CN114113947A - Switch cabinet based on ultraviolet imaging method and discharge state sensing method thereof - Google Patents
Switch cabinet based on ultraviolet imaging method and discharge state sensing method thereof Download PDFInfo
- Publication number
- CN114113947A CN114113947A CN202111440303.1A CN202111440303A CN114113947A CN 114113947 A CN114113947 A CN 114113947A CN 202111440303 A CN202111440303 A CN 202111440303A CN 114113947 A CN114113947 A CN 114113947A
- Authority
- CN
- China
- Prior art keywords
- switch cabinet
- image
- discharge state
- sensing
- parameters
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000003384 imaging method Methods 0.000 title claims abstract description 21
- 239000002245 particle Substances 0.000 claims abstract description 26
- 238000005457 optimization Methods 0.000 claims abstract description 16
- 230000009467 reduction Effects 0.000 claims abstract description 15
- 238000001228 spectrum Methods 0.000 claims abstract description 13
- 238000012935 Averaging Methods 0.000 claims abstract description 8
- 238000013135 deep learning Methods 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims abstract description 5
- 238000003709 image segmentation Methods 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 22
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 230000005684 electric field Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 3
- 230000005611 electricity Effects 0.000 claims 2
- 238000004458 analytical method Methods 0.000 abstract description 2
- 238000000605 extraction Methods 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 description 12
- 238000009413 insulation Methods 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000007792 addition Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000007847 structural defect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing Relating To Insulation (AREA)
Abstract
The invention discloses a switch cabinet based on an ultraviolet imaging method and a discharge state sensing method thereof, which comprises the steps of capturing the corona discharge moment of the switch cabinet by using an ultraviolet imager, establishing an image, carrying out image segmentation by a threshold method, obtaining singular value parameters from the segmented image, separating gamma energy spectrum components and noise according to the singular value parameters, finally obtaining the image parameters after noise reduction through diagonal averaging operation, substituting the image parameters into a particle swarm optimization algorithm for deep learning and training and optimizing, and sensing the discharge state of the switch cabinet by using an optimization result through a computer; by the aid of the system, the parameter extraction efficiency and the analysis speed can be improved, and the real-time performance and the accuracy of sensing of the discharge state of the switch cabinet are improved.
Description
Technical Field
The invention relates to the field of power monitoring, in particular to a switch cabinet based on an ultraviolet imaging method and a discharge state sensing method thereof.
Background
With the continuous expansion of the scale of power grids and the continuous improvement of power load requirements, the damage and failure of various types of high-voltage equipment used in power systems are increasing, and accordingly, the requirements for preventive maintenance are also increasing. The transmission line and the substation electrical equipment work in the atmospheric environment. In some cases, corona discharge and surface partial discharge phenomena occur with the occurrence of structural defects that decrease in insulating properties. The corona discharge detection is carried out on the electrical equipment, and the possible degradation condition of insulation can be mastered in time. The dangerous condition of the insulation can be determined before a serious accident occurs. Thereby avoiding the occurrence of accidents: the ultraviolet pulse method for detecting the discharge of the high-voltage electrical equipment has important significance for realizing intelligent fault diagnosis and state maintenance of the electrical equipment. In the discharging process of the electrical equipment, a large amount of ultraviolet rays are radiated outwards from corona and partial discharge parts, so that the insulation condition of operating equipment can be indirectly evaluated by utilizing the generation and enhancement of corona discharge and partial discharge, the defects of the insulation equipment can be found in time, and compared with the traditional detection methods such as ultrasonic detection and infrared detection, the ultraviolet imaging method detection technology has a plurality of unique advantages in a power system.
Compared with other detection means, the ultraviolet imager which is gradually popularized at present has the advantages of visual observation, good predictability, long observation distance and the like. The reports of research on the aspect of developing an ultraviolet online detection system of electric equipment in China are very few, preliminary research is conducted on the aspect of research on the aspects of Chongqing university and Qinghua university, and an ultraviolet imaging method detection system can directly count the number of discharge pulses of the equipment and has the characteristics of rapidness, intuition and better predictability; compared with a leakage current detection method, the method has the characteristics of no contact, no influence of high-frequency interference and higher sensitivity, has the advantages of low cost, high sensitivity, online detection, early warning and the like, is not limited by traffic conditions and human factors, is more suitable for real-time monitoring of the running state of high-voltage electrical equipment, and has wide application prospect.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides the switch cabinet based on the ultraviolet imaging method and the discharge state sensing method thereof, the method can improve the detection speed and the state diagnosis accuracy, has strong practicability, can be applied to the complex working condition of the switch cabinet, and enables the switch cabinet state sensing to be more intelligent.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
a switch cabinet based on an ultraviolet imaging method comprises a data acquisition system, an ultraviolet imager, a coaxial cable, a switch cabinet, a computer and a PID controller, wherein the input end of the data acquisition system is electrically connected with the output end of the ultraviolet imager, the data acquisition system is electrically connected with the switch cabinet and the computer through the coaxial cable respectively, and the data acquisition system is connected with the PID controller.
A switch cabinet discharge state sensing method based on an ultraviolet imaging method comprises the following steps:
s1: capturing the corona discharge moment of the switch cabinet by using an ultraviolet imager, and establishing an image;
s2: carrying out image segmentation by a threshold value method, and obtaining singular value parameters of the segmented image;
s3: separating gamma energy spectrum components and noise according to the singular value parameters, and obtaining image parameters after noise reduction through diagonal averaging operation;
s4: substituting the particle swarm optimization algorithm for deep learning, training and optimizing, and sensing the discharge state of the switch cabinet through a computer according to an optimization result.
Furthermore, the method also comprises the step that the miniature electric field sensor senses the change of leakage current around the switch cabinet and transmits a signal to the computer to give an early warning.
Further, the thresholding method in step S2 is to separate the light spot from the image background by acquiring the information of the image gray value.
Further, the noise reduction algorithm of step S3 includes the following steps:
establishing a track matrix M for the separated image parameters:
wherein d is the number of gamma energy spectrum addresses and l is the embedding dimension;
decomposing matrix singular values, calculating the number of nonzero matrix singular values, and performing grouping calculation on the singular values, wherein the noise parameters corresponding to the smaller singular values can obtain a track matrix formula:
wherein alpha is a non-zero singular value, beta and sigma are respectively a left singular value vector and a right singular value vector;
and carrying out diagonal averaging on the matrix subjected to noise reduction, and converting the matrix into a gamma energy spectrum, wherein the formula is as follows:
the effect of image noise reduction can be achieved by selecting a proper embedding dimension and a proper matrix order, and a clear light spot area image is obtained.
Further, the particle swarm optimization algorithm of step S4 includes the following steps:
substituting photon number and electron number parameters and calculating the fitness of each particle;
secondly, the position and the speed of the particles are updated according to the appropriateness;
whether the maximum iteration times or the optimal solution is found is judged;
fourthly, if yes, ending; and if not, returning to the step.
The invention has the advantages and beneficial effects that:
the invention relates to a sensing method of switch cabinet discharge state based on ultraviolet imaging method, a micro electric field sensor can sense the leakage current change around the switch cabinet and transmit the signal to a computer to give early warning, simultaneously, an ultraviolet imager is used for capturing the corona discharge moment of the switch cabinet, an image is established, the image is segmented by a threshold value method, the segmented image is subjected to singular value parameter acquisition, separating gamma energy spectrum components and noise according to singular value parameters, obtaining image parameters after noise reduction through diagonal averaging operation, substituting the image parameters into a particle swarm optimization algorithm for deep learning, training and optimizing, sensing the discharge state of the switch cabinet through a computer according to an optimization result, improving the detection speed and the accuracy of state diagnosis, having strong practicability, the intelligent sensing system can be applied to complex working conditions where the switch cabinet is located, and enables state sensing of the switch cabinet to be more intelligent.
Drawings
The invention is described in detail below with reference to the following figures and examples:
FIG. 1 is a diagram of a UV imaging sensing switch cabinet status system;
FIG. 2 is a flow chart of a method for sensing the discharge state of a switch cabinet based on an ultraviolet imaging method according to the invention;
FIG. 3 is a block diagram of a particle swarm optimization algorithm.
Wherein: according to collection system 1, ultraviolet light imager 2, coaxial cable 3, cubical switchboard 4, computer 5, PID controller 6.
Detailed Description
The present invention is further described in detail with reference to the following specific examples, but the scope of the present invention is not limited by the specific examples, which are defined by the claims. In addition, any modification or change that can be easily made by a person having ordinary skill in the art without departing from the technical solution of the present invention will fall within the scope of the claims of the present invention.
Example 1:
as shown in fig. 1, the switch cabinet based on the ultraviolet imaging method includes a data acquisition system 1, an ultraviolet imager 2, a coaxial cable 3, a switch cabinet 4, a computer 5 and a PID controller 6, wherein an input end of the data acquisition system 1 is electrically connected to an output end of the ultraviolet imager 2, the data acquisition system 1 is electrically connected to the switch cabinet 4 and the computer 5 through the coaxial cable 3, and the data acquisition system is connected to the PID controller 6. Wherein, the data acquisition system 1 adopts PCL 9812. The data acquisition system is used for acquiring data recorded by the ultraviolet imager, the ultraviolet imager is used for photographing the switch cabinet and recording parameters, the computer is used for recording the ultraviolet imaging parameters and evaluating the discharge state, and the PID controller is used for controlling the data acquisition system.
As shown in fig. 2, the method for sensing the discharge state of the switch cabinet based on the ultraviolet imaging method in the embodiment includes the following steps:
s1: capturing the corona discharge moment of the switch cabinet by using an ultraviolet imager, and establishing an image;
s2: carrying out image segmentation by a threshold value method, and obtaining singular value parameters of the segmented image;
s3, separating gamma energy spectrum components and noise according to the singular value parameters, and obtaining image parameters after noise reduction through diagonal averaging operation;
s4: and substituting the image parameters into a particle swarm optimization algorithm for deep learning, training and optimizing, and sensing the discharge state of the switch cabinet through a computer according to an optimized result.
Wherein the thresholding method described in step S2 separates the light spot from the image background mainly by acquiring information of the gray value of the image.
The noise reduction algorithm for processing the ultraviolet image in step S2 mainly includes the steps of:
establishing a track matrix M for the separated image parameters:
wherein d is the number of gamma energy spectrum addresses, l is the embedding dimension, and m is the gamma energy spectrum parameter. k is 1,2, · n
Decomposing matrix singular values, calculating the number of nonzero matrix singular values, and performing grouping calculation on the singular values, wherein the noise parameters corresponding to smaller singular values can obtain a track matrix X formula as follows:
wherein alpha is a non-zero singular value, beta and sigma are respectively a left singular value vector and a right singular value vector. j is a natural number from 1 to n
And carrying out diagonal averaging on the matrix subjected to noise reduction, and converting the matrix into a gamma energy spectrum, wherein the formula is as follows:
wherein y (m) is a matrix after noise reduction, m is a gamma energy spectrum parameter, j is a natural number from 1 to N, and N is a maximum channel address number.
As shown in the formula, the effect of image noise reduction can be achieved by selecting a proper embedding dimension and a proper matrix order, and a clear light spot area image is obtained.
As shown in fig. 3, the particle swarm optimization algorithm in step S4 includes the following steps:
substituting photon number and electron number parameters and calculating the fitness of each particle;
secondly, the position and the speed of the particles are updated according to the appropriateness;
whether the maximum iteration times or the optimal solution is found is judged;
fourthly, if yes, ending; and if not, returning to the step.
Wherein: the particle swarm algorithm records two extreme values pbest and gbest of the particles to update the speed and the position of the particle swarm algorithm by the following calculation process:
vi＝vi+m1×rand()×(pbest-xi)+m2×rand()×(gbest-xi) (14)
xi＝xi+vi (15)
where v is the velocity of the particle, rand () is a random number between (0,1), x is the current position of the particle, m1And m2Is a learning factor, typically equal to 2, i 1, and 2 … … N is the number of particles.
The first part of formula 14 is a memory term, which represents the influence of the last speed and direction, and the second part of formula 14 is a self-recognition term, which is a vector pointing from the current point to the best point of the particle itself and represents the part from which the motion of the particle comes from the experience of the user; the third part is a group recognition item which is a vector pointing to the best point of the group from the current point and reflects the interrelation among the particles. And forming a standard form of the particle swarm optimization algorithm based on the two formulas.
The number of the optimal solutions of photons and electrons is obtained through the optimization calculation and is defined as follows;
in the embodiment, according to the adaptability of photons and electrons in the surface environment of the switch cabinet, the photon parameter is set to be 2400, the electronic parameter is set to be 600, the learning rate is 0.001-0.1, and S is defineda，CaThe area of the light spot and the number of photons are respectively. The following formula is established:
wherein SinsThe area of the image shot by the ultraviolet imager, S is the area of the light spot, CaThe calculation formula is the ratio of the number of ultraviolet discharge photons to the discharge area, and is as follows:
wherein N isuFor the number of photons in the discharge process of the switch cabinet, define as none in the ultraviolet imageLight spot, when the number of photons is less than 10, it is defined as normal state, when CaAnd when the number of photons is less than 0.5 and less than 500 and is more than 10, the corona discharge state is defined. When C is presentaGreater than 0.5 and less than 0.9, the number of photons between 500 and 1500 defines the strong discharge state. According to the particle swarm optimization algorithm, the parameter extraction efficiency and the analysis speed can be improved, and the real-time performance and the accuracy of the switch cabinet discharge state sensing are improved.
Example 2:
as shown in fig. 1, the present embodiment is different from embodiment 1 only in that the following steps are further included:
and sensing the leakage current change around the switch cabinet through the miniature electric field sensor and transmitting a signal to the computer to give an early warning.
The rest is the same as example 1.
While the preferred embodiments of the present invention have been illustrated and described, it will be appreciated by those skilled in the art that various modifications and additions may be made to the specific embodiments described and illustrated, and such modifications and additions are intended to be covered by the scope of the present invention.
Claims (6)
1. A cubical switchboard based on ultraviolet imaging method which characterized in that: including data acquisition system (1), ultraviolet light imager (2), coaxial cable (3), cubical switchboard (4), computer (5) and PID controller (6), the input of data acquisition system (1) is connected with the output electricity of ultraviolet light imager (2), and data acquisition system (1) is connected with cubical switchboard (4) and computer (5) electricity respectively through coaxial cable (3), and data acquisition system (1) links to each other with PID controller (6).
2. The method for sensing the discharge state of the switch cabinet based on the ultraviolet imaging method as claimed in claim 1, characterized by comprising the following steps:
s1: capturing the corona discharge moment of the switch cabinet by using an ultraviolet imager, and establishing an image;
s2: carrying out image segmentation by a threshold value method, and obtaining singular value parameters of the segmented image;
s3: separating gamma energy spectrum components and noise according to the singular value parameters, and obtaining image parameters after noise reduction through diagonal averaging operation;
s4: substituting the particle swarm optimization algorithm for deep learning, training and optimizing, and sensing the discharge state of the switch cabinet through a computer according to an optimization result.
3. The method for sensing the discharge state of the switch cabinet based on the ultraviolet imaging method as claimed in claim 2, wherein: the method also comprises the step that the miniature electric field sensor senses the change of leakage current around the switch cabinet and transmits signals to the computer to give an early warning.
4. The method for sensing the discharge state of the switch cabinet based on the ultraviolet imaging method as claimed in claim 2, wherein: the thresholding method in step S2 is to separate the light spot from the image background by acquiring the information of the gray value of the image.
5. The method for sensing the discharge state of the switch cabinet based on the ultraviolet imaging method as claimed in claim 2, wherein the noise reduction algorithm of step S3 includes the following steps:
establishing a track matrix M for the separated image parameters:
wherein d is the number of gamma energy spectrum addresses and l is the embedding dimension;
decomposing matrix singular values, calculating the number of nonzero matrix singular values, and performing grouping calculation on the singular values, wherein the noise parameters corresponding to the smaller singular values can obtain a track matrix formula:
wherein alpha is a non-zero singular value, beta and sigma are respectively a left singular value vector and a right singular value vector;
and carrying out diagonal averaging on the matrix subjected to noise reduction, and converting the matrix into a gamma energy spectrum, wherein the formula is as follows:
the effect of image noise reduction can be achieved by selecting a proper embedding dimension and a proper matrix order, and a clear light spot area image is obtained.
6. The method for sensing the discharge state of the switch cabinet based on the ultraviolet imaging method as claimed in claim 2, wherein the particle swarm optimization algorithm of step S4 includes the following steps:
substituting photon number and electron number parameters and calculating the fitness of each particle;
secondly, the position and the speed of the particles are updated according to the appropriateness;
whether the maximum iteration times or the optimal solution is found is judged;
fourthly, if yes, ending; and if not, returning to the step.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111440303.1A CN114113947A (en) | 2021-11-30 | 2021-11-30 | Switch cabinet based on ultraviolet imaging method and discharge state sensing method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111440303.1A CN114113947A (en) | 2021-11-30 | 2021-11-30 | Switch cabinet based on ultraviolet imaging method and discharge state sensing method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114113947A true CN114113947A (en) | 2022-03-01 |
Family
ID=80368410
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111440303.1A Pending CN114113947A (en) | 2021-11-30 | 2021-11-30 | Switch cabinet based on ultraviolet imaging method and discharge state sensing method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114113947A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017214738A1 (en) * | 2016-06-15 | 2017-12-21 | Selfrag Ag | Method of treating a solid material by means of high voltage discharges |
| CN109063780A (en) * | 2018-08-10 | 2018-12-21 | 国网上海市电力公司 | Partial discharge of transformer recognition methods based on particle group optimizing core neighbour's propagation algorithm |
| CN109470628A (en) * | 2018-09-29 | 2019-03-15 | 江苏新绿能科技有限公司 | Contact net insulator contamination condition detection method |
| CN110146791A (en) * | 2019-05-07 | 2019-08-20 | 国网山东省电力公司电力科学研究院 | A kind of corona detection method based on image procossing |
| CN111833312A (en) * | 2020-06-22 | 2020-10-27 | 国网江苏省电力有限公司电力科学研究院 | Ultraviolet image diagnosis method and system for detecting discharge of fault insulator |
-
2021
- 2021-11-30 CN CN202111440303.1A patent/CN114113947A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017214738A1 (en) * | 2016-06-15 | 2017-12-21 | Selfrag Ag | Method of treating a solid material by means of high voltage discharges |
| CN109063780A (en) * | 2018-08-10 | 2018-12-21 | 国网上海市电力公司 | Partial discharge of transformer recognition methods based on particle group optimizing core neighbour's propagation algorithm |
| CN109470628A (en) * | 2018-09-29 | 2019-03-15 | 江苏新绿能科技有限公司 | Contact net insulator contamination condition detection method |
| CN110146791A (en) * | 2019-05-07 | 2019-08-20 | 国网山东省电力公司电力科学研究院 | A kind of corona detection method based on image procossing |
| CN111833312A (en) * | 2020-06-22 | 2020-10-27 | 国网江苏省电力有限公司电力科学研究院 | Ultraviolet image diagnosis method and system for detecting discharge of fault insulator |
Non-Patent Citations (2)
| Title |
|---|
| SHILING ZHANG等: "Optimization of Corona Ring Structure for UHV Composite Insulator Using Finite Element Method and PSO Algorithm", 《2013 IEEE INTERNATIONAL CONFERENCE ON SOLID DIELECTRICS》, 4 July 2013 (2013-07-04), pages 1 - 4 * |
| 曹辉等: "奇异谱分析用于提升双光梳激光测距精度", 《物理学报》, 31 December 2018 (2018-12-31), pages 1 - 7 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111289854B (en) | Insulator insulation state evaluation method of 3D-CNN and LSTM based on ultraviolet video | |
| CN113505655B (en) | Intelligent bearing fault diagnosis method for digital twin system | |
| CN111754465A (en) | Insulator positioning and string drop detection method | |
| Cui et al. | The methods in infrared thermal imaging diagnosis technology of power equipment | |
| CN113486877B (en) | Power equipment infrared image real-time detection and diagnosis method based on light artificial intelligent model | |
| CN113158722A (en) | Rotary machine fault diagnosis method based on multi-scale deep neural network | |
| CN105300528A (en) | Infrared image diagnosis method and infrared image diagnosis system for transformer station equipment | |
| CN110412458A (en) | A kind of OLTC drive failure diagnostic method | |
| CN106338674A (en) | DC cable connector insulation fault diagnosis method and system based on improved ECOC classifier | |
| CN113219328A (en) | Intelligent fault diagnosis method for circuit breaker operating mechanism based on information fusion | |
| Maraaba et al. | Estimation of high voltage insulator contamination using a combined image processing and artificial neural networks | |
| CN117110798B (en) | Fault detection method and system for intelligent power distribution network | |
| CN114113947A (en) | Switch cabinet based on ultraviolet imaging method and discharge state sensing method thereof | |
| CN111881793B (en) | Non-invasive load monitoring method and system based on capsule network | |
| CN110132566B (en) | OLTC fault diagnosis method based on fuzzy clustering | |
| Li et al. | DC arc fault risk degree evaluation based on back propagation neural network | |
| CN217181103U (en) | Monitoring system of high-voltage switch cabinet | |
| CN115828088A (en) | High-voltage shunt reactor vibration abnormity fault diagnosis method based on deep learning | |
| CN114462521A (en) | Efficient intelligent classification and detection method for power equipment | |
| CN107862245A (en) | A kind of method for monitoring abnormality of client power distribution room | |
| CN113376473A (en) | Fault arc detection method based on support vector machine and image recognition | |
| CN111398810A (en) | Slip ring electric spark detection and diagnosis system and detection and diagnosis method | |
| CN113160236A (en) | Image identification method for shadow shielding of photovoltaic cell | |
| Ma et al. | GIS mechanical fault diagnosis and test analysis based on S transform-SVM-AlexNet model | |
| CN112883639A (en) | GIS equipment service life prediction device and method based on machine learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |