CN102519974A - Method for detecting cracking of composite insulator based on intelligent image identification - Google Patents
Method for detecting cracking of composite insulator based on intelligent image identification Download PDFInfo
- Publication number
- CN102519974A CN102519974A CN2011104195838A CN201110419583A CN102519974A CN 102519974 A CN102519974 A CN 102519974A CN 2011104195838 A CN2011104195838 A CN 2011104195838A CN 201110419583 A CN201110419583 A CN 201110419583A CN 102519974 A CN102519974 A CN 102519974A
- Authority
- CN
- China
- Prior art keywords
- composite insulator
- full
- cracks
- image
- cluster parachute
- 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
Abstract
The invention provides a method for detecting the cracking of a composite insulator based on the intelligent image identification. A high spatial resolution camera is adopted to image the composite insulator, the obtained image is pretreated and undergoes edge detection, and cracking characteristics are extracted from the image to determine the cracking degree of the composite insulator. According to the method based on the image identification in the invention, the online detection of the cracking case of the composite insulator can be realized without the tower climbing of a worker, the onsite detection difficulty is small, and the early discovery and the replacement of the cracked composite insulator can avoid generations of power grid safety accidents.
Description
Technical field
The present invention relates to a kind of composite insulator be full of cracks detection method; Belong to power transmission and transforming equipment running status maintenance field; Relate in particular to a kind of composite insulator be full of cracks detection method, can be used for the be full of cracks state of on-the-spot charged detection composite insulator based on image intelligent identification.
Background technology
Composite insulator has good anti-fouling flashover performance, is not easy breakdownly, and the problems such as cluster parachute self-destruction of null value, low value and the glass insulator of porcelain insulator can not occur.The eighties in 20th century, China experts and scholars have launched the research and development to composite insulator on the basis of drawing external experience, and mid-term, sample dropped into trial run the latter stage eighties.At the beginning of the nineties, pollution flashover accident appears in various places in succession, because anti-pollution characteristic is good, composite insulator is dropped into hangs the net use.To the end of the year 1994, the composite insulator of hanging net operation reaches 50,000.Since then, composite insulator networking quantity rapidly increases: nineteen ninety-five is 100,000, and 1998 is 460,000, and calendar year 2001 is 1,600,000, and hanging net operation had reached 3,000,000 in 2005.By in Dec, 2010, the 66kV of State Grid Corporation of China's administration and above electric pressure circuit account for electric pressure circuit all types of the same race at 37.02% of fortune insulator number at fortune composite insulator number.
From present ruuning situation, the operational reliability of composite insulator is better than porcelain insulator and glass insulator.But along with the increase of the operation time limit, umbrella cover material embrittlement, sclerosis, efflorescence, cracking, plug expose, and partial discharge phenomenon appears in insulating surface, and hydrophobicity performance problem such as weakens and highlights gradually.Insulator not only will play insulating effect to electrical equipment or conductor, also will play the fixed suspension effect, and the insulator of deterioration will threaten the safe operation of electrical network.
Experts and scholars have launched big quantity research to the detection method of insulator both at home and abroad; Existing composite insulator detection method has contact, contactless; Wherein the contact detection method comprises voltage distribution, short circuit fork method, sparking distance method, photo-electric test rod method, sound pulse detection method, Leakage Current mensuration, and the non-contact detection method comprises ultrasonic Detection Method, laser-Doppler vibratory drilling method, infrared measurement of temperature method, corona video camera method, sonic detection and radiowave detection method.The contact detection method needs manual work to step on the tower operation, is not suitable for on-the-spot the detection.Most methods are only obvious to fault detect effects a certain or a few kinds in the non-contact detection method, but the fault of other types is difficult to detect, and equipment needed thereby is expensive, and it is not very desirable detecting effect.
The be full of cracks of composite insulator material can cause plug to expose, and is exposed to airborne plug and is corroded easily, and physical strength reduces even the generation brittle failure.Because composite insulator is excellent type structure, in case lost efficacy, will be greater than by the molecular insulator chain of a plurality of insulation to the influence of transmission line of electricity.Existing composite insulator be full of cracks detection method only is adapted at the laboratory mostly carries out, and cost is high, and workload is big, is not suitable for on-the-spot charged detection, and composite insulator lacks suitable in-situ check and test method and device.
The bibliographical information of relevant this respect for example application number is the utility model patent of the charged detector of liquid crystal graphic presentation high voltage composite insulators by name of 200520006400.X; A kind of device of charged detection high voltage composite insulators defective is disclosed, can identification tape reply to come to nothing in conductive defect, the inside of closing insulator by cable and the compound inslation substring in low null value insulation.Yet above-mentioned patent does not relate to the detection method of the be full of cracks situation of on-the-spot charged detection composite insulator.
In view of this, be necessary to provide a kind of composite insulator be full of cracks detection method based on image recognition, running status that can on-the-spot charged detection composite insulator, and the be full of cracks situation of composite insulator carried out check and analysis.
Summary of the invention
Technical matters to be solved by this invention is: to the deficiency that prior art exists, a kind of detection method of composite insulator be full of cracks is provided, needn't steps on tower, need not dismantle composite insulator, can detect the be full of cracks situation of composite insulator at the scene.
The technical scheme that the present invention adopted is: a kind of composite insulator be full of cracks detection method based on image intelligent identification, it is characterized in that, and may further comprise the steps:
1) with the high spatial resolution camera composite insulator is formed images, obtain the high spatial resolution image of composite insulator;
2) image pre-service: the image to composite insulator carries out pre-service, comprises geometry correction, radiant correction, denoising, to obtain comparatively accurate spectral information;
3) rim detection: adopt the level and smooth image of Gaussian filter,, gradient magnitude is carried out non-maximum value suppress, detect and adjoining edge with the dual threshold algorithm with single order local derviation finite difference compute gradient amplitude and direction;
4) extract slight crack: at first; Confirm the scope of composite insulator based on the result of rim detection; With the result of rim detection raw video fit with composite insulator, confirm the pixel coverage of composite insulator cluster parachute, and with cluster parachutes different on image different gray values mark; Then, to each cluster parachute, the edge in its pixel coverage of mark, and judge whether the edge is slight crack, wherein, judge that the method for slight crack is:,, then be not slight crack if do not have if the threshold value that outnumbers of marginal point continuous pixels then is judged to be slight crack with this edge; At last, can obtain the slight crack of all cluster parachutes;
5) the be full of cracks situation of judgement composite insulator:, calculate the pixel count N that cluster parachute comprised according to the cluster parachute scope of composite insulator
1,,, calculate the pixel and the N of the slight crack that is comprised in this cluster parachute according to the slight crack of being judged before to this cluster parachute
2Order
, judge the degree that composite insulator chaps with the scope of threshold value, more than or equal to threshold value, then this cluster parachute chaps as if t; If t is less than threshold value, then this cluster parachute does not chap; Judge the be full of cracks degree of each cluster parachute on the composite insulator one by one,, then judge the be full of cracks of whole string composite insulator if a cluster parachute be full of cracks is arranged; Do not take place if cluster parachute all has the be full of cracks situation, then judge the not be full of cracks of whole string composite insulator.
The invention has the beneficial effects as follows: the present invention is based on the be full of cracks situation that the method for image recognition can online detection composite insulator; Do not need workman Deng Ta; On-the-spot detection difficulty is little, and the composite insulator of finding and replace be full of cracks early can be avoided the generation of power grid security accident.
Description of drawings
Fig. 1 is the technology path figure based on the composite insulator be full of cracks detection method of image intelligent identification of the embodiment of the invention.
Fig. 2 is for obtaining the enforcement block diagram of high spatial resolution image among Fig. 1.
Fig. 3 is the pretreated process flow diagram of image among Fig. 1.
Fig. 4 is the enforcement block diagram that extracts slight crack among Fig. 1.
Fig. 5 is a method block diagram of judging composite insulator be full of cracks situation among Fig. 1.
Embodiment
In order to understand the present invention better, further illustrate content of the present invention below in conjunction with embodiment, but content of the present invention not only is confined to following embodiment.Those skilled in the art can do various changes or modification to the present invention, and these equivalent form of values are equally within the listed claims limited range of the application.
Description of symbols in the accompanying drawing: 1-obtains high spatial resolution image, the pre-service of 2-image, and the 3-rim detection, the 4-slight crack extracts; 5-judges the be full of cracks situation of composite insulator, 1.1-composite insulator, 1.2-high spatial resolution camera, 1.3-high spatial resolution image; 2.1-geometry correction, 2.2-radiant correction, 2.3-denoising, the image after 2.4-handles; 4.1-the pixel coverage of composite insulator cluster parachute, 4.2-slight crack, the be full of cracks situation of 5.1-cluster parachute, the be full of cracks situation of 5.2-composite insulator.
Principle of work of the present invention: high spatial resolution image can reflect subject rich details information; Composite insulator is if there is slight crack; On high spatial resolution image, can be differentiated; Therefore, only need the scene that composite insulator is carried out to picture, can analyze the be full of cracks situation of composite insulator through image.Slight crack has certain shape facility on the image, can analyze the slight crack situation of its corresponding composite insulator through the textural characteristics that extracts image.
Fig. 1 is technology path figure of the present invention.Composite insulator be full of cracks detection method based on image recognition provided by the invention at first will be obtained the high spatial resolution image of composite insulator, image pre-service 2, and rim detection 3 then, extract slight crack 4, judge the be full of cracks situation 5 of composite insulator.
Fig. 2 directly forms images to composite insulator with the high spatial resolution camera for obtaining the enforcement block diagram of high spatial resolution image among Fig. 1, then image is carried out pre-service.Pretreated flow process is as shown in Figure 3, and high spatial resolution image 1.3 is carried out geometry correction 2.1, radiant correction 2.2, and denoising 2.3 then, the compound inslation sub-image after obtaining handling.
To the compound inslation sub-image after handling; With the canny operator compound inslation sub-image is carried out rim detection; Step is following: with the level and smooth image of Gaussian filter; With single order local derviation finite difference compute gradient amplitude and direction, gradient magnitude is carried out non-maximum value suppress, detect and adjoining edge with the dual threshold algorithm.
Fig. 4 is the enforcement block diagram that extracts slight crack among Fig. 1.At first, confirm the scope of composite insulator, with the result of rim detection raw video fit, confirm the pixel coverage of composite insulator cluster parachute, and cluster parachutes different on the image is used the different gray values mark with composite insulator according to the result of rim detection.Then, to each cluster parachute, the edge in its pixel coverage of mark, and judge whether the edge is slight crack.Wherein, judge that the method for slight crack is:,, then be not slight crack if do not have if the threshold value that outnumbers of marginal point continuous pixels then is judged to be slight crack with this edge.At last, can obtain the slight crack of all cluster parachutes.
After having obtained the cluster parachute scope and slight crack of composite insulator, judge that composite insulator be full of cracks degree methods is as shown in Figure 5.According to the cluster parachute scope of composite insulator, calculate the pixel count N that cluster parachute comprised
1,,, calculate the pixel and the N of the slight crack that is comprised in this cluster parachute according to the slight crack of being judged before to this cluster parachute
2Make
; Judge the degree of composite insulator be full of cracks with the scope of threshold value; If t is more than or equal to threshold value, then this cluster parachute chaps; If t is less than threshold value, then this cluster parachute does not chap.Judge the be full of cracks degree of each cluster parachute on the composite insulator one by one,, then judge the be full of cracks of whole string composite insulator if a cluster parachute be full of cracks is arranged; Do not take place if cluster parachute all has the be full of cracks situation, then judge the not be full of cracks of whole string composite insulator.
The content of not doing in this instructions to describe in detail belongs to this area professional and technical personnel's known prior art.
Claims (1)
1. the composite insulator be full of cracks detection method based on image intelligent identification is characterized in that, may further comprise the steps:
1) with the high spatial resolution camera composite insulator is formed images, obtain the high spatial resolution image of composite insulator;
2) image pre-service: the image to composite insulator carries out pre-service, comprises geometry correction, radiant correction, denoising, to obtain comparatively accurate spectral information;
3) rim detection: adopt the level and smooth image of Gaussian filter,, gradient magnitude is carried out non-maximum value suppress, detect and adjoining edge with the dual threshold algorithm with single order local derviation finite difference compute gradient amplitude and direction;
4) extract slight crack: at first; Confirm the scope of composite insulator based on the result of rim detection; With the result of rim detection raw video fit with composite insulator, confirm the pixel coverage of composite insulator cluster parachute, and with cluster parachutes different on image different gray values mark; Then, to each cluster parachute, the edge in its pixel coverage of mark, and judge whether the edge is slight crack, wherein, judge that the method for slight crack is:,, then be not slight crack if do not have if the threshold value that outnumbers of marginal point continuous pixels then is judged to be slight crack with this edge; At last, can obtain the slight crack of all cluster parachutes;
5) the be full of cracks situation of judgement composite insulator:, calculate the pixel count N that cluster parachute comprised according to the cluster parachute scope of composite insulator
1,,, calculate the pixel and the N of the slight crack that is comprised in this cluster parachute according to the slight crack of being judged before to this cluster parachute
2Order
, judge the degree that composite insulator chaps with the scope of threshold value, more than or equal to threshold value, then this cluster parachute chaps as if t; If t is less than threshold value, then this cluster parachute does not chap; Judge the be full of cracks degree of each cluster parachute on the composite insulator one by one,, then judge the be full of cracks of whole string composite insulator if a cluster parachute be full of cracks is arranged; Do not take place if cluster parachute all has the be full of cracks situation, then judge the not be full of cracks of whole string composite insulator.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110419583.8A CN102519974B (en) | 2011-12-15 | 2011-12-15 | Method for detecting cracking of composite insulator based on intelligent image identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110419583.8A CN102519974B (en) | 2011-12-15 | 2011-12-15 | Method for detecting cracking of composite insulator based on intelligent image identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102519974A true CN102519974A (en) | 2012-06-27 |
| CN102519974B CN102519974B (en) | 2014-07-02 |
Family
ID=46290964
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110419583.8A Active CN102519974B (en) | 2011-12-15 | 2011-12-15 | Method for detecting cracking of composite insulator based on intelligent image identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102519974B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886610A (en) * | 2014-04-05 | 2014-06-25 | 东北电力大学 | Image type defect detecting method for insulator |
| CN108737686A (en) * | 2018-06-11 | 2018-11-02 | 昆明理工大学 | Edge enhancing error based on image coefficient change spreads digital halftoning method |
| CN109615656A (en) * | 2018-11-20 | 2019-04-12 | 哈尔滨理工大学 | A kind of backbone localization method based on pattern search |
| CN109884468A (en) * | 2019-03-05 | 2019-06-14 | 河海大学 | A kind of insulator self-destruction defect inspection method based on image pixel accumulation analysis |
| CN111260637A (en) * | 2020-01-19 | 2020-06-09 | 石家庄铁道大学 | Asphalt road transverse fracture detection method based on regional difference |
| CN112379225A (en) * | 2020-10-31 | 2021-02-19 | 国网天津市电力公司 | Power equipment corona identification and evaluation alarm system and use method thereof |
| CN113622239A (en) * | 2021-09-28 | 2021-11-09 | 吴海涛 | Local strengthening method for road subgrade |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10235267A (en) * | 1997-02-25 | 1998-09-08 | Ngk Insulators Ltd | Method for inspecting defective primer coating and inspection device used therefor |
| CN101609053A (en) * | 2009-07-24 | 2009-12-23 | 国网电力科学研究院武汉南瑞有限责任公司 | A kind of intelligent insulator on-line monitoring device and method thereof |
| CN102230893A (en) * | 2011-03-28 | 2011-11-02 | 广西电网公司电力科学研究院 | Quantitative identification method of composite insulator umbrella skirt aging |
-
2011
- 2011-12-15 CN CN201110419583.8A patent/CN102519974B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10235267A (en) * | 1997-02-25 | 1998-09-08 | Ngk Insulators Ltd | Method for inspecting defective primer coating and inspection device used therefor |
| CN101609053A (en) * | 2009-07-24 | 2009-12-23 | 国网电力科学研究院武汉南瑞有限责任公司 | A kind of intelligent insulator on-line monitoring device and method thereof |
| CN102230893A (en) * | 2011-03-28 | 2011-11-02 | 广西电网公司电力科学研究院 | Quantitative identification method of composite insulator umbrella skirt aging |
Non-Patent Citations (2)
| Title |
|---|
| 林聚财 等: "基于彩色图像的玻璃绝缘子缺陷诊断", 《电网技术》, vol. 35, no. 1, 31 January 2011 (2011-01-31) * |
| 葛玉敏 等: "基于航拍图像的绝缘子表面状态检测", 《高压电器》, vol. 46, no. 4, 30 April 2010 (2010-04-30) * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886610A (en) * | 2014-04-05 | 2014-06-25 | 东北电力大学 | Image type defect detecting method for insulator |
| CN103886610B (en) * | 2014-04-05 | 2016-08-17 | 东北电力大学 | A kind of insulator image defect detection method |
| CN108737686A (en) * | 2018-06-11 | 2018-11-02 | 昆明理工大学 | Edge enhancing error based on image coefficient change spreads digital halftoning method |
| CN109615656A (en) * | 2018-11-20 | 2019-04-12 | 哈尔滨理工大学 | A kind of backbone localization method based on pattern search |
| CN109884468A (en) * | 2019-03-05 | 2019-06-14 | 河海大学 | A kind of insulator self-destruction defect inspection method based on image pixel accumulation analysis |
| CN111260637A (en) * | 2020-01-19 | 2020-06-09 | 石家庄铁道大学 | Asphalt road transverse fracture detection method based on regional difference |
| CN112379225A (en) * | 2020-10-31 | 2021-02-19 | 国网天津市电力公司 | Power equipment corona identification and evaluation alarm system and use method thereof |
| CN113622239A (en) * | 2021-09-28 | 2021-11-09 | 吴海涛 | Local strengthening method for road subgrade |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102519974B (en) | 2014-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102519974B (en) | Method for detecting cracking of composite insulator based on intelligent image identification | |
| CN102520286B (en) | Hyperspectrum-based composite insulator operation state classification method | |
| CN102520323B (en) | Hyperspectrum-based composite insulator aging operating state detection method | |
| CN102519846B (en) | Hyperspectrum-based composite insulator hydrophobicity detection method | |
| CN101487866B (en) | On-line detection method for AC power transmission line porcelain zero resistance insulator based on infrared thermal imaging | |
| CN103926510B (en) | A kind of cable sheath electric current and current-carrying capacity on-line monitoring and fault diagonosing localization method | |
| CN103529362B (en) | Based on insulator identification and the defect diagnostic method of perception | |
| CN104267063A (en) | Low-value insulator detection method based on infrared thermography | |
| CN110349128B (en) | Method for detecting icicle bridging degree between glass insulator umbrellas | |
| CN106326808A (en) | Method for detecting bird nests in power transmission line poles based on unmanned plane images | |
| CN104849287A (en) | Composite insulator contamination degree non-contact detection method | |
| CN111754465A (en) | Insulator positioning and string drop detection method | |
| CN102831393A (en) | Rapid image recognizing method of power tower pole outline | |
| CN109523543A (en) | A kind of wire strand breakage detection method based on Edge Distance | |
| CN101672885A (en) | Method for on-line detecting external insulation state of electric transmission and transformation equipment | |
| CN107729397B (en) | Method for judging ice and snow covering type by using RGB (red, green and blue) components of image | |
| CN109827662A (en) | Determination method based on dead wind area low resistance insulator infrared detection temperature threshold | |
| CN204679591U (en) | A kind of leakage conductor state measuring device with electricity based on electric field method | |
| CN108573233B (en) | Power grid ceramic insulator identification method based on image processing technology | |
| Wei et al. | Inverse application of charge simulation method in detecting faulty ceramic insulators and processing influence from tower | |
| CN112884720B (en) | Distribution line pollution flashover insulator detection method and system | |
| Changfu et al. | Research of substation equipment abnormity identification based on image processing | |
| Cao et al. | Research on small-scale defect identification and detection of smart grid transmission lines based on image recognition | |
| Pan | Intelligent image recognition research on status of power transmission lines | |
| Anjum et al. | Radio frequency (RF) technique for field inspection of porcelain insulators |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |