CN106355187A - Application of visual information to electrical equipment monitoring - Google Patents
Application of visual information to electrical equipment monitoring Download PDFInfo
- Publication number
- CN106355187A CN106355187A CN201610807476.5A CN201610807476A CN106355187A CN 106355187 A CN106355187 A CN 106355187A CN 201610807476 A CN201610807476 A CN 201610807476A CN 106355187 A CN106355187 A CN 106355187A
- Authority
- CN
- China
- Prior art keywords
- image
- electrical equipment
- power equipment
- fault
- visual information
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention discloses application of visual information to electrical equipment monitoring. The application of the visual information to electrical equipment monitoring includes the steps of firstly, acquiring electrical equipment images and establishing an electrical equipment image database; subjecting the images to preprocessing such as denoising and enhancement; then, subjecting the image to segmentation processing so as to extract image features; finally, conducting fault judgment through image classification and recognition so as to confirm whether electrical equipment has faults or not as well as fault classifications. The application of the visual information to electrical equipment monitoring has the advantages that multiple kinds of algorithms are integrated, a system is of real-time performance, dynamicity, high intelligent level and the like, accidents and economic loss caused by the faults of the electrical equipment are reduced technically, and safe running of the electrical equipment is guaranteed.
Description
Technical field
The invention belongs to digital image processing techniques field and in particular to visual information power equipment monitoring in should
With.
Background technology
The development degree of power system and technical level have become one of mark of development of all countries economy level.Currently, I
State's electrical network scale is increasing, and structure is more and more intensive, and the connection between region is also more and more tightr.If power equipment occurs
Fault, then can produce extremely disadvantageous impact.In order to improve the stability of power system, whether detection power equipment in advance
There is fault is the important step preventing power system from breaking down.Power system device is monitored can guarantee that to go out in system
Quick diagnosis, on-call maintenance before fault, so that it is guaranteed that power equipment safety runs.
Some Utilities Electric Co.s are mounted with video monitoring system in power plant, transformer station at present, achievable remote monitoring and control
Etc. function.But these monitoring systems only have video monitoring function, video image identification function is not it is impossible to efficiently identify electricity
Power equipment fault.In order to give full play to the function of video monitoring system, remote digital video monitoring equipment and digitized map can be adopted
As identifying system combines, to realize electrical equipment fault monitoring, and then provide new method and means for equipment fault monitoring.
Content of the invention
(1) goal of the invention
Application in power equipment monitoring for the visual information is a kind of non-contact electric power equipment fault detection method, the method gram
Take the deficiency of Traditional Man detection method and contaction measurement method, there is real-time, dynamic, low cost, accuracy of detection
And intelligence degree high the features such as.The method can technically ensure that power equipment safety runs, and reduces because of electrical equipment fault
The accident brought and economic loss, have certain using value.
(2) technical scheme
A kind of application in power equipment monitoring for visual information, is characterized in that gathering power equipment image first, sets up electric power
Equipment image data base;Then the pretreatment such as denoising, enhancing are carried out to image;Then dividing processing is carried out to extract to image
Characteristics of image;Carry out fault judgement finally by image classification and identification, thus obtaining power equipment to whether there is fault and event
The conclusion of barrier classification;
Step is as follows:
A, using industrial camera gather power equipment image;
B, denoising is carried out to image;
C, enhancement process is carried out to image;
D, dividing processing is carried out to image;
E, extraction characteristics of image;
F, image classification and identification;
G, judgement power equipment whether there is fault and fault category.
Further, described in step b, denoising is carried out to image,
The method that combines with cycle spinning is converted using contourlet denoising is carried out to image.
Further, described in step c, enhancement process is carried out to image,
Non-linear enhancement process is carried out to image using non-lower sampling contourlet conversion.
Further, described in step d, image segmentation process is carried out to image,
Dividing processing is carried out to image using simplified pulse coupled neural network model.
Further, the extraction characteristics of image described in step e,
The area of extraction image, rectangular degree, the hu not feature such as bending moment.
Further, the image classification described in step f and identification,
Using probabilistic neural network method, image is classified and identified.
(3) beneficial effect
Application in power equipment monitoring for the visual information is a kind of non-contact electric power equipment fault detection method, using vision
Information, on-line monitoring electrical equipment fault under not affecting power equipment normal operation.The method has low cost, detection
Precision and high degree of automation, the features such as real-time, dynamic, Detection results are good, technically reduce because of electrical equipment fault
Accident and the economic loss brought are it is ensured that power equipment safety runs.
Brief description
Fig. 1 is the specific implementation of the method.
Specific embodiment
Specific implementation with reference to the method is described in further detail to embodiment of the present invention.
As shown in figure 1, application in power equipment monitoring for the visual information based on the present invention, it is characterized in that gathering first
Power equipment image, sets up power equipment image data base, and then image carries out the pretreatment such as denoising, enhancing, and to pretreatment
Image afterwards carries out image segmentation, then extracts characteristics of image, and image is classified and identifies, terminal decision power equipment
With the presence or absence of fault and fault type;Step is as follows:
A, using industrial camera gather power equipment image;
B, denoising is carried out to image;
C, enhancement process is carried out to image;
D, dividing processing is carried out to image;
E, extraction characteristics of image;
F, image classification and identification;
G, judgement power equipment whether there is fault and fault category.
Further, described in step b, denoising is carried out to image, using contourlet conversion and cycle spinning phase
Carry out denoising in conjunction with to image.Replace the Laplace transform in contourlet conversion with wavelet transformation first, to drop
The redundancy of low contourlet conversion;Then combine cycle spinning mode, make this conversion have translation invariance;Finally adopt
Adaptive threshold mode, the power equipment image denoising to collection.
Further, described in step c, enhancement process is carried out to image, converted to figure using non-lower sampling contourlet
As carrying out enhancement process.Initially with non-lower sampling contourlet conversion, image is decomposed;Then adopt non-linear increasing
Majorant carries out nonlinear transformation to decomposition coefficient;Finally it is reconstructed, image after being strengthened.
Further, described in step d, dividing processing is carried out to image, simplifies traditional pulse coupled neural network first,
It is simplified type Pulse Coupled Neural Network;Then to this model parameter assignment;Then utilize this model segmentation figure picture.
Further, the extraction characteristics of image described in step e, the area of extraction image, rectangular degree, the hu not spy such as bending moment
Levy.
Further, the image classification described in step f and identification, is classified to image using probabilistic neural network method
With identification, first training set and test set are produced according to characteristics of image;Then set up the power equipment based on probabilistic neural network
Fault category model;Then image classification and identification are carried out.
Further, the judgement power equipment described in step g whether there is fault and fault category, by comparing test set
Error between prediction classification and true classification, to judge that power equipment whether there is fault and fault category.
In sum, application in power equipment monitoring for the visual information of the present invention can be entered to electrical equipment fault and classification
Row is effectively monitored, and has low cost, the features such as accuracy of detection is high, intelligence degree is high, is greatly improving power equipment monitoring effect
In the case of rate, guarantee that power equipment safety runs from technical elements.
Claims (1)
1. application in power equipment monitoring for the visual information, is characterized in that gathering power equipment image first, sets up electric power and set
Standby image data base;Then the pretreatment such as denoising, enhancing are carried out to image;Then image is split special to be extracted image
Levy;Carry out fault judgement finally by image classification and identification, thus obtaining power equipment to whether there is fault and fault category
Conclusion;Step is as follows:
A, using industrial camera gather power equipment image;
B, denoising is carried out to image;
C, enhancement process is carried out to image;
D, dividing processing is carried out to image;
E, extraction characteristics of image;
F, image classification and identification;
G, judgement power equipment whether there is fault and fault category.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610807476.5A CN106355187A (en) | 2016-09-07 | 2016-09-07 | Application of visual information to electrical equipment monitoring |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610807476.5A CN106355187A (en) | 2016-09-07 | 2016-09-07 | Application of visual information to electrical equipment monitoring |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106355187A true CN106355187A (en) | 2017-01-25 |
Family
ID=57859350
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610807476.5A Pending CN106355187A (en) | 2016-09-07 | 2016-09-07 | Application of visual information to electrical equipment monitoring |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106355187A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109345788A (en) * | 2018-09-26 | 2019-02-15 | 国网安徽省电力有限公司铜陵市义安区供电公司 | A kind of monitoring early-warning system of view-based access control model feature |
WO2019062818A1 (en) * | 2017-09-30 | 2019-04-04 | 施耐德电气工业公司 | Method and device for identifying state of electrical apparatus |
CN112348085A (en) * | 2020-11-06 | 2021-02-09 | 广西电网有限责任公司钦州供电局 | Power data monitoring system and method |
US11961292B2 (en) | 2021-01-21 | 2024-04-16 | Abb S.P.A. | Computer-implemented method for assisting a user in interacting with an electronic relay for electric power distribution grids |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102129564A (en) * | 2011-02-14 | 2011-07-20 | 西南交通大学 | Contact network failure detection and diagnosis method based on unmanned aerial vehicle |
CN103235830A (en) * | 2013-05-13 | 2013-08-07 | 北京臻迪科技有限公司 | Unmanned aerial vehicle (UAV)-based electric power line patrol method and device and UAV |
CN103268501A (en) * | 2013-06-04 | 2013-08-28 | 成都思晗科技有限公司 | Image recognition method for intelligent transmission line patrol |
CN103413150A (en) * | 2013-06-28 | 2013-11-27 | 广东电网公司电力科学研究院 | Power line defect diagnosis method based on visible light image |
CN103630244A (en) * | 2013-12-18 | 2014-03-12 | 重庆大学 | Equipment fault diagnosis method and system of electric power system |
CN105868722A (en) * | 2016-04-05 | 2016-08-17 | 国家电网公司 | Identification method and system of abnormal power equipment images |
-
2016
- 2016-09-07 CN CN201610807476.5A patent/CN106355187A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102129564A (en) * | 2011-02-14 | 2011-07-20 | 西南交通大学 | Contact network failure detection and diagnosis method based on unmanned aerial vehicle |
CN103235830A (en) * | 2013-05-13 | 2013-08-07 | 北京臻迪科技有限公司 | Unmanned aerial vehicle (UAV)-based electric power line patrol method and device and UAV |
CN103268501A (en) * | 2013-06-04 | 2013-08-28 | 成都思晗科技有限公司 | Image recognition method for intelligent transmission line patrol |
CN103413150A (en) * | 2013-06-28 | 2013-11-27 | 广东电网公司电力科学研究院 | Power line defect diagnosis method based on visible light image |
CN103630244A (en) * | 2013-12-18 | 2014-03-12 | 重庆大学 | Equipment fault diagnosis method and system of electric power system |
CN105868722A (en) * | 2016-04-05 | 2016-08-17 | 国家电网公司 | Identification method and system of abnormal power equipment images |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019062818A1 (en) * | 2017-09-30 | 2019-04-04 | 施耐德电气工业公司 | Method and device for identifying state of electrical apparatus |
US11302099B2 (en) | 2017-09-30 | 2022-04-12 | Schneider Electric Industries Sas | Method and device for recognizing states of electrical devices |
CN109345788A (en) * | 2018-09-26 | 2019-02-15 | 国网安徽省电力有限公司铜陵市义安区供电公司 | A kind of monitoring early-warning system of view-based access control model feature |
CN112348085A (en) * | 2020-11-06 | 2021-02-09 | 广西电网有限责任公司钦州供电局 | Power data monitoring system and method |
CN112348085B (en) * | 2020-11-06 | 2024-04-09 | 广西电网有限责任公司钦州供电局 | Power data monitoring system and method |
US11961292B2 (en) | 2021-01-21 | 2024-04-16 | Abb S.P.A. | Computer-implemented method for assisting a user in interacting with an electronic relay for electric power distribution grids |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110826538B (en) | Abnormal off-duty identification system for electric power business hall | |
Davari et al. | Intelligent diagnosis of incipient fault in power distribution lines based on corona detection in UV-visible videos | |
CN110018389B (en) | Online fault monitoring method and system for power transmission line | |
Huang et al. | Arc detection and recognition in pantograph–catenary system based on convolutional neural network | |
CN109359697A (en) | Graph image recognition methods and inspection system used in a kind of power equipment inspection | |
CN111260629A (en) | Pantograph structure abnormity detection algorithm based on image processing | |
CN105447471A (en) | Infrared detection based device gas leakage identification method and apparatus | |
CN106355187A (en) | Application of visual information to electrical equipment monitoring | |
CN105654461A (en) | Machine vision detection method for fracture of multi-bundle conductor spacer | |
CN116740654B (en) | Substation operation prevention and control method based on image recognition technology | |
CN113205039A (en) | Power equipment fault image identification and disaster investigation system and method based on multiple DCNNs | |
CN113298077A (en) | Transformer substation foreign matter identification and positioning method and device based on deep learning | |
CN116012762A (en) | Traffic intersection video image analysis method and system for power equipment | |
CN115909395A (en) | Bird damage monitoring method and device for power transmission line, electronic equipment and storage medium | |
WO2024119983A1 (en) | Anomality detection method and apparatus for cable terminal of rail vehicle | |
CN117110798B (en) | Fault detection method and system for intelligent power distribution network | |
CN114283330B (en) | Online inspection identification method and system based on multi-source data | |
Huang et al. | Cluster Analysis Based Arc Detection in Pantograph‐Catenary System | |
CN115909212A (en) | Real-time early warning method for typical violation behaviors of power operation | |
Rongrong et al. | Fault diagnosis method of distribution equipment based on hybrid model of robot and deep learning | |
CN110516551B (en) | Vision-based line patrol position deviation identification system and method and unmanned aerial vehicle | |
Changfu et al. | Research of substation equipment abnormity identification based on image processing | |
CN112101375A (en) | Intelligent substation equipment state detection method and system based on deep learning | |
Sheng et al. | A YOLOX-Based Detection Method of Triple-Cascade Feature Level Fusion for Power System External Defects | |
Murthy et al. | Distribution system insulator monitoring using video surveillance and support vector machines for complex background images |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170125 |
|
WD01 | Invention patent application deemed withdrawn after publication |