CN106920240A - A kind of insulator identification and method for diagnosing faults based on infrared image - Google Patents
A kind of insulator identification and method for diagnosing faults based on infrared image Download PDFInfo
- Publication number
- CN106920240A CN106920240A CN201710137104.0A CN201710137104A CN106920240A CN 106920240 A CN106920240 A CN 106920240A CN 201710137104 A CN201710137104 A CN 201710137104A CN 106920240 A CN106920240 A CN 106920240A
- Authority
- CN
- China
- Prior art keywords
- insulator
- infrared image
- diagnosing faults
- faults based
- identification
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0008—Industrial image inspection checking presence/absence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Radiation Pyrometers (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The present invention discloses a kind of insulator identification based on infrared image and method for diagnosing faults, comprises the following steps：A, insulator is taken pictures, image recognition is carried out, to distinguish different insulators；The temperature profile that B, analysis different insulative show in the picture, faulty insulator is judged to by the abnormal insulator of temperature profile.The present invention can improve the deficiencies in the prior art, be adapted to the automatic detecting of complex environment, and false drop rate is low.
Description
Technical field
The present invention relates to electric network fault identifying and diagnosing technical field, especially a kind of insulator identification based on infrared image
And method for diagnosing faults.
Background technology
Because domestic power network scale constantly expands, long distance transmission line, such as special (super) high-tension line rapid development, and
Many transmission lines of electricity are distributed between high and steep mountains, cause traditional artificial line walking to receive terrain environment, peopleware, weather conditions
Etc. the influence of uncertain factor, efficiency is low, and it is long to patrol the cycle again, patrols and examines data accuracy not high.Therefore, recent year start by
Step development helicopter or UAV Intelligent patrol and examine technology, can not be constrained by geographical environment, greatly improve efficiency.But
The problem remained using the technology of patrolling and examining of unmanned plane is relatively low automaticity, and the data processing work after patrolling and examining is very heavy,
Manually check substantial amounts of Video data, record defect, easy missing inspection and time-consuming effort.
At present, the engineer inside many scholars and power system has had begun to be navigated based on unmanned plane automatic detecting
Image is clapped, using image processing techniques Aerial Images are analyzed with the research of detection insulator breakdown.But current research
It is concentrated mainly in the Intelligent Recognition to visible ray Aerial Images, and is limited to the complex environment along overhead transmission line and day
The influence of gas, current research is also in theory stage, it is difficult to be applied in actual items.Because many meetings are right in actual environment
The visible images details that identification is interfered, such as light, texture can be weakened in infrared image.Using it is infrared heat into
As method can reduce environmental disturbances, and most failures can be detected, therefore the identification of the insulator based on infrared image and failure are examined
Disconnected method has practicality higher, reduces the labor workload of line data-logging, and the degree of accuracy of work is patrolled and examined in raising.
For the identification technology of insulator, related scholar proposes the method based on image segmentation, and this kind of method is typically used
Be the innovatory algorithm based on OTSU methods, the OTSU algorithms for such as being improved based on Morphology Algorithm and connected domain thought.Then should
AdaBoost algorithms are used, the invariant moment features in coarse positioning region are calculated, a cascade classifier is trained, to reject nonisulated son
Region, realization is accurately positioned to insulator, such as a kind of insulator chain described based on Threshold segmentation and two-value shape facility
Automatic positioning method, looks for food-particle first with the grey entropy model based on non-downsampling Contourlet conversion (NSCT) and bacterium
Group's optimization (BF-PSO) algorithm asks for threshold value, and original Aerial Images are divided into bianry image, recycles insulation in bianry image
The shape facility of substring, description is digitized to its feature, and removes nonisulated sub-goal on this basis, realizes insulator
Be automatically positioned.
For the troubleshooting issue of located rear insulator, it is difficult to where the bottleneck captured in studying at present.Pin
To insulator chain excalation (falling piece) failure, have based on insulator number in least square ellipse fitting process calculating insulator chain
Detection method, also first with wavelet modulus maxima method extract image border, next use improved Hough transform
Ellipse in detection image, is finally based on the parameter position information of insulator, realizes that insulator falls the diagnosis of piece fault type.This
Two methods require that the image background comprising insulator to be identified is simple, and interference is few, while needing to understand insulator chain in advance
Certain fixing model.Due to the harshness of precondition, still greatly differed from each other with practical application.For insulator is damaged, cracking and
The fault types such as entrainment foreign matter, also have scholar to be studied.
The content of the invention
The technical problem to be solved in the present invention is to provide a kind of insulator identification based on infrared image and fault diagnosis side
Method, can solve the problem that the deficiencies in the prior art, be adapted to the automatic detecting of complex environment, and false drop rate is low.
In order to solve the above technical problems, the technical solution used in the present invention is as follows.
A kind of insulator identification and method for diagnosing faults based on infrared image, comprise the following steps：
A, insulator is taken pictures, image recognition is carried out, to distinguish different insulators；
The temperature profile that B, analysis different insulative show in the picture, event is judged to by the abnormal insulator of temperature profile
Barrier insulator.
Preferably, in step A, all of surf characteristic points in infrared image are calculated first, then with template data
Feature point set carries out k nearest neighbor matching, screens out the characteristic point for being not belonging to insulator, and all characteristic points then are carried out into space clustering
To distinguish different insulators.
Preferably, during K- neighborhood matchings are carried out, being accelerated using K-D trees.
Preferably, when carrying out K-D trees and being accelerated, K- is synchronized using the non-characteristic point of the association on characteristic point periphery
Neighborhood matching, using the mean eigenvalue of non-characteristic point after matching and the mean eigenvalue of characteristic point to the root node value of K-D trees
It is modified, modification method is.
Wherein, x is the root node of the K-D trees before amendment, and x ' is the root node of revised K-D trees, and y is characterized a composition
Characteristic vector mould, y0For in standard picture feature point group into characteristic vector mould, z be non-feature point group into feature to
The mould of amount, z0For in standard picture non-feature point group into characteristic vector mould.
Preferably, in step B, using the axis temperature of each insulator feature set as temperature profile.
Preferably, extracting principal direction to each insulator feature set, principal direction is corrected and fits insulator axle
Line, extracts axis temperature.
Preferably, extracting the principal direction of each insulator feature set using linear regression.
The beneficial effect brought using above-mentioned technical proposal is：The present invention can be realized in automatic identification infrared image
Insulator, saving the step of need manual identified in conventional method, while reducing workload, improve efficiency and accurate
Degree, the method for diagnosing faults based on temperature data, with very big practicality, extremely meets the site environment of complexity.This is automatic
Identification and diagnostic method, greatly reduce the situation of flase drop, while also increasing detection cycle, extend Faulty insulator and deposit
Potential safety hazard so that full-automatic circuit is patrolled and examined and is possibly realized.
Brief description of the drawings
Fig. 1 is insulator chain Stepwise calibration flow chart.
Fig. 2 is infrared thermal imaging insulator chain central temperature curve fault verification flow chart.
Fig. 3 is the infrared image of insulator.
Fig. 4 is the diagnostic result drawn according to infrared image in Fig. 3.
Specific embodiment
Reference picture 1-2 a, specific embodiment of the invention includes,
A, insulator is taken pictures, image recognition is carried out, to distinguish different insulators；
The temperature profile that B, analysis different insulative show in the picture, event is judged to by the abnormal insulator of temperature profile
Barrier insulator.
In step A, all of surf characteristic points in infrared image are calculated first, then the feature point set with template data enters
Row k nearest neighbor is matched, and screens out the characteristic point for being not belonging to insulator, then carries out space clustering to distinguish difference by all characteristic points
Insulator.
During K- neighborhood matchings are carried out, accelerated using K-D trees.
When carrying out K-D trees and being accelerated, K- neighborhood matchings are synchronized using the non-characteristic point of the association on characteristic point periphery,
The root node value of K-D trees is modified using the mean eigenvalue of non-characteristic point after matching and the mean eigenvalue of characteristic point,
Modification method is.
Wherein, x is the root node of the K-D trees before amendment, and x ' is the root node of revised K-D trees, and y is characterized a composition
Characteristic vector mould, y0For in standard picture feature point group into characteristic vector mould, z be non-feature point group into feature to
The mould of amount, z0For in standard picture non-feature point group into characteristic vector mould.
In step B, using the axis temperature of each insulator feature set as temperature profile.
Principal direction is extracted to each insulator feature set, principal direction is corrected and is fitted insulator axis, extract axle
Line temperature.
The principal direction of each insulator feature set is extracted using linear regression.
Can there is certain error in the method for extracting insulator principal direction, cause principal direction to be fitted and mistake occur, the present invention
Principal direction is corrected using the method for Stepwise calibration, after preliminary insulator principal direction is obtained, all characteristic points is obtained in main side
One whole insulator is carried out decile by upward projection, the span according to projection coordinate, can be with base on each segment
Originally ignore the deformation of insulator, Stepwise calibration then is carried out to each segment.According to insulator length self adaptation to be segmented
Selection segmentation number.
The fault type of insulator mainly has between surface fracture, cracking, filth, piece to be carried foreign matter secretly and falls piece (partly absolutely
Edge is lost) etc., this will cause the reduction of insulator resistance, cause heat production to increase, and temperature rises.Concrete methods of realizing is：(1)
Traversal insulator chain axis temperature obtains temperature change interval [min, max]；(2) insulator is found in temperature change interval
Mean temperature, using 0.1 ° as step-length；(3) threshold curve is generated, insulator two ends take 0.35 ° of threshold value, and center takes threshold value
0.25 °, and successively decreased to center from two ends and form U-shaped distribution；(4) temperature is found using insulator chain mean temperature and threshold curve
Out-of-the way position.
Reference picture 3-4, photographic analysis is carried out by insulator, can accurately obtain the trouble point information of insulator.This
Invention can realize the insulator in automatic identification infrared image, save the step of need manual identified in conventional method, subtract
While few workload, efficiency and the degree of accuracy are improve, the method for diagnosing faults based on temperature data, with very big practicality
Property, extremely meet the site environment of complexity.The automatic identification and diagnostic method, greatly reduce the situation of flase drop, while
Detection cycle is increased, the potential safety hazard of Faulty insulator presence is extended so that full-automatic circuit is patrolled and examined and is possibly realized.
In the description of the invention, it is to be understood that term " longitudinal direction ", " transverse direction ", " on ", D score, "front", "rear",
The orientation or position relationship of the instruction such as "left", "right", " vertical ", " level ", " top ", " bottom ", " interior ", " outward " are based on accompanying drawing institute
The orientation or position relationship for showing, are for only for ease of the description present invention, must rather than the device or element for indicating or imply meaning
With specific orientation, with specific azimuth configuration and operation, therefore must be not considered as limiting the invention.
General principle of the invention and principal character and advantages of the present invention has been shown and described above.The technology of the industry
Personnel it should be appreciated that the present invention is not limited to the above embodiments, simply explanation described in above-described embodiment and specification this
The principle of invention, without departing from the spirit and scope of the present invention, various changes and modifications of the present invention are possible, these changes
Change and improvement all fall within the protetion scope of the claimed invention.The claimed scope of the invention by appending claims and its
Equivalent thereof.
Claims (7)
1. a kind of insulator identification and method for diagnosing faults based on infrared image, it is characterised in that comprise the following steps：
A, insulator is taken pictures, image recognition is carried out, to distinguish different insulators；
The temperature profile that B, analysis different insulative show in the picture, is judged to that failure is exhausted by the abnormal insulator of temperature profile
Edge.
2. insulator identification and method for diagnosing faults based on infrared image according to claim 1, it is characterised in that：Step
In rapid A, all of surf characteristic points in infrared image are calculated first, then the feature point set with template data carries out k nearest neighbor
Match somebody with somebody, screen out the characteristic point for being not belonging to insulator, then carry out space clustering to distinguish different insulators by all characteristic points.
3. insulator identification and method for diagnosing faults based on infrared image according to claim 2, it is characterised in that：
Carry out during K- neighborhood matchings, accelerated using K-D trees.
4. insulator identification and method for diagnosing faults based on infrared image according to claim 3, it is characterised in that：
When carrying out K-D trees and being accelerated, K- neighborhood matchings are synchronized using the non-characteristic point of the association on characteristic point periphery, after matching
The mean eigenvalue of non-characteristic point and the mean eigenvalue of characteristic point are modified to the root node value of K-D trees, and modification method is.
Wherein, x is the root node of the K-D trees before amendment, and x ' is the root node of revised K-D trees, and y is characterized a spy for composition
Levy vector field homoemorphism, y0For in standard picture feature point group into characteristic vector mould, z be non-feature point group into characteristic vector
Mould, z0For in standard picture non-feature point group into characteristic vector mould.
5. insulator identification and method for diagnosing faults based on infrared image according to claim 1, it is characterised in that：Step
In rapid B, using the axis temperature of each insulator feature set as temperature profile.
6. insulator identification and method for diagnosing faults based on infrared image according to claim 5, it is characterised in that：It is right
Each insulator feature set extracts principal direction, principal direction is corrected and fits insulator axis, extracts axis temperature.
7. insulator identification and method for diagnosing faults based on infrared image according to claim 6, it is characterised in that：Make
The principal direction of each insulator feature set is extracted with linear regression.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710137104.0A CN106920240A (en) | 2017-03-09 | 2017-03-09 | A kind of insulator identification and method for diagnosing faults based on infrared image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710137104.0A CN106920240A (en) | 2017-03-09 | 2017-03-09 | A kind of insulator identification and method for diagnosing faults based on infrared image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106920240A true CN106920240A (en) | 2017-07-04 |
Family
ID=59461505
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710137104.0A Withdrawn CN106920240A (en) | 2017-03-09 | 2017-03-09 | A kind of insulator identification and method for diagnosing faults based on infrared image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106920240A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107833211A (en) * | 2017-11-01 | 2018-03-23 | 国家电网公司 | Zero resistance insulator automatic testing method and device based on infrared image |
| CN107831423A (en) * | 2017-11-06 | 2018-03-23 | 海南电网有限责任公司电力科学研究院 | Composite insulator interface defect discrimination method based on the identification of infrared thermal imagery axis temperature |
| CN110472510A (en) * | 2019-07-16 | 2019-11-19 | 上海电力学院 | Based on infrared and visual picture electrical equipment fault detection method and assessment equipment |
| CN111624229A (en) * | 2020-05-15 | 2020-09-04 | 嘉兴恒创电力设计研究院有限公司明绘分公司 | Intelligent charged equipment fault diagnosis method based on infrared imaging |
| WO2021190056A1 (en) * | 2020-03-26 | 2021-09-30 | 国网湖北省电力有限公司电力科学研究院 | Infrared zero value diagnosis method and system for porcelain insulator string |
| CN114048828A (en) * | 2022-01-11 | 2022-02-15 | 合肥金星智控科技股份有限公司 | Furnace tube image processing method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102201115A (en) * | 2011-04-07 | 2011-09-28 | 湖南天幕智能科技有限公司 | Real-time panoramic image stitching method of aerial videos shot by unmanned plane |
| CN103336224A (en) * | 2013-07-03 | 2013-10-02 | 同济大学 | Complex information based insulator temperature rise fault comprehensive diagnosis method |
| CN103413139A (en) * | 2013-06-28 | 2013-11-27 | 广东电网公司电力科学研究院 | Electric equipment abnormal heating detection method based on infrared inspection video data of power line inspection |
| US20160342733A1 (en) * | 2015-05-18 | 2016-11-24 | Regeneron Pharmaceuticals, Inc. | Methods And Systems For Copy Number Variant Detection |
-
2017
- 2017-03-09 CN CN201710137104.0A patent/CN106920240A/en not_active Withdrawn
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102201115A (en) * | 2011-04-07 | 2011-09-28 | 湖南天幕智能科技有限公司 | Real-time panoramic image stitching method of aerial videos shot by unmanned plane |
| CN103413139A (en) * | 2013-06-28 | 2013-11-27 | 广东电网公司电力科学研究院 | Electric equipment abnormal heating detection method based on infrared inspection video data of power line inspection |
| CN103336224A (en) * | 2013-07-03 | 2013-10-02 | 同济大学 | Complex information based insulator temperature rise fault comprehensive diagnosis method |
| US20160342733A1 (en) * | 2015-05-18 | 2016-11-24 | Regeneron Pharmaceuticals, Inc. | Methods And Systems For Copy Number Variant Detection |
Non-Patent Citations (2)
| Title |
|---|
| 敬忠良: "《航天器自主操作的测量与控制》", 31 December 2011, 中国宇航出版社 * |
| 袁安富等: "一种基于SURF特征的零件识别算法", 《计算机应用与软件》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107833211A (en) * | 2017-11-01 | 2018-03-23 | 国家电网公司 | Zero resistance insulator automatic testing method and device based on infrared image |
| CN107833211B (en) * | 2017-11-01 | 2021-05-25 | 国家电网公司 | Infrared image-based zero value insulator automatic detection method and device |
| CN107831423A (en) * | 2017-11-06 | 2018-03-23 | 海南电网有限责任公司电力科学研究院 | Composite insulator interface defect discrimination method based on the identification of infrared thermal imagery axis temperature |
| CN107831423B (en) * | 2017-11-06 | 2019-12-13 | 海南电网有限责任公司电力科学研究院 | composite insulator interface defect identification method based on infrared thermal image axis temperature identification |
| CN110472510A (en) * | 2019-07-16 | 2019-11-19 | 上海电力学院 | Based on infrared and visual picture electrical equipment fault detection method and assessment equipment |
| WO2021190056A1 (en) * | 2020-03-26 | 2021-09-30 | 国网湖北省电力有限公司电力科学研究院 | Infrared zero value diagnosis method and system for porcelain insulator string |
| CN111624229A (en) * | 2020-05-15 | 2020-09-04 | 嘉兴恒创电力设计研究院有限公司明绘分公司 | Intelligent charged equipment fault diagnosis method based on infrared imaging |
| CN114048828A (en) * | 2022-01-11 | 2022-02-15 | 合肥金星智控科技股份有限公司 | Furnace tube image processing method |
| CN114048828B (en) * | 2022-01-11 | 2022-04-19 | 合肥金星智控科技股份有限公司 | Furnace tube image processing method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106920240A (en) | A kind of insulator identification and method for diagnosing faults based on infrared image | |
| Davari et al. | Intelligent diagnosis of incipient fault in power distribution lines based on corona detection in UV-visible videos | |
| CN104809732B (en) | A kind of power equipment appearance method for detecting abnormality compared based on image | |
| CN103487729B (en) | Based on the power equipments defect detection method that ultraviolet video and infrared video merge | |
| CN104764748B (en) | Position method, system and the method and system of fault detect of insulator | |
| CN107483014B (en) | A kind of photovoltaic panel failure automatic detection method | |
| CN112380952A (en) | Power equipment infrared image real-time detection and identification method based on artificial intelligence | |
| CN104318582B (en) | Detection method for bad state of rotating double-lug component pin of high-speed rail contact network | |
| CN103279765B (en) | Steel wire rope surface damage detection method based on images match | |
| CN108280855A (en) | A kind of insulator breakdown detection method based on Fast R-CNN | |
| CN107358259B (en) | Covering ice for insulator detection method based on GLOH description son and GVF-Snake model | |
| CN111814686A (en) | Vision-based power transmission line identification and foreign matter invasion online detection method | |
| CN111260629A (en) | Pantograph structure abnormity detection algorithm based on image processing | |
| CN105354589A (en) | Method and system for intelligently identifying insulator crack in catenary image | |
| CN102508110A (en) | Texture-based insulator fault diagnostic method | |
| CN105957073B (en) | Transmission line of electricity broken lot fault detection method | |
| CN103413150A (en) | Power line defect diagnosis method based on visible light image | |
| CN108680833B (en) | Composite insulator defect detection system based on unmanned aerial vehicle | |
| CN105741291A (en) | Method for detecting faults of equipotential lines of high-speed railway overhead line system suspension devices | |
| CN112200178A (en) | Transformer substation insulator infrared image detection method based on artificial intelligence | |
| CN108846331A (en) | The video frequency identifying method whether a kind of EMU chassis screw fastener falls off | |
| CN105096305A (en) | Method and device for analyzing state of insulator | |
| CN110348380A (en) | A kind of visualization grounding switch state video recognition system and method | |
| CN112508911A (en) | Rail joint touch net suspension support component crack detection system based on inspection robot and detection method thereof | |
| CN116310274A (en) | State evaluation method for power transmission and transformation equipment |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20170704 |