CN108280855A - A kind of insulator breakdown detection method based on Fast R-CNN - Google Patents
A kind of insulator breakdown detection method based on Fast R-CNN Download PDFInfo
- Publication number
- CN108280855A CN108280855A CN201810038127.0A CN201810038127A CN108280855A CN 108280855 A CN108280855 A CN 108280855A CN 201810038127 A CN201810038127 A CN 201810038127A CN 108280855 A CN108280855 A CN 108280855A
- Authority
- CN
- China
- Prior art keywords
- insulator
- cnn
- fast
- detection
- transmission line
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of insulator breakdown detection methods based on Fast R CNN.Transmission line of electricity image information is collected by unmanned plane, robot or camera apparatus, it realizes and insulator device recognition is detected, it identifies insulator and is classified, fault identification can be carried out simultaneously, intelligent measurement goes out faulty insulator, fault location is carried out to it and identifies out of order type, realizes and the intelligent measurement and insulator image failure of insulator are positioned.The invention reside in be combined unmanned plane with Faster R CNN technologies, pass through a variety of insulation subgraphs of Faster R CNN target detections, realize the classification to the subcategory that insulate, framing finally is realized to the insulation subgraph classified, and the failure of insulator is identified by characteristics of image, reach the fault detect to insulator in turn, dramatically saves the cost of overhaul, keep inspection system highly efficient and intelligent.
Description
Technical field
The present invention relates to vision technique and depth learning technology field, specially a kind of insulation based on Fast R-CNN
Sub- fault detection method.
Background technology
Insulator is the device to play an important role in overhead transmission line, plays the works such as electric insulation and circuit support
With.Once insulator is damaged, the reliability service of transmission line of electricity can be seriously threatened.According to statistics, caused by insulator breakdown
Trip accident accounts for the 81.3% of current power transmission line accident, thus for insulator fault detect to transmission line safety and
Reliability is significant.During current power transmission circuit line walking, artificial line walking take, effort and it is dangerous, can not estimate
Cable lightning stroke insulation damages, insulator contamination and breakage.Unmanned air vehicle technique and airmanship and wireless communication skill in recent years
The fast-developing and continuous maturation of art, both at home and abroad many electric power enterprises trial carry out electric system line walking using unmanned plane auxiliary.
However to these mass image datas using the interpretation of staff's naked eyes without automated image analysis function, easily occur tight
The detection erroneous judgement of weight or situation of failing to judge, it is difficult to it is accurate to find security risk existing for transmission line of electricity, and substantially increase maintenance
Cost.Therefore it is very important using the automatic fault detection method of image processing techniques research power-line patrolling, it can be improved
The accuracy of detection, and keep airflight platform inspection system highly efficient and intelligent.
The country is broadly divided into three kinds for the image processing techniques of insulator at present：One, based on color threshold segmentation
Method extracts insulation sub-goal by Threshold segmentation on saturation degree component, but can not exclude saturation degree component and insulation
The interference that son is close and brings；Two, it is based on contours extract, by detecting that the circular contour of sub-pieces carries out ellipse fitting,
To carry out the positioning to insulator, but the changes such as affine, perspective, translation can occur for insulation subgraph captured in the process of taking photo by plane
It changes, shooting angle and shooting distance can all influence positioning of this method to insulator.Three, textural characteristics are based on, it is exhausted by extracting
The textural characteristics of edge carry out the detection positioning of insulator, but computationally intensive based on textural characteristics method, and it is simple to be suitable only for background
Detection, however the insulator background taken photo by plane is complicated, is easy to happen error detection, application is not strong.Existing method is all from insulation
The single feature of son is detected, and is not detected comprehensively from the feature of insulator, causes false drop rate high, without too big reality
Border meaning.
In computer vision field, CNN (Convolutional Neural Network) has played outstanding performance,
This mainly has benefited from the special networks structure it is suitable for image data.Faster R-CNN（Faster Regions with
Convolutional Neural Network）Basic structure be still convolutional neural networks, the application in image is exactly
The position that target in figure is likely to occur is found out in advance, by using information such as texture, edge, colors in image, ensures selecting
Take less window（Thousands of even hundreds of）In the case of keep higher recall rate.Faster R-CNN methods are not only from mesh
Target color（Color histogram）And texture（Histogram of gradients）, and from the more Color Channels of various features to Objective extraction feature,
Even if having noise and environmental disturbances, remain to keep accurately discrimination, this for insulator in the case of background complexity still
Higher discrimination can be kept significant, and can also effectively identify insulator breakdown, there is good answer to electric inspection process
Use foreground.
Invention content
The purpose of the present invention is to provide a kind of insulator breakdown detection methods based on Fast R-CNN, pass through skill of taking photo by plane
The automatic fault detection of insulator is realized in the combination of art and Faster R-CNN technologies.
To achieve the above object, the technical scheme is that：A kind of insulator breakdown detection based on Fast R-CNN
Method, this method realize the insulator device to transmission line of electricity by the combination of the technology of taking photo by plane and Faster R-CNN technologies
Part carries out fault identification and orients fault point while detecting fault type.
In an embodiment of the present invention, steps are as follows for this method specific implementation,
S1, transmission line of electricity image information is acquired by unmanned plane；
S2, insulator classification and Detection：First using the insulator in parts of images as training sample, and using in Fast R-CNN
Convolution kernel extract insulator include color, profile, texture feature be trained as feature vector；When detection, pass through
It may be the encirclement frame of target that region, which proposes that network generates on the image, and the model after training can sentence these encirclement frames
It is fixed, it detects whether for target insulator, to orient picture position where insulator, and pass through the grader in Fast R-CNN
Identify its classification；
S3, insulator breakdown positioning：Training process, with insulation subclassification, is fallen to go here and there failure due to working as insulator, is fallen with detection
Displacement is set to be had differences with other sub-pieces, therefore includes wheel by extracting it based on the convolution kernel in Fast R-CNN
Wide, texture feature can detect that insulator falls to go here and there guilty culprit encirclement frame, and orient abort situation
In an embodiment of the present invention, this method can also be used to the Electricity Department that detection includes conductor spacer, grading ring, stockbridge damper
Part.
In an embodiment of the present invention, in the step S1, additionally it is possible to acquire power transmission line by robot or camera apparatus
Road image information.
Compared to the prior art, the invention has the advantages that：The invention reside in by unmanned plane and Faster R-
CNN technologies are combined, then a variety of by Faster R-CNN target detections first by the acquisition to insulator device image
Insulate subgraph, realizes the classification to the subcategory that insulate, and finally realizes framing to the insulation subgraph classified, and pass through
Characteristics of image identifies the failure of insulator, and then reaches the fault detect to insulator, dramatically saves the cost of overhaul, makes to patrol
Linear system system is highly efficient and intelligent.
Description of the drawings
Fig. 1 insulator breakdown overhaul flow charts.
Fig. 2 Faster R-CNN work flow diagrams.
Fig. 3 Faster R-CNN network structures.
Specific implementation mode
Below in conjunction with the accompanying drawings, technical scheme of the present invention is specifically described.
A kind of insulator breakdown detection method based on Fast R-CNN of the present invention, this method by the technology of taking photo by plane and
The combination of Faster R-CNN technologies is realized and carries out fault identification and position to be out of order to the insulator device of transmission line of electricity
Put while detecting fault type, steps are as follows for this method specific implementation,
S1, transmission line of electricity image information is acquired by unmanned plane；
S2, insulator classification and Detection：First using the insulator in parts of images as training sample, and using in Fast R-CNN
Convolution kernel extract insulation sub-color, profile, Texture eigenvalue are trained as feature vector.When detection, pass through region
It may be the encirclement frame of target to propose that network generates on the image, and the model after training can judge these encirclement frames, examine
Whether survey is target insulator, and can be effectively applicable to the image detection of glass insulator and composite insulator can orient insulator
Place picture position, and its classification is identified by the grader in Fast R-CNN；
S3, insulator breakdown positioning：Training process, with insulation subclassification, is fallen to go here and there failure due to working as insulator, is fallen with detection
Displacement is set to be had differences with other sub-pieces, therefore by extracting its profile, line based on the convolution kernel in Fast R-CNN
The features such as reason can detect that insulator falls to go here and there guilty culprit encirclement frame, and orient abort situation.
This method can also be used to the power components that detection includes conductor spacer, grading ring, stockbridge damper.
In the step S1, additionally it is possible to acquire transmission line of electricity image information by robot or camera apparatus.
It is the specific implementation process of the present invention below.
Insulator breakdown detection based on Faster R-CNN is divided into two detection process：Insulator classification and Detection and insulation
Sub- fault location.Work flow diagram has most as shown in Figure 1, for the magnanimity photo that unmanned plane transmission line of electricity is taken photo by plane
Photo cannot be used for detecting insulator breakdown, therefore by insulator classification and Detection, a little magnanimity photos progress intelligent screening is gone forward side by side
Row classification lays the foundation to carry out fault detect in next step.The training positive sample of insulator classification and Detection module is various classifications
Insulator chain, it is energy saving in complex background to reach identification.For the photo that classifying screen is selected, carry out insulator breakdown detection with
Positioning, the training positive sample of the module are the fault point of insulator, thus can be used for the fault condition of insulator missing or explosion into
Row localization of fault, and outline fault point with encirclement frame in the figure of faulty insulator and show fault type, accomplish to insulate
The intelligent measurement of sub- failure.
Faster R-CNN work flow diagrams are as shown in Fig. 2, Faster-CNN methods include 2 CNN networks：Region carries
Discuss network RPN（Regional Proposal Network）Network is detected with Fast R-CNN.Wherein RPN is full convolution net
Network, core concept are proposed using the direct generating region of convolutional neural networks, generated in picture it is a series of it is multiple dimensioned how long
The candidate frame of wide ratio.Fast R-CNN are detected based on the RPN candidate frames extracted and are identified target therein.Fig. 3 is Faster R-
CNN network structures, specific detection process are as follows：The image of input operates first by rolling up base by convolution sum pondization, contracting
Subtract picture size and depth extraction characteristics of image, form characteristic pattern in last Ceng Juan base, characteristic pattern is input picture
Deep layer convolution feature, the further feature of similar object are sufficiently close to；Further feature without similar object is widely different, i.e., in spy
The upper object of sign figure has good separability.RPN networks carry out window sliding on characteristic pattern, extract a series of candidate frames,
And judge window for target or background.Network is detected finally by Fast R-CNN, which equally carries out characteristic pattern special
The candidate frame that the provincial characteristics of extraction and RPN are extracted is passed through pooling layers of ROI by sign extraction together, and pooling layers of ROI is same
When collect characteristic pattern and candidate frame, and carry out Region Feature Extraction, and be sent to subsequent two layers full articulamentum and pass through
Softmax judges target category, while the position of image where display target, and is modified to detection block so that detection block
Position it is more accurate.Faster R-CNN methods can be classified and be positioned, and can find out position and the identification of insulator simultaneously
Its type similarly can also carry out insulator breakdown type batch processing, efficiently intelligence.
The above are preferred embodiments of the present invention, all any changes made according to the technical solution of the present invention, and generated function is made
When with range without departing from technical solution of the present invention, all belong to the scope of protection of the present invention.
Claims (4)
1. a kind of insulator breakdown detection method based on Fast R-CNN, it is characterised in that：This method by the technology of taking photo by plane and
The combination of Faster R-CNN technologies is realized and carries out fault identification and position to be out of order to the insulator device of transmission line of electricity
It puts while detecting fault type.
2. a kind of insulator breakdown detection method based on Fast R-CNN according to claim 1, it is characterised in that：It should
Steps are as follows for method specific implementation,
S1, transmission line of electricity image information is acquired by unmanned plane；
S2, insulator classification and Detection：First using the insulator in parts of images as training sample, and using in Fast R-CNN
Convolution kernel extract insulator include color, profile, texture feature be trained as feature vector；When detection, pass through
It may be the encirclement frame of target that region, which proposes that network generates on the image, and the model after training can sentence these encirclement frames
It is fixed, it detects whether for target insulator, to orient picture position where insulator, and pass through the grader in Fast R-CNN
Identify its classification；
S3, insulator breakdown positioning：Training process, with insulation subclassification, is fallen to go here and there failure due to working as insulator, is fallen with detection
Displacement is set to be had differences with other sub-pieces, therefore includes wheel by extracting it based on the convolution kernel in Fast R-CNN
Wide, texture feature can detect that insulator falls to go here and there guilty culprit encirclement frame, and orient abort situation.
3. a kind of insulator breakdown detection method based on Fast R-CNN according to claim 1 or 2, feature exist
In：This method can also be used to the power components that detection includes conductor spacer, grading ring, stockbridge damper.
4. a kind of insulator breakdown detection method based on Fast R-CNN according to claim 2, it is characterised in that：Institute
It states in step S1, additionally it is possible to which transmission line of electricity image information is acquired by robot or camera apparatus.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810038127.0A CN108280855A (en) | 2018-01-13 | 2018-01-13 | A kind of insulator breakdown detection method based on Fast R-CNN |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810038127.0A CN108280855A (en) | 2018-01-13 | 2018-01-13 | A kind of insulator breakdown detection method based on Fast R-CNN |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108280855A true CN108280855A (en) | 2018-07-13 |
Family
ID=62803633
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810038127.0A Pending CN108280855A (en) | 2018-01-13 | 2018-01-13 | A kind of insulator breakdown detection method based on Fast R-CNN |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108280855A (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109165318A (en) * | 2018-08-13 | 2019-01-08 | 洛阳视距智能科技有限公司 | A kind of damper data set construction method towards intelligent patrol detection |
| CN109325539A (en) * | 2018-09-30 | 2019-02-12 | 云南电网有限责任公司普洱供电局 | Insulator falls crosstalk detecting method and device |
| CN109685761A (en) * | 2018-11-08 | 2019-04-26 | 宁波送变电建设有限公司甬城配电网建设分公司 | A kind of power cable defect inspection method and its detection system based on cloud platform |
| CN109709452A (en) * | 2018-12-21 | 2019-05-03 | 深圳供电局有限公司 | Insulator detection method, system and device of power transmission line |
| CN109765462A (en) * | 2019-03-05 | 2019-05-17 | 国家电网有限公司 | Fault detection method, device and the terminal device of transmission line of electricity |
| CN109767427A (en) * | 2018-12-25 | 2019-05-17 | 北京交通大学 | The detection method of train rail fastener defect |
| CN109801284A (en) * | 2019-01-25 | 2019-05-24 | 华中科技大学 | A kind of high iron catenary insulator breakdown detection method based on deep learning |
| CN109815798A (en) * | 2018-12-17 | 2019-05-28 | 广东电网有限责任公司 | Unmanned plane image processing method and system |
| CN110119771A (en) * | 2019-04-29 | 2019-08-13 | 杭州电子科技大学上虞科学与工程研究院有限公司 | Ultra-high-tension power transmission line stockbridge damper detection method based on assemblage characteristic and cascade classifier |
| CN110378221A (en) * | 2019-06-14 | 2019-10-25 | 安徽南瑞继远电网技术有限公司 | A kind of power grid wire clamp detects and defect identification method and device automatically |
| CN110826413A (en) * | 2019-10-10 | 2020-02-21 | 深圳供电局有限公司 | Transmission line damper fault detection method and system and storage medium |
| CN111382766A (en) * | 2018-12-29 | 2020-07-07 | 中国科学院沈阳计算技术研究所有限公司 | Equipment fault detection method based on fast R-CNN |
| CN111402253A (en) * | 2020-04-03 | 2020-07-10 | 华东交通大学 | Online monitoring method for state of power transmission and transformation equipment integrating edge calculation and deep learning |
| CN111428567A (en) * | 2020-02-26 | 2020-07-17 | 沈阳大学 | Pedestrian tracking system and method based on affine multi-task regression |
| CN111812096A (en) * | 2020-06-02 | 2020-10-23 | 国网浙江嘉善县供电有限公司 | Rapid positioning intelligent image detection method for insulator arc burn |
| CN111833347A (en) * | 2020-07-31 | 2020-10-27 | 广东电网有限责任公司 | Transmission line damper defect detection method and related device |
| CN111914720A (en) * | 2020-07-27 | 2020-11-10 | 长江大学 | Method and device for identifying insulator burst of power transmission line |
| CN112102236A (en) * | 2020-08-07 | 2020-12-18 | 东南大学 | Polycrystalline subfissure detection method based on two deep stages |
| CN112766107A (en) * | 2021-01-08 | 2021-05-07 | 武汉大学 | High-voltage cable state detection method based on multi-source heterogeneous data fusion |
| CN113538411A (en) * | 2021-08-06 | 2021-10-22 | 广东电网有限责任公司 | Insulator defect detection method and device |
| CN113538412A (en) * | 2021-08-06 | 2021-10-22 | 广东电网有限责任公司 | Insulator defect detection method and device for aerial image |
| CN115761453A (en) * | 2022-10-20 | 2023-03-07 | 浙江大学 | Power inspection scene-oriented light-weight single-sample target detection method based on feature matching |
| CN113538411B (en) * | 2021-08-06 | 2024-10-18 | 广东电网有限责任公司 | Insulator defect detection method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106504233A (en) * | 2016-10-18 | 2017-03-15 | 国网山东省电力公司电力科学研究院 | Image electric power widget recognition methodss and system are patrolled and examined based on the unmanned plane of Faster R CNN |
| CN106599939A (en) * | 2016-12-30 | 2017-04-26 | 深圳市唯特视科技有限公司 | Real-time target detection method based on region convolutional neural network |
| CN106874890A (en) * | 2017-03-16 | 2017-06-20 | 天津大学 | A kind of method of insulator missing in identification transmission line of electricity based on Aerial Images |
| CN106877237A (en) * | 2017-03-16 | 2017-06-20 | 天津大学 | A kind of method of insulator missing in detection transmission line of electricity based on Aerial Images |
| CN107274451A (en) * | 2017-05-17 | 2017-10-20 | 北京工业大学 | Isolator detecting method and device based on shared convolutional neural networks |
| CN107392901A (en) * | 2017-07-24 | 2017-11-24 | 国网山东省电力公司信息通信公司 | A kind of method for transmission line part intelligence automatic identification |
-
2018
- 2018-01-13 CN CN201810038127.0A patent/CN108280855A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106504233A (en) * | 2016-10-18 | 2017-03-15 | 国网山东省电力公司电力科学研究院 | Image electric power widget recognition methodss and system are patrolled and examined based on the unmanned plane of Faster R CNN |
| CN106599939A (en) * | 2016-12-30 | 2017-04-26 | 深圳市唯特视科技有限公司 | Real-time target detection method based on region convolutional neural network |
| CN106874890A (en) * | 2017-03-16 | 2017-06-20 | 天津大学 | A kind of method of insulator missing in identification transmission line of electricity based on Aerial Images |
| CN106877237A (en) * | 2017-03-16 | 2017-06-20 | 天津大学 | A kind of method of insulator missing in detection transmission line of electricity based on Aerial Images |
| CN107274451A (en) * | 2017-05-17 | 2017-10-20 | 北京工业大学 | Isolator detecting method and device based on shared convolutional neural networks |
| CN107392901A (en) * | 2017-07-24 | 2017-11-24 | 国网山东省电力公司信息通信公司 | A kind of method for transmission line part intelligence automatic identification |
Non-Patent Citations (1)
| Title |
|---|
| 王万国等: "基于 RCNN的无人机巡检图像电力小部件识别研究", 《地球信息科学》 * |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109165318A (en) * | 2018-08-13 | 2019-01-08 | 洛阳视距智能科技有限公司 | A kind of damper data set construction method towards intelligent patrol detection |
| CN109325539A (en) * | 2018-09-30 | 2019-02-12 | 云南电网有限责任公司普洱供电局 | Insulator falls crosstalk detecting method and device |
| CN109685761A (en) * | 2018-11-08 | 2019-04-26 | 宁波送变电建设有限公司甬城配电网建设分公司 | A kind of power cable defect inspection method and its detection system based on cloud platform |
| CN109685761B (en) * | 2018-11-08 | 2020-09-22 | 宁波送变电建设有限公司甬城配电网建设分公司 | Power cable defect detection method and detection system based on cloud platform |
| CN109815798A (en) * | 2018-12-17 | 2019-05-28 | 广东电网有限责任公司 | Unmanned plane image processing method and system |
| CN109709452A (en) * | 2018-12-21 | 2019-05-03 | 深圳供电局有限公司 | Insulator detection method, system and device of power transmission line |
| CN109767427A (en) * | 2018-12-25 | 2019-05-17 | 北京交通大学 | The detection method of train rail fastener defect |
| CN111382766A (en) * | 2018-12-29 | 2020-07-07 | 中国科学院沈阳计算技术研究所有限公司 | Equipment fault detection method based on fast R-CNN |
| CN109801284A (en) * | 2019-01-25 | 2019-05-24 | 华中科技大学 | A kind of high iron catenary insulator breakdown detection method based on deep learning |
| CN109765462A (en) * | 2019-03-05 | 2019-05-17 | 国家电网有限公司 | Fault detection method, device and the terminal device of transmission line of electricity |
| CN110119771A (en) * | 2019-04-29 | 2019-08-13 | 杭州电子科技大学上虞科学与工程研究院有限公司 | Ultra-high-tension power transmission line stockbridge damper detection method based on assemblage characteristic and cascade classifier |
| CN110119771B (en) * | 2019-04-29 | 2020-12-22 | 杭州电子科技大学上虞科学与工程研究院有限公司 | High-voltage transmission line vibration damper detection method based on combination characteristics and cascade classifier |
| CN110378221A (en) * | 2019-06-14 | 2019-10-25 | 安徽南瑞继远电网技术有限公司 | A kind of power grid wire clamp detects and defect identification method and device automatically |
| CN110826413B (en) * | 2019-10-10 | 2022-01-25 | 深圳供电局有限公司 | Transmission line damper fault detection method and system and storage medium |
| CN110826413A (en) * | 2019-10-10 | 2020-02-21 | 深圳供电局有限公司 | Transmission line damper fault detection method and system and storage medium |
| CN111428567B (en) * | 2020-02-26 | 2024-02-02 | 沈阳大学 | Pedestrian tracking system and method based on affine multitask regression |
| CN111428567A (en) * | 2020-02-26 | 2020-07-17 | 沈阳大学 | Pedestrian tracking system and method based on affine multi-task regression |
| CN111402253A (en) * | 2020-04-03 | 2020-07-10 | 华东交通大学 | Online monitoring method for state of power transmission and transformation equipment integrating edge calculation and deep learning |
| CN111812096A (en) * | 2020-06-02 | 2020-10-23 | 国网浙江嘉善县供电有限公司 | Rapid positioning intelligent image detection method for insulator arc burn |
| CN111914720A (en) * | 2020-07-27 | 2020-11-10 | 长江大学 | Method and device for identifying insulator burst of power transmission line |
| CN111833347A (en) * | 2020-07-31 | 2020-10-27 | 广东电网有限责任公司 | Transmission line damper defect detection method and related device |
| CN112102236A (en) * | 2020-08-07 | 2020-12-18 | 东南大学 | Polycrystalline subfissure detection method based on two deep stages |
| CN112766107A (en) * | 2021-01-08 | 2021-05-07 | 武汉大学 | High-voltage cable state detection method based on multi-source heterogeneous data fusion |
| CN113538411A (en) * | 2021-08-06 | 2021-10-22 | 广东电网有限责任公司 | Insulator defect detection method and device |
| CN113538412A (en) * | 2021-08-06 | 2021-10-22 | 广东电网有限责任公司 | Insulator defect detection method and device for aerial image |
| CN113538412B (en) * | 2021-08-06 | 2024-08-02 | 广东电网有限责任公司 | Insulator defect detection method and device for aerial image |
| CN113538411B (en) * | 2021-08-06 | 2024-10-18 | 广东电网有限责任公司 | Insulator defect detection method and device |
| CN115761453A (en) * | 2022-10-20 | 2023-03-07 | 浙江大学 | Power inspection scene-oriented light-weight single-sample target detection method based on feature matching |
| CN115761453B (en) * | 2022-10-20 | 2023-08-04 | 浙江大学 | Feature matching-based light single sample target detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108280855A (en) | A kind of insulator breakdown detection method based on Fast R-CNN | |
| CN112199993B (en) | Method for identifying transformer substation insulator infrared image detection model in any direction based on artificial intelligence | |
| CN109118479B (en) | Capsule network-based insulator defect identification and positioning device and method | |
| CN105744232B (en) | A kind of method of the transmission line of electricity video external force damage prevention of Behavior-based control analytical technology | |
| CN103279765B (en) | Steel wire rope surface damage detection method based on images match | |
| CN111080598B (en) | Bolt and nut missing detection method for coupler yoke key safety crane | |
| CN111784633B (en) | Insulator defect automatic detection algorithm for electric power inspection video | |
| CN107123131B (en) | Moving target detection method based on deep learning | |
| CN105741291B (en) | A kind of high-speed railway touching net suspension arrangement equipotential line fault detection method | |
| CN108022235A (en) | High-voltage power transmission tower critical component defect identification method | |
| CN111339883A (en) | Method for identifying and detecting abnormal behaviors in transformer substation based on artificial intelligence in complex scene | |
| CN111814686A (en) | Vision-based power transmission line identification and foreign matter invasion online detection method | |
| CN109176513B (en) | A kind of method for inspecting and cruising inspection system of intelligent inspection robot | |
| CN112528979B (en) | Transformer substation inspection robot obstacle distinguishing method and system | |
| CN111260629A (en) | Pantograph structure abnormity detection algorithm based on image processing | |
| CN108288055A (en) | Block of bow collector of electric locomotive based on depth network and placement test and arc method for measuring | |
| CN109766746A (en) | A kind of track foreign matter detecting method of unmanned plane video | |
| CN107833211A (en) | Zero resistance insulator automatic testing method and device based on infrared image | |
| CN106339657A (en) | Straw incineration monitoring method and device based on monitoring video | |
| CN105096305A (en) | Method and device for analyzing state of insulator | |
| CN114694050A (en) | Power equipment running state detection method based on infrared image | |
| CN112508911A (en) | Rail joint touch net suspension support component crack detection system based on inspection robot and detection method thereof | |
| CN106920240A (en) | A kind of insulator identification and method for diagnosing faults based on infrared image | |
| CN117557570A (en) | Rail vehicle abnormality detection method and system | |
| CN117423018A (en) | Power equipment detection system and method based on unmanned aerial vehicle acquisition multi-mode source fusion |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180713 |