CN113702786A - K-means-based multi-parameter suspension insulator insulation state evaluation method - Google Patents
K-means-based multi-parameter suspension insulator insulation state evaluation method Download PDFInfo
- Publication number
- CN113702786A CN113702786A CN202111026834.6A CN202111026834A CN113702786A CN 113702786 A CN113702786 A CN 113702786A CN 202111026834 A CN202111026834 A CN 202111026834A CN 113702786 A CN113702786 A CN 113702786A
- Authority
- CN
- China
- Prior art keywords
- insulation state
- discharge
- parameter
- ultraviolet
- suspension insulator
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—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
-
- 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
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing Relating To Insulation (AREA)
- Insulators (AREA)
Abstract
The invention discloses a K-means-based multi-parameter suspension insulator insulation state evaluation method, which comprises the steps of synchronously acquiring ultraviolet video, leakage current and acoustic emission signals in the insulator discharging process, preprocessing the signals, synthesizing three parameters to form a three-dimensional sample point, and constructing an insulator insulation state sample library comprising a training set and a testing set. And sending the sample points in the training set into a K-means clustering network, setting four insulator insulation states comprising 'normal', 'poor' and 'poor', repeatedly adjusting the position of a clustering center according to the magnitude of a loss function value, considering that the clustering effect is optimal when the value is less than a given value, calculating the distance between the sample point to be tested and the optimal clustering center, and realizing the evaluation of the suspension insulator insulation state.
Description
Technical Field
The invention relates to the technical field of high voltage test technology, image processing technology and machine learning, in particular to a K-means-based multi-parameter suspension insulator insulation state evaluation method.
Background
The transmission of electric energy mainly depends on an overhead transmission line, and the insulator is an important component of the overhead transmission line and plays a role in electric insulation and mechanical support between a lead and a tower. The insulator is subjected to the combined action of factors such as irradiation, corona discharge, salt mist, bird pecking and the like for a long time, so that the defects of damage, aging and the like are easily generated. The defect insulator is easier to generate corona discharge, the traditional manual inspection cannot timely master the running state of the insulator, the further development of discharge may cause flashover of the insulator along the surface, and the normal running of a power system is threatened.
The traditional inspection method is mainly a visual observation method, is influenced by human factors, and is easy to generate false detection and missing detection. The ultraviolet imaging method detects a discharge phenomenon of the apparatus by detecting ultraviolet light generated by ionized gas. The ultraviolet imaging method has the advantages of non-contact, high positioning precision, strong anti-interference capability and the like. The leakage current is the current flowing through the surface contamination layer of the insulator under the action of the working voltage, and is a dynamic parameter for representing the state of the insulator. Detecting leakage current is a common detection method for insulators. In the gas discharge theory, discharge is often accompanied by emission of acoustic signals, and different acoustic emission signals correspond to different discharge stages, and in recent years, acoustic emission technology has been applied to the research of insulator state detection. The monitoring of the power system adopts an ultraviolet imaging method, a leakage current method and an acoustic emission signal method, but the method combining the ultraviolet imaging method, the leakage current method and the acoustic emission signal method is rarely adopted.
The method synchronously collects ultraviolet video, leakage current and acoustic emission signals in the discharging process of the insulator and preprocesses multi-parameter signals. And integrating the three signals to form a three-dimensional sample point corresponding to the discharging process in a certain time. And clustering all sample points by adopting a sample clustering method based on K-means to correspond to different discharging stages, namely different insulation states of the insulators. The method can solve the problem of evaluating the external insulation state of the power equipment, and has a very wide application prospect.
Disclosure of Invention
In order to solve the problem of insulator insulation state evaluation, the invention provides a K-means-based multi-parameter suspension insulator insulation state evaluation method, which can realize intelligent evaluation of the external insulation state of power equipment.
A K-means-based multi-parameter suspension insulator insulation state assessment method comprises the following steps:
step 1: and synchronously acquiring an ultraviolet video, a leakage current signal and an acoustic emission signal in the discharging process of the suspension insulator and recording the environmental sound pressure level value.
Step 2: and preprocessing the multi-parameter signal, and calculating the area of a light spot, the number of photons, the effective value of leakage current and the sound pressure level value per second in the ultraviolet video. And synthesizing the three parameters to form three-dimensional sample points in the discharge process within a certain time T, and establishing different insulation state sample libraries of the insulator, wherein the sample libraries comprise a training set and a testing set.
And step 3: and setting the number of the clustering centers to be 4, and sending the sample points in the training set into a K-means network for training and feature learning.
And 4, step 4: and calculating the distance synthesis between all samples and the centers of the belonged classes, namely loss function values, repeatedly adjusting the positions of the clustering centers to reduce the loss function values, and obtaining the optimal sample clustering center for the insulator insulation state evaluation.
And 5: and respectively calculating the distance between the three-dimensional sample point in the test set and each clustering center, wherein the class with the minimum calculated distance is the class to which the sample point belongs, namely the insulator insulation state corresponding to the discharge of the section.
Further, a time synchronization method is adopted for synchronously acquiring ultraviolet video, leakage current signals and acoustic emission signals in the discharging process of the suspension insulator in the step 1, and the time references of the ultraviolet imager, the leakage current sensor and the noise sensor are adjusted to be consistent.
Further, the multi-parameter signal preprocessing in the step 2 comprises ultraviolet video preprocessing, namely ultraviolet image frame extraction and calculation of an ultraviolet light spot area average value and a photon number average value within a certain time T, and taking the comprehensive average value of the ultraviolet light spot area average value and the photon number average value as an ultraviolet parameter value within the certain time T; leakage current preprocessing, namely a leakage current peak value within a certain time T; and acoustic emission signal preprocessing, namely, the difference between the mean value of the sound pressure level and the ambient sound pressure level of a certain time T.
Preferably, the calculation of the spot area of the ultraviolet image extracted from the ultraviolet video frame comprises graying, binaryzation, noise removal through opening and closing operation and pixel area calculation.
Further, in the step 3, the four cluster centers correspond to four insulation states of the insulator, including corona slight discharge, corona strong discharge, arc discharge and near flashover discharge, and the insulation states are respectively marked as general, poor and very poor.
Further, in the step 4, the sum of the distances between the samples and the centers of the classes to which the samples belong is calculated to be a loss function, the positions of the centers of the samples are repeatedly adjusted, and the previous calculation process is repeated.
Preferably, in the step 5, the distances between the three-dimensional sample points in the test set and each cluster center are respectively calculated, and the class with the minimum calculated distance is the class to which the sample point belongs, that is, the insulator insulation state corresponding to the discharge of the section. After the classification of the sample points to be tested is successful, the sample points can be classified into a training set, and the more training samples are, the better the training effect is.
The invention has the advantages that: ultraviolet parameters, leakage current parameters and acoustic emission signal parameters are integrated, multiple parameters and an artificial intelligence algorithm are combined to carry out intelligent assessment on the insulation state of the insulator, and misjudgment on the insulation state of the insulator caused by fluctuation and randomness of ultraviolet light spots is avoided. Other electrical equipment can also generate ultraviolet light spots, leakage current and acoustic emission signals when discharging, and the method can be applied to intelligent evaluation of the insulation state of the external insulation of the electrical equipment.
Drawings
FIG. 1 is a flow chart of a K-means based multi-parameter suspension insulator insulation state assessment network;
FIG. 2 is a schematic diagram of a multi-parameter signal synchronously acquired according to an embodiment of the present invention;
FIG. 3 is a flow chart of spot area calculation for UV images;
FIG. 4 is a schematic diagram of multi-parameter preprocessing and three-dimensional sample point acquisition;
FIG. 5 is a sample clustering flow chart of the K-means algorithm.
Detailed Description
The technical scheme of the invention is clearly and completely described below by combining the attached drawings.
The invention provides a K-means-based multi-parameter suspension insulator insulation state evaluation method, and the insulator insulation state can be evaluated according to the conditions of generality, poor property, difference and poor property. The method comprises the steps of synchronously acquiring an ultraviolet video, leakage current and acoustic emission signals by using an ultraviolet imager, a leakage current acquisition card and a noise sensor, preprocessing the three parameters to construct an insulator insulation state sample library comprising a training set and a testing set, repeatedly calculating and optimizing through a K-means network training sample to obtain an optimal clustering center, and evaluating the insulator insulation state according to the optimal clustering center position.
Fig. 1 is a flow chart of a K-means-based multi-parameter suspension insulator insulation state evaluation network, including:
step 1: and synchronously acquiring an ultraviolet video, a leakage current signal and an acoustic emission signal in the discharging process of the suspension insulator and recording the environmental sound pressure level value. Due to the randomness and the fluctuation of ultraviolet light spots in the discharging process, the time length of each section of ultraviolet video is controlled to be 10s, meanwhile, leakage current and acoustic emission signals in 10s are collected, and ultraviolet image frame extraction is carried out on the collected ultraviolet video.
Fig. 2 shows multi-parameter signals synchronously acquired by the embodiment of the invention, and three parameters are synchronously acquired by designing an insulator high-voltage test.
Step 2: and preprocessing the multi-parameter signal, and calculating the area of a light spot, the number of photons, the effective value of leakage current and the sound pressure level value per second in the ultraviolet video. And synthesizing the three parameters to form three-dimensional sample points in the discharge process within a certain time T, and establishing different insulation state sample libraries of the insulator, wherein the sample libraries comprise a training set and a testing set.
Fig. 3 shows a calculation process of the ultraviolet spot area, and the calculation process of the open-close operation in morphology comprises the following steps: open operation
Wherein X represents the image to be calculated, S represents the structural element in the image, and the closed operation
The small light spots and the noise light spots in the ultraviolet image can be eliminated through the switching operation.
Fig. 4 shows the processes of preprocessing the ultraviolet parameter, the leakage current parameter, and the acoustic emission signal parameter and obtaining the three-dimensional sample point, where the leakage current signal preprocessing is to calculate the leakage current peak value at a certain time T, and the preprocessing processes of the ultraviolet parameter and the acoustic emission signal parameter are as in formulas (1) and (2):
and extracting an ultraviolet video frame and calculating the spot area of the ultraviolet image to obtain the number of ultraviolet photons and the spot area of each frame in the discharging process. UV represents the UV discharge parameter in the discharge video, CiPhoton number, S, for a single frame discharge UV imageiThe spot area of the single-frame discharge ultraviolet image, and n is the total frame number of the discharge video. A. thereIs the relative sound pressure level of the discharge process of this segment, AjThe sound pressure level per second during the discharge of the segment, AenvM is the total seconds of the discharge process at the time of the test, which is the ambient sound pressure level. Comprehensive ultraviolet discharge parameter UV, leakage current pulse peak value ImaxRelative sound pressure level AreAnd then three-dimensional sample points in the insulator insulation state sample library can be formed.
And step 3: and setting the number of the clustering centers to be 4, and sending the sample points in the training set into a K-means network for training and feature learning. The number of the clustering centers, namely the K value in the K-means calculation network, is set to 4 in the embodiment of the invention, and corresponds to four types of discharge with different degrees.
And 4, step 4: and calculating the distance synthesis between all samples and the centers of the belonged classes, namely loss function values, repeatedly adjusting the positions of the clustering centers to reduce the loss function values, and obtaining the optimal sample clustering center for the insulator insulation state evaluation.
FIG. 5 shows a K-means-based insulator discharge sample labeling process, and the calculation process is shown in equations (3) to (5):
d(xi,xj) The distance between samples is represented, m is the number of clustering centers, and W (C) is a loss function, and the similarity degree of the samples of the same type is represented, namely the sum of the distances between the samples and the centers of the classes to which the samples belong.
Is the center of the mean of the ith class,
to indicate a function, the value is 1 or 0. C*And the optimization process for minimizing the loss function is shown, and the position of the clustering center is adjusted to make the loss function value smaller than a specified value, so that the optimal clustering center of the sample is obtained.
The ultraviolet discharge parameter of the first cluster center is 68, the peak value of the leakage current pulse is 12mA, and the relative sound pressure level is 11. The insulator is marked to be slightly corona-discharged in the state, and the insulation state of the insulator is marked as 'normal'.
The second category has a central ultraviolet discharge parameter of 414, a leakage current pulse peak of 84mA, and a relative sound pressure level of 22. Marking the insulator corona discharge intensity in the state, and marking the insulation state of the insulator as poor.
The third category has a central ultraviolet discharge parameter of 806 and a leakage current pulse peak of 174mA, relative sound pressure level of 24. Marking that the insulator enters into the arc discharge stage in the state, and marking the insulation state of the insulator as 'poor'.
The fourth class has a central ultraviolet discharge parameter of 1963, a leakage current pulse peak of 214mA, and a relative sound pressure level of 28. Marking that the insulator is close to flashover in the state, and marking the insulation state of the insulator as poor.
And 5: and respectively calculating the distance between the three-dimensional sample point in the test set and each clustering center, wherein the class with the minimum calculated distance is the class to which the sample point belongs, namely the insulator insulation state corresponding to the discharge of the section. The specific calculation process is as formula (6):
V＝min(xi-xl)2 (6)
v represents the insulation state of the insulator, xiRepresenting three-dimensional sample points, x, to be measuredlRepresenting the best sample cluster center.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are merely illustrative of the principles of the invention, but that various changes and modifications may be made without departing from the spirit and scope of the invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (6)
1. A K-means-based multi-parameter suspension insulator insulation state assessment method comprises the following steps:
step 1: synchronously acquiring an ultraviolet video, a leakage current signal and an acoustic emission signal in the discharging process of the suspension insulator and recording an environmental sound pressure level value;
step 2: preprocessing a multi-parameter signal, and calculating the area of a light spot, the number of photons, the effective value of leakage current and the sound pressure level value per second in an ultraviolet video;
synthesizing three parameters to form three-dimensional sample points in the discharge process in T time, and establishing different insulation state sample libraries of the insulator, wherein the sample libraries comprise a training set and a testing set;
and step 3: setting the number of clustering centers to be 4, and sending sample points in the training set into a K-means network for training and feature learning;
and 4, step 4: calculating the distance between all samples and the centers of the belonged classes to be integrated, namely loss function values, repeatedly adjusting the positions of the clustering centers to reduce the loss function values to obtain the optimal sample clustering centers serving as the evaluation standards of the insulation states of the insulators;
and 5: and respectively calculating the distance between the three-dimensional sample point in the test set and each clustering center, wherein the class with the minimum calculated distance is the class to which the sample point belongs, namely the insulator insulation state corresponding to the discharge of the section.
2. The K-means based multi-parameter suspension insulator insulation state evaluation method according to claim 1, characterized in that: the step of preprocessing the ultraviolet video in the discharge process of the suspension insulator comprises the steps of video resolution, time length unification and ultraviolet image frame extraction.
3. The K-means based multi-parameter suspension insulator insulation state evaluation method according to claim 1, characterized in that: and the step of forming a three-dimensional sample point in the discharging process within a certain time T by the comprehensive three parameters comprises the step of calculating the comprehensive average value of the ultraviolet photon number and the light spot area, the average peak value of the leakage current pulse and the average relative sound pressure value in the discharging process.
4. The K-means based multi-parameter suspension insulator insulation state evaluation method according to claim 1, characterized in that: the four types of discharge include slight corona discharge, strong corona discharge, arc discharge and near flashover discharge, and the four types of insulation states are respectively marked as normal, poor and very poor.
5. The K-means based multi-parameter suspension insulator insulation state evaluation method according to claim 1, characterized in that: ultraviolet discharge parameters, leakage current and acoustic emission signals in the discharge process are integrated and sent to a K-means algorithm network for training.
6. The K-means based multi-parameter suspension insulator insulation state evaluation method according to claim 1, characterized in that: and adjusting the position of the clustering center according to the loss function value, and when the error value is less than a given value, considering that the position of the clustering center is optimal, and storing the position.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111026834.6A CN113702786B (en) | 2021-09-02 | 2021-09-02 | K-means-based multi-parameter suspension insulator insulation state evaluation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111026834.6A CN113702786B (en) | 2021-09-02 | 2021-09-02 | K-means-based multi-parameter suspension insulator insulation state evaluation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113702786A true CN113702786A (en) | 2021-11-26 |
| CN113702786B CN113702786B (en) | 2023-09-01 |
Family
ID=78657433
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111026834.6A Active CN113702786B (en) | 2021-09-02 | 2021-09-02 | K-means-based multi-parameter suspension insulator insulation state evaluation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113702786B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113807267A (en) * | 2021-09-22 | 2021-12-17 | 华北电力大学 | Suspension insulator discharge severity assessment method based on ultraviolet video and deep learning |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2472688A2 (en) * | 2010-12-28 | 2012-07-04 | BAM Bundesanstalt für Materialforschung und -prüfung | High voltage device and method for monitoring degradation of insulation in a high voltage device |
| CN105004972A (en) * | 2015-06-25 | 2015-10-28 | 华北电力大学（保定） | Porcelain insulator insulation state evaluation method based on solar-blind ultraviolet imaging image feature |
| CN105137298A (en) * | 2015-08-25 | 2015-12-09 | 国家电网公司 | Transmission line suspension insulator string external insulation state assessment method |
| CN110308375A (en) * | 2019-06-26 | 2019-10-08 | 国网陕西省电力公司西安供电公司 | A kind of cable insulation status appraisal procedure based on Artificial neural network ensemble |
| CN111289854A (en) * | 2020-02-26 | 2020-06-16 | 华北电力大学 | Insulator insulation state evaluation method of 3D-CNN and LSTM based on ultraviolet video |
| CN112462208A (en) * | 2020-11-13 | 2021-03-09 | 国网浙江省电力有限公司舟山供电公司 | Multi-parameter-based direct current cable insulation diagnosis and performance test system |
| CN113325281A (en) * | 2021-05-26 | 2021-08-31 | 国网陕西省电力公司电力科学研究院 | Method and system for identifying each development stage of GIS insulation defect partial discharge |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111652835A (en) * | 2020-02-12 | 2020-09-11 | 天津大学 | Method for detecting insulator loss of power transmission line based on deep learning and clustering |
-
2021
- 2021-09-02 CN CN202111026834.6A patent/CN113702786B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2472688A2 (en) * | 2010-12-28 | 2012-07-04 | BAM Bundesanstalt für Materialforschung und -prüfung | High voltage device and method for monitoring degradation of insulation in a high voltage device |
| CN105004972A (en) * | 2015-06-25 | 2015-10-28 | 华北电力大学（保定） | Porcelain insulator insulation state evaluation method based on solar-blind ultraviolet imaging image feature |
| CN105137298A (en) * | 2015-08-25 | 2015-12-09 | 国家电网公司 | Transmission line suspension insulator string external insulation state assessment method |
| CN110308375A (en) * | 2019-06-26 | 2019-10-08 | 国网陕西省电力公司西安供电公司 | A kind of cable insulation status appraisal procedure based on Artificial neural network ensemble |
| CN111289854A (en) * | 2020-02-26 | 2020-06-16 | 华北电力大学 | Insulator insulation state evaluation method of 3D-CNN and LSTM based on ultraviolet video |
| CN112462208A (en) * | 2020-11-13 | 2021-03-09 | 国网浙江省电力有限公司舟山供电公司 | Multi-parameter-based direct current cable insulation diagnosis and performance test system |
| CN113325281A (en) * | 2021-05-26 | 2021-08-31 | 国网陕西省电力公司电力科学研究院 | Method and system for identifying each development stage of GIS insulation defect partial discharge |
Non-Patent Citations (3)
| Title |
|---|
| 刘云鹏等: "基于稀疏表示的绝缘子紫外图谱闪络状态分类评估方法", 《高电压技术》 * |
| 刘庆珍等: "基于降维技术与K-means聚类的油纸绝缘状态综合灰评估", 《电力系统保护与控制》 * |
| 李和明等: "基于放电紫外成像参量的绝缘子污秽状态评估", 《电工技术学报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113807267A (en) * | 2021-09-22 | 2021-12-17 | 华北电力大学 | Suspension insulator discharge severity assessment method based on ultraviolet video and deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113702786B (en) | 2023-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105004972B (en) | Porcelain insulator Condition assessment of insulation method based on day blind ultraviolet imagery characteristics of image | |
| Davari et al. | Intelligent diagnosis of incipient fault in power distribution lines based on corona detection in UV-visible videos | |
| CN106919978B (en) | Method for identifying and detecting parts of high-speed rail contact net supporting device | |
| CN109118479B (en) | Capsule network-based insulator defect identification and positioning device and method | |
| CN103487729B (en) | Based on the power equipments defect detection method that ultraviolet video and infrared video merge | |
| CN103442209B (en) | Video monitoring method of electric transmission line | |
| CN105447471A (en) | Infrared detection based device gas leakage identification method and apparatus | |
| CN108573225A (en) | A kind of local discharge signal mode identification method and system | |
| CN111784633A (en) | Insulator defect automatic detection algorithm for power inspection video | |
| CN111398291B (en) | Flat enameled electromagnetic wire surface flaw detection method based on deep learning | |
| CN111289854A (en) | Insulator insulation state evaluation method of 3D-CNN and LSTM based on ultraviolet video | |
| CN112200178A (en) | Transformer substation insulator infrared image detection method based on artificial intelligence | |
| CN113065484A (en) | Insulator contamination state assessment method based on ultraviolet spectrum | |
| CN114724042B (en) | Automatic detection method for zero-value insulator in power transmission line | |
| CN114359695A (en) | Insulator breakage identification method based on uncertainty estimation | |
| CN113805018A (en) | Intelligent identification method for partial discharge fault type of 10kV cable of power distribution network | |
| CN113702786B (en) | K-means-based multi-parameter suspension insulator insulation state evaluation method | |
| Zhang et al. | Detection and condition assessment of icicle bridging for suspension glass insulator by image analysis | |
| Dai et al. | Leakage region detection of gas insulated equipment by applying infrared image processing technique | |
| CN112419243A (en) | Power distribution room equipment fault identification method based on infrared image analysis | |
| CN114487742B (en) | High-voltage shell discharge insulation performance detection system based on multi-mode texture analysis | |
| CN113781436B (en) | High-voltage switch state monitoring method based on camera and angle measurement | |
| CN115130516A (en) | GIS equipment state identification method and device based on spectrum power spectrum entropy | |
| CN107194923B (en) | Ultraviolet image diagnosis method for defect inspection of contact network power equipment | |
| Wang et al. | Visual defect detection for substation equipment based on joint inspection data of camera and robot |
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 |