial historical occurrence frequency distribution maps, and marking the partial historical occurrence frequency distribution maps as a second distribution map;
acquiring historical weather information and predicted weather information of a geographic area corresponding to the second distribution diagram, wherein the historical weather information comprises temperature, humidity and air pressure values;
based on the historical weather information, the second distribution diagram and the future weather information, predicting by using a Kalman filtering algorithm and a differential autoregressive moving average prediction model to obtain a certain type of discharge frequency of the power equipment in the geographic area corresponding to the second distribution diagram in a first future time period;
and generating a corresponding maintenance bill of materials according to the predicted discharge frequency.
In a second aspect, the present embodiment provides a partial discharge type identifying apparatus for a high-voltage electrical apparatus, the apparatus including:
the first acquisition module is used for acquiring partial discharge signal data images fed back by the partial discharge signal acquisition device and recording the partial discharge signal data images as first image data, and the partial discharge signal acquisition device is used for acquiring discharge signals of the power equipment;
the first calculation module is used for judging the equipment temperature of the partial discharge signal collector, and under the condition that the equipment temperature is in a first temperature difference range, the expansion convolution of the first image data is used for highlighting noise characteristics in the first image data through long-path fusion shallow layer and deep layer information in the characteristic enhancement module, and removing peak noise in the first image data through wavelet hard threshold filtering to obtain second image data, wherein the first temperature difference range is the normal working temperature of the partial discharge signal collector and is used for guaranteeing the signal collection precision of the collector;
the feature extraction module is used for extracting a feature set in the second image data, wherein the feature set comprises contour features and texture features of the second image data;
the second calculation module is used for constructing a discharge type evaluation model, inputting the feature set into the discharge type evaluation model to obtain a first discharge type corresponding to the first image data, wherein the discharge type evaluation model is a BP neural network algorithm for judging the discharge type corresponding to the image data according to the contour features and the texture features in the image data.
Optionally, the first computing module further includes:
the third calculation unit is used for judging that if the equipment temperature is not in the first temperature difference range, finding a temperature difference compensation coefficient corresponding to the equipment temperature according to historical temperature difference experiment compensation data, wherein the historical temperature difference experiment data is a distortion compensation coefficient of a collector under different recorded experiment environment temperatures;
the image correction unit is used for correcting the first image data through the temperature compensation coefficient, enabling the expansion convolution of the corrected first image data to highlight noise characteristics in the first image data through long-path fusion shallow layer and deep layer information in the characteristic enhancement module, and removing peak noise in the first image data through wavelet hard threshold filtering to obtain second image data.
Optionally, the second computing module includes:
the first acquisition unit is used for acquiring first data, wherein the first data comprises historical second image data collected by the partial discharge signal collectors and corresponding discharge types; further obtaining a historical second image data set corresponding to each discharge type;
the model training unit is used for training the BP neural network model based on the historical second image data sets of all the discharge types to obtain a trained model, and the trained model is recorded as a discharge type evaluation model.
Optionally, the high-voltage electrical equipment partial discharge type identification device further includes:
the first acquisition module is used for acquiring a historical occurrence frequency distribution diagram corresponding to each discharge type based on historical acquisition data of all partial discharge signal collectors in the detection area, wherein the historical acquisition data comprises position information, discharge time and discharge types of the power equipment, and the historical occurrence frequency distribution diagram reflects corresponding discharge positions, discharge time and discharge times of the same discharge type;
the third calculation module is used for collecting a plurality of partial discharge signal collectors with close discharge positions in the historical occurrence frequency distribution map based on a distance clustering algorithm to obtain a plurality of partial historical occurrence frequency distribution maps, and marking the partial historical occurrence frequency distribution maps as a second distribution map;
the second acquisition module is used for acquiring historical weather information and predicted weather information of a geographic area corresponding to the second distribution diagram, wherein the historical weather information comprises temperature, humidity and air pressure values;
the fourth calculation module is used for predicting and obtaining a certain type of discharge frequency of the power equipment in the geographic area corresponding to the second distribution diagram in a first future time period by utilizing a Kalman filtering algorithm and a differential autoregressive moving average prediction model based on the historical weather information, the second distribution diagram and the future weather information;
and the consumable prediction module is used for generating a corresponding maintenance bill of materials according to the predicted discharge frequency of the corresponding type.
In a third aspect, embodiments of the present application provide a high voltage electrical apparatus partial discharge type identification apparatus, the apparatus comprising a memory and a processor.
The memory is used for storing a computer program; the processor is used for executing the computer program to realize the steps of the method for identifying the partial discharge type of the high-voltage electrical equipment.
In a fourth aspect, embodiments of the present application provide a medium having stored thereon a computer program which, when executed by a processor, implements the steps of the above-described method for identifying a partial discharge type of a high-voltage electrical apparatus.
The beneficial effects of the invention are as follows:
according to the partial discharge type identification method for the high-voltage electrical equipment, when the partial discharge signal data image fed back by the partial discharge signal collector is acquired, the working temperature of the corresponding partial discharge signal collector is considered, when the working temperature is within the preset reasonable temperature difference range, the partial discharge signal data image which is subjected to feedback distortion acquisition only can be judged as effective image data by a system, the effective image data image is eliminated, the definition enhancement (noise elimination) and the image feature extraction are carried out to obtain the contour feature data and the texture feature data which can represent the partial discharge detail information in combination with the trained discharge type assessment model, the discharge type corresponding to the partial discharge signal data image is obtained, the partial discharge measurement and the discharge type identification of the electrical equipment are further realized, no artificial participation is required in the whole process, the relevant identification experience is not accumulated by relevant power maintenance personnel, and the talent culture cost is reduced.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the embodiments of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for identifying partial discharge type of high-voltage electrical equipment according to an embodiment of the invention;
FIG. 2 is a schematic diagram of a partial discharge type recognition device for high-voltage electrical equipment according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a partial discharge type identification device for a high-voltage electrical device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that: like reference numerals or letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Before the explanation, a brief description needs to be made on the distribution of collectors and the distribution situation of the power equipment, a fixed number of test specimens are randomly selected from the power equipment in an area, corresponding collectors are arranged on the specimens to realize the implementation detection of the belt equipment, and then the specific types of the power equipment to be monitored are the same, such as transformers, cables, transformer boxes and the like, wherein the embodiment takes a high-voltage transformer as an explanation object, and the other power equipment can realize the identification of the partial discharge type of the same power equipment according to the related principles disclosed by the embodiment, and the description is not related.
Example 1
As shown in fig. 1, the present embodiment provides a method for identifying a partial discharge type of a high-voltage electrical apparatus, which includes steps S1, S2, S3 and S4.
Step S1, obtaining partial discharge signal data images fed back by a partial discharge signal collector, and recording the partial discharge signal data images as first image data, wherein the partial discharge signal collector is used for collecting discharge signals of power equipment;
s2, in order to ensure that the partial discharge signal data fed back by the partial discharge signal collector are highly accurate, the equipment temperature of the collector needs to be primarily judged, and when the equipment temperature is in a normal range (a first temperature difference range), the first image data is further processed, wherein the specific processing mode is to enable the expansion convolution of the first image data to highlight noise characteristics in the first image data through long-path fusion shallow layer and deep layer information in a characteristic enhancement module, and remove peak noise in the first image data through wavelet hard threshold filtering, so that the fluctuation textures or contours of a plurality of peaks in the first image data are more clear to prepare for the extraction of the contour characteristics and texture characteristics of the next step, and second image data is obtained, wherein the first temperature difference range is the normal working temperature of the partial discharge signal collector and is used for ensuring the signal acquisition precision of the collector;
s3, extracting contour features and texture features in the second image data, wherein contour features and texture feature extraction algorithms in the picture are all of the prior art, and detailed description of the embodiment is omitted herein;
s4, constructing a discharge type evaluation model, and inputting the feature set into the discharge type evaluation model to obtain a first discharge type corresponding to first image data, wherein the discharge type evaluation model is a BP neural network algorithm for judging the discharge type corresponding to the image data according to contour features and texture features in the image data;
the specific construction mode of the discharge type evaluation model may be:
s41, acquiring first data, wherein the first data comprises historical second image data collected by a plurality of partial discharge signal collectors and corresponding discharge types, classifying the first data according to the discharge types to obtain historical second image data sets corresponding to each discharge type, so that a BP neural network model can independently learn the historical second image data sets of each discharge type, the model training time and the required number of the historical second image data sets are shortened, and particularly the number of the historical second image data sets is limited and the demand of the BP neural network model is large, therefore, the training mode is improved, and the value of the historical second image data sets can be fully exerted;
s42, training the BP neural network model based on the historical second image data sets of all the discharge types to obtain a trained model, and recording the trained model as a discharge type evaluation model, specifically, firstly, putting each discharge type into the BP neural network model for training, then randomly extracting the historical second image data for error correction reinforcement training until the BP neural network model can successfully classify all the second image data corresponding to the multi-type discharge types in the test group, and terminating the training.
In summary, it can be seen that in embodiment 1, when the partial discharge signal data image fed back by the partial discharge signal collector is obtained, the working temperature of the corresponding partial discharge signal collector is considered, and when the working temperature is within the preset reasonable temperature difference range, the system determines that the partial discharge signal data image is effective image data, and the contour feature data and the texture feature data capable of representing the partial discharge detail information are obtained by performing definition enhancement (noise elimination) and image feature extraction on the effective image data, and combined with a trained discharge type evaluation model, so as to obtain the discharge type corresponding to the partial discharge signal data image, thereby realizing partial discharge measurement and discharge type identification of the power equipment, avoiding the whole process from artificial participation, enabling relevant power maintenance personnel to not need to accumulate relevant identification experience, and reducing talent cultivation cost.
Example 2
The present embodiment is based on embodiment 1, and is further described in step S2, when the partial discharge signal collector is at an abnormal temperature (no longer within the first temperature difference range), for the processing mode of the collected partial discharge signal data image, since the characteristic configuration of the image data is simpler, a single longitudinal amplitude coefficient may be adopted as the compensation coefficient, and for the specific confirmation mode of the compensation coefficient, a multi-gradient temperature experiment side may be adopted, specifically: the measured same partial discharge signal collector collects a plurality of partial discharge signal data images corresponding to the same stable discharge device detected at different temperatures, and then a temperature compensation coefficient at different temperatures is determined, so that the partial discharge signal data image at abnormal temperatures is close to the partial discharge signal data image at normal temperatures as much as possible.
After obtaining the compensation coefficients at different temperatures, the compensation/correction method for the partial discharge signal data image acquired when the equipment temperature is not in the first temperature difference range may be as follows:
s21, if the equipment temperature is not in the first temperature difference range, finding a temperature difference compensation coefficient corresponding to the equipment temperature according to historical temperature difference experiment compensation data, wherein the historical temperature difference experiment data are distortion compensation coefficients of collectors under different experiment environment temperatures;
s22, correcting the first image data through a temperature compensation coefficient, enabling the expansion convolution of the corrected first image data to be integrated with shallow and deep information through a long path in a characteristic enhancement module to highlight noise characteristics in the first image data, and removing peak noise in the first image data through wavelet hard threshold filtering to obtain second image data.
Example 3
Before the explanation, a brief description needs to be made on the distribution of the collectors and the distribution situation of the power equipment, the collectors are arranged in a mode that a fixed number of monitoring specimens are selected from the power equipment in one area at first, the corresponding collectors are arranged on the specimens so as to realize indirect monitoring of all the power equipment of the same type in the whole area, the specific types of the power equipment need to be the same, such as a transformer, a cable, a transformer box and the like, wherein the embodiment takes a high-voltage transformer as an illustration object, and the other power equipment can realize the identification of the partial discharge type of the same power equipment according to the related principles disclosed in the embodiment, and the description is not related;
after the first discharge type corresponding to the first image data is obtained, the historical discharge data can be further analyzed and utilized to reduce the redundancy of the post-maintenance system, specifically:
s5, obtaining a historical occurrence frequency distribution map corresponding to each discharge type based on historical acquisition data of all partial discharge signal collectors in a detection area, wherein the historical acquisition data comprises position information, discharge time and discharge types of power equipment, and the historical occurrence frequency distribution map reflects corresponding discharge positions, discharge time and discharge times of the same discharge type;
s6, collecting a plurality of partial discharge signal collectors with close discharge positions in the historical occurrence frequency distribution map based on a distance clustering algorithm to obtain a plurality of partial historical occurrence frequency distribution maps, and marking the partial historical occurrence frequency distribution maps as a second distribution map;
s7, acquiring historical weather information and predicted weather information of a geographical area corresponding to the second distribution diagram, wherein the historical weather information comprises temperature, humidity and air pressure values;
s8, based on the historical weather information, the second distribution diagram and the future weather information, predicting to obtain a certain type of discharge frequency of the power equipment in the geographic area corresponding to the second distribution diagram in a first future time period by using a Kalman filtering algorithm and a differential autoregressive moving average prediction model;
and S9, generating a corresponding maintenance bill of materials according to the predicted discharge frequency.
Example 4
As shown in fig. 2, the present embodiment provides a partial discharge type recognition apparatus for a high-voltage electrical apparatus, the apparatus including:
a first acquisition module 71, configured to acquire a partial discharge signal data image fed back by a partial discharge signal collector, which is used to collect a discharge signal of the power device, and record the partial discharge signal data image as first image data;
a first calculation module 72, configured to determine a device temperature of the partial discharge signal collector, and in case that the device temperature is within a first temperature difference range, highlight noise characteristics in the first image data by fusing information of shallow layers and deep layers through long paths in the characteristic enhancement module by using expansion convolution of the first image data, and remove peak noise in the first image data through wavelet hard threshold filtering, so as to obtain second image data, where the first temperature difference range is a normal working temperature of the partial discharge signal collector, and is used to ensure signal collection accuracy of the collector;
a feature extraction module 73, configured to extract a feature set in the second image data, where the feature set includes a contour feature and a texture feature of the second image data;
the second calculation module 74 is configured to construct a discharge type evaluation model, and input the feature set into the discharge type evaluation model to obtain a first discharge type corresponding to the first image data, where the discharge type evaluation model is a BP neural network algorithm for determining the discharge type corresponding to the image data according to the contour feature and the texture feature in the image data.
Optionally, the first computing module 72 further includes:
a third calculation unit 721, configured to determine that if the device temperature is not within the first temperature difference range, find a temperature difference compensation coefficient corresponding to the device temperature according to historical temperature difference experiment compensation data, where the historical temperature difference experiment data is a distortion compensation coefficient of the collector under different experimental environment temperatures;
the image correction unit 722 is configured to correct the first image data by using a temperature compensation coefficient, and perform dilation convolution on the corrected first image data to highlight noise characteristics in the first image data by using long-path fusion shallow layer and deep layer information in the characteristic enhancement module, and remove peak noise in the first image data by using wavelet hard threshold filtering to obtain second image data.
Optionally, the second computing module 74 includes:
a first acquiring unit 741, configured to acquire first data, where the first data includes historical second image data collected by the plurality of partial discharge signal collectors and a corresponding discharge type; classifying the first data according to discharge types to obtain a historical second image data set corresponding to each discharge type;
the model training unit 742 is configured to train the BP neural network model based on the historical second image data sets of all the discharge types, and obtain a trained model, which is denoted as a discharge type evaluation model.
Optionally, the high-voltage electrical equipment partial discharge type identification device further includes:
a first acquisition module 75, configured to obtain a historical occurrence frequency distribution map corresponding to each discharge type based on historical acquisition data of all partial discharge signal collectors in the detection area, where the historical acquisition data includes position information, discharge time and discharge type of the power device, and the historical occurrence frequency distribution map reflects corresponding discharge positions, discharge times and discharge times of the same discharge type;
a third calculation module 76, configured to aggregate a plurality of partial discharge signal collectors with adjacent discharge positions in the historical occurrence frequency distribution map based on a clustering algorithm of distance class, to obtain a plurality of partial historical occurrence frequency distribution maps, and record the partial historical occurrence frequency distribution maps as a second distribution map;
a second obtaining module 77, configured to obtain historical weather information and predicted weather information of a geographical area corresponding to the second distribution diagram, where the historical weather information includes temperature, humidity and barometric pressure values;
a fourth calculation module 78, configured to predict, based on the historical weather information, the second distribution diagram and the future weather information, a certain type of discharge frequency of the power equipment in the geographic area corresponding to the second distribution diagram in a first future period of time by using a kalman filtering algorithm and a differential autoregressive moving average prediction model;
the consumable predicting module 79 is configured to generate a corresponding maintenance bill of materials according to the predicted discharge frequency of the corresponding type.
It should be noted that, regarding the apparatus in the above embodiments, the specific manner in which the respective modules perform the operations has been described in detail in the embodiments regarding the method, and will not be described in detail herein.
Example 5
Corresponding to the above method embodiments, the present disclosure also provides a high-voltage electrical apparatus partial discharge type recognition apparatus, and a high-voltage electrical apparatus partial discharge type recognition apparatus described below and a high-voltage electrical apparatus partial discharge type recognition method described above may be referred to correspondingly to each other.
Fig. 3 is a block diagram illustrating a high voltage electrical device partial discharge type identification device 800 according to an example embodiment. As shown in fig. 3, the electronic device 800 may include: a processor 801, a memory 802. The electronic device 800 may also include one or more of a multimedia component 803, an input/output (I/O) interface 804, and a communication component 805.
The processor 801 is configured to control the overall operation of the electronic device 800 to perform all or part of the steps in the above-described method for identifying a partial discharge type of a high-voltage electrical device. The memory 402 is used to store various types of data to support operation on the electronic device 800, which may include, for example, instructions for any application or method operating on the electronic device 800, as well as application-related data, such as contact data, messages sent and received, pictures, audio, video, and so forth. The Memory 802 may be implemented by any type or combination of volatile or non-volatile Memory devices, such as static random access Memory (Static Random Access Memory, SRAM for short), electrically erasable programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory, EEPROM for short), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM for short), programmable Read-Only Memory (Programmable Read-Only Memory, PROM for short), read-Only Memory (ROM for short), magnetic Memory, flash Memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and an audio component. Wherein the screen may be, for example, a touch screen, the audio component being for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or transmitted through the communication component 805. The audio assembly further comprises at least one speaker for outputting audio signals. The I/O interface 804 provides an interface between the processor 801 and other interface modules, which may be a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the electronic device 800 and other devices. Wireless communication, such as Wi-Fi, bluetooth, near field communication (Near FieldCommunication, NFC for short), 2G, 3G or 4G, or a combination of one or more thereof, the respective communication component 805 may thus comprise: wi-Fi module, bluetooth module, NFC module.
In an exemplary embodiment, the electronic device 800 may be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, abbreviated ASIC), digital signal processor (DigitalSignal Processor, abbreviated DSP), digital signal processing device (Digital Signal Processing Device, abbreviated DSPD), programmable logic device (Programmable Logic Device, abbreviated PLD), field programmable gate array (Field Programmable Gate Array, abbreviated FPGA), controller, microcontroller, microprocessor, or other electronic components for performing the high voltage electrical device partial discharge type identification method described above.
In another exemplary embodiment, a computer readable storage medium is also provided, comprising program instructions which, when executed by a processor, implement the steps of the above-described method for identifying a partial discharge type of a high voltage electrical apparatus. For example, the computer readable storage medium may be the memory 802 described above including program instructions executable by the processor 801 of the electronic device 800 to perform the high voltage electrical device partial discharge type identification method described above.
Example 6
Corresponding to the above method embodiments, the present disclosure further provides a readable storage medium, and a readable storage medium described below and a high-voltage electrical apparatus partial discharge type identification method described above may be referred to correspondingly with each other.
A readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the high voltage electrical apparatus partial discharge type identification method of the above method embodiments.
The readable storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, and the like.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method for identifying partial discharge type of high-voltage electrical equipment, the method comprising:
acquiring partial discharge signal data images fed back by a partial discharge signal collector, and recording the partial discharge signal data images as first image data, wherein the partial discharge signal collector is used for collecting discharge signals of power equipment;
judging the equipment temperature of the partial discharge signal collector, under the condition that the equipment temperature is in a first temperature difference range, enabling the expansion convolution of the first image data to highlight noise characteristics in the first image data through long-path fusion shallow layer and deep layer information in a characteristic enhancement module, removing peak noise in the first image data through wavelet hard threshold filtering to obtain second image data, wherein the first temperature difference range is the normal working temperature of the partial discharge signal collector and is used for guaranteeing the signal collection precision of the collector;
extracting a feature set in the second image data, wherein the feature set comprises contour features and texture features of the second image data;
and constructing a discharge type evaluation model, inputting the feature set into the discharge type evaluation model to obtain a first discharge type corresponding to the first image data, wherein the discharge type evaluation model is a BP neural network algorithm for judging the discharge type corresponding to the image data according to the contour features and the texture features in the image data.
2. The method for identifying a partial discharge type of a high-voltage electrical apparatus according to claim 1, wherein after said determining an apparatus temperature of the partial discharge signal collector, further comprising:
if the equipment temperature is not in the first temperature difference range, finding a temperature difference compensation coefficient corresponding to the equipment temperature according to historical temperature difference experiment compensation data, wherein the historical temperature difference experiment data is a distortion compensation coefficient of a collector under different recorded experiment environment temperatures;
correcting the first image data through a temperature compensation coefficient, enabling the expansion convolution of the corrected first image data to highlight noise characteristics in the first image data through long-path fusion shallow layer and deep layer information in a characteristic enhancement module, and removing peak noise in the first image data through wavelet hard threshold filtering to obtain second image data.
3. The method for identifying a partial discharge type of a high-voltage electric device according to claim 1, wherein the constructing a discharge type evaluation model includes:
acquiring first data, wherein the first data comprises historical second image data collected by a plurality of partial discharge signal collectors and corresponding discharge types; classifying the first data according to discharge types to obtain a historical second image data set corresponding to each discharge type;
and training the BP neural network model based on the historical second image data sets of all the discharge types to obtain a trained model, and recording the trained model as a discharge type evaluation model.
4. The method for identifying a partial discharge type of a high-voltage electrical apparatus according to claim 1, wherein after obtaining the first discharge type corresponding to the first image data, further comprises:
obtaining a historical occurrence frequency distribution map corresponding to each discharge type based on historical acquisition data of all partial discharge signal collectors in a detection area, wherein the historical acquisition data comprises position information, discharge time and discharge types of power equipment, and the historical occurrence frequency distribution map reflects corresponding discharge positions, discharge time and discharge times of the same discharge type;
clustering a plurality of partial discharge signal collectors with close discharge positions in the historical occurrence frequency distribution map based on a distance type clustering algorithm to obtain a plurality of partial historical occurrence frequency distribution maps, and marking the partial historical occurrence frequency distribution maps as a second distribution map;
acquiring historical weather information and predicted weather information of a geographic area corresponding to the second distribution diagram, wherein the historical weather information comprises temperature, humidity and air pressure values;
based on the historical weather information, the second distribution diagram and the future weather information, predicting by using a Kalman filtering algorithm and a differential autoregressive moving average prediction model to obtain a certain type of discharge frequency of power equipment in a geographic area corresponding to the second distribution diagram in a first future time period;
and generating a corresponding maintenance bill of materials according to the predicted discharge frequency.
5. A high voltage electrical apparatus partial discharge type recognition device, the device comprising:
the first acquisition module is used for acquiring partial discharge signal data images fed back by the partial discharge signal acquisition device and recording the partial discharge signal data images as first image data, and the partial discharge signal acquisition device is used for acquiring discharge signals of the power equipment;
the first calculation module is used for judging the equipment temperature of the partial discharge signal collector, and under the condition that the equipment temperature is in a first temperature difference range, the expansion convolution of the first image data is used for highlighting noise characteristics in the first image data through long-path fusion shallow layer and deep layer information in the characteristic enhancement module, and removing peak noise in the first image data through wavelet hard threshold filtering to obtain second image data, wherein the first temperature difference range is the normal working temperature of the partial discharge signal collector and is used for guaranteeing the signal collection precision of the collector;
the feature extraction module is used for extracting a feature set in the second image data, wherein the feature set comprises contour features and texture features of the second image data;
the second calculation module is used for constructing a discharge type evaluation model, inputting the feature set into the discharge type evaluation model to obtain a first discharge type corresponding to the first image data, wherein the discharge type evaluation model is a BP neural network algorithm for judging the discharge type corresponding to the image data according to the contour features and the texture features in the image data.
6. The apparatus for identifying a partial discharge type of a high-voltage electric device according to claim 5, wherein the first calculation module further comprises:
the third calculation unit is used for judging that if the equipment temperature is not in the first temperature difference range, finding a temperature difference compensation coefficient corresponding to the equipment temperature according to historical temperature difference experiment compensation data, wherein the historical temperature difference experiment data is a distortion compensation coefficient of a collector under different recorded experiment environment temperatures;
the image correction unit is used for correcting the first image data through the temperature compensation coefficient, enabling the expansion convolution of the corrected first image data to highlight noise characteristics in the first image data through long-path fusion shallow layer and deep layer information in the characteristic enhancement module, and removing peak noise in the first image data through wavelet hard threshold filtering to obtain second image data.
7. The apparatus of claim 5, wherein the second computing module comprises:
the first acquisition unit is used for acquiring first data, wherein the first data comprises historical second image data collected by the partial discharge signal collectors and corresponding discharge types; classifying the first data according to discharge types to obtain a historical second image data set corresponding to each discharge type;
the model training unit is used for training the BP neural network model based on the historical second image data sets of all the discharge types to obtain a trained model, and the trained model is recorded as a discharge type evaluation model.
8. The high-voltage electrical apparatus partial discharge type recognition apparatus according to claim 5, further comprising:
the first acquisition module is used for acquiring a historical occurrence frequency distribution diagram corresponding to each discharge type based on historical acquisition data of all partial discharge signal collectors in the detection area, wherein the historical acquisition data comprises position information, discharge time and discharge types of the power equipment, and the historical occurrence frequency distribution diagram reflects corresponding discharge positions, discharge time and discharge times of the same discharge type;
the third calculation module is used for collecting a plurality of partial discharge signal collectors with close discharge positions in the historical occurrence frequency distribution map based on a distance clustering algorithm to obtain a plurality of partial historical occurrence frequency distribution maps, and marking the partial historical occurrence frequency distribution maps as a second distribution map;
the second acquisition module is used for acquiring historical weather information and predicted weather information of a geographic area corresponding to the second distribution diagram, wherein the historical weather information comprises temperature, humidity and air pressure values;
the fourth calculation module is used for predicting and obtaining a certain type of discharge frequency of the power equipment in the geographic area corresponding to the second distribution diagram in a first future time period by utilizing a Kalman filtering algorithm and a differential autoregressive moving average prediction model based on the historical weather information, the second distribution diagram and the future weather information;
and the consumable prediction module is used for generating a corresponding maintenance bill of materials according to the predicted discharge frequency of the corresponding type.
9. An electronic device, comprising:
a memory for storing a computer program;
a processor for carrying out the method steps of any one of claims 1-4 when executing a program stored on a memory.
10. A medium having stored thereon a computer program, which when executed by a processor, implements the method steps of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310367157.7A CN116091501B (en) | 2023-04-07 | 2023-04-07 | Method, device, equipment and medium for identifying partial discharge type of high-voltage electrical equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310367157.7A CN116091501B (en) | 2023-04-07 | 2023-04-07 | Method, device, equipment and medium for identifying partial discharge type of high-voltage electrical equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116091501A CN116091501A (en) | 2023-05-09 |
| CN116091501B true CN116091501B (en) | 2023-06-23 |
Family
ID=86187231
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310367157.7A Active CN116091501B (en) | 2023-04-07 | 2023-04-07 | Method, device, equipment and medium for identifying partial discharge type of high-voltage electrical equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116091501B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113156513A (en) * | 2021-04-14 | 2021-07-23 | 吉林大学 | Convolutional neural network seismic signal denoising method based on attention guidance |
| CN114140353A (en) * | 2021-11-25 | 2022-03-04 | 苏州大学 | Swin-Transformer image denoising method and system based on channel attention |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2987900B1 (en) * | 2012-03-09 | 2015-07-31 | Alstom Technology Ltd | METHOD FOR RECOGNIZING PARTIAL DISCHARGES ISSUED INSIDE AND OUTSIDE AN ELECTRICAL APPARATUS |
| CN111178388B (en) * | 2019-12-05 | 2022-06-17 | 上海交通大学 | Partial discharge phase distribution detection method based on NSCT photoelectric fusion atlas |
| US11481607B2 (en) * | 2020-07-01 | 2022-10-25 | International Business Machines Corporation | Forecasting multivariate time series data |
| CN112801889A (en) * | 2021-01-06 | 2021-05-14 | 携程旅游网络技术（上海）有限公司 | Image denoising method, system, device and storage medium |
| CN115187527B (en) * | 2022-06-27 | 2023-04-07 | 上海格鲁布科技有限公司 | Separation and identification method for multi-source mixed ultrahigh frequency partial discharge spectrum |
-
2023
- 2023-04-07 CN CN202310367157.7A patent/CN116091501B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113156513A (en) * | 2021-04-14 | 2021-07-23 | 吉林大学 | Convolutional neural network seismic signal denoising method based on attention guidance |
| CN114140353A (en) * | 2021-11-25 | 2022-03-04 | 苏州大学 | Swin-Transformer image denoising method and system based on channel attention |
Non-Patent Citations (2)
| Title |
|---|
| 《Median Filter Aided CNN based Image Denoising:An Ensemble Approach》;Subhrajit Dey等;《algorithms》;全文 * |
| 《双通道扩张卷积注意力图像去噪网络》;曹义亲 等;《计算机应用研究》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116091501A (en) | 2023-05-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111797890A (en) | Method and system for detecting defects of power transmission line equipment | |
| CN108648169A (en) | The method and device of high voltage power transmission tower defects of insulator automatic identification | |
| CN108304567B (en) | Method and system for identifying working condition mode and classifying data of high-voltage transformer | |
| CN108562821B (en) | Method and system for determining single-phase earth fault line selection of power distribution network based on Softmax | |
| CN112631240A (en) | Spacecraft fault active detection method and device | |
| CN110728300A (en) | Method and system for identifying fault type based on turnout action current curve | |
| CN113255590A (en) | Defect detection model training method, defect detection method, device and system | |
| CN111695620A (en) | Method and system for detecting and correcting abnormal data of time sequence of power system | |
| CN112037223B (en) | Image defect detection method and device and electronic equipment | |
| CN111815576B (en) | Method, device, equipment and storage medium for detecting corrosion condition of metal part | |
| CN110910360A (en) | Power grid image positioning method and image positioning model training method | |
| CN113379252A (en) | Bayesian network high-voltage switch cabinet health system evaluation method based on multi-scale arrangement entropy | |
| CN115793590A (en) | Data processing method and platform suitable for system safety operation and maintenance | |
| CN112419243B (en) | Power distribution room equipment fault identification method based on infrared image analysis | |
| CN111027565A (en) | Power transmission and transformation equipment report content generation method based on optical vision semantic extraction | |
| CN114581419A (en) | Transformer insulating sleeve defect detection method, related equipment and readable storage medium | |
| CN116091501B (en) | Method, device, equipment and medium for identifying partial discharge type of high-voltage electrical equipment | |
| CN114169245A (en) | Transformer fault diagnosis method, device and equipment | |
| CN107194923B (en) | Ultraviolet image diagnosis method for defect inspection of contact network power equipment | |
| JP3234742B2 (en) | Method and apparatus for estimating remaining life of electronic component | |
| CN116184060A (en) | Abnormal monitoring method and system suitable for porcelain insulator live working | |
| CN115601293A (en) | Object detection method and device, electronic equipment and readable storage medium | |
| CN113447572B (en) | Steel rail flaw detection method, electronic device, steel rail flaw detection vehicle and readable storage medium | |
| CN115130516A (en) | GIS equipment state identification method and device based on spectrum power spectrum entropy | |
| CN113420686A (en) | Power transmission line inspection method, device and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |