CN111046943A - Method and system for automatically identifying state of isolation switch of transformer substation - Google Patents
Method and system for automatically identifying state of isolation switch of transformer substation Download PDFInfo
- Publication number
- CN111046943A CN111046943A CN201911253589.5A CN201911253589A CN111046943A CN 111046943 A CN111046943 A CN 111046943A CN 201911253589 A CN201911253589 A CN 201911253589A CN 111046943 A CN111046943 A CN 111046943A
- Authority
- CN
- China
- Prior art keywords
- image
- isolation switch
- state
- switch
- isolation
- 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
- 238000002955 isolation Methods 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 27
- 238000012545 processing Methods 0.000 claims abstract description 26
- 238000012549 training Methods 0.000 claims abstract description 10
- 238000013135 deep learning Methods 0.000 claims description 24
- 238000007689 inspection Methods 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 12
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 6
- 238000011176 pooling Methods 0.000 claims description 5
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 229910052744 lithium Inorganic materials 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
Abstract
The utility model provides a transformer substation isolation switch state automatic identification method and system, including patrolling and examining robot, processing system and control system, it is provided with binocular camera on the robot to patrol and examine, binocular camera is used for gathering the image of transformer substation isolation switch, control system control patrols and examines the removal of robot to transmit the image for processing system, processing system is configured into and constructs the degree of depth learning algorithm model, and according to the image of the isolation switch state identification of off-line collection, the artifical isolation switch mark that carries out, trains mark data, utilizes the degree of depth learning algorithm model after the training to the isolation switch image that the on-line obtained, handles, obtains the kind, the position and the state that opens and shuts of switch.
Description
Technical Field
The disclosure belongs to the technical field of isolation switch automatic state identification, and particularly relates to a transformer substation isolation switch state automatic identification method and system.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
With the rapid development of technologies such as image processing and computer vision, the positioning and identification of the transformer substation isolation disconnecting link are made possible through a camera and a traditional computer vision algorithm. The state of the isolation disconnecting link is detected by fixing mechanical equipment and a sensor, and different types of isolation disconnecting links cannot be distinguished well, but the mode has higher cost and is not flexible enough, so that the isolation disconnecting link is not convenient to popularize generally.
Disclosure of Invention
The method and the system can automatically identify the type of the disconnecting link, position the disconnecting link and judge the opening and closing state of the disconnecting link under multiple scenes. The intelligent identification of the state of the isolation disconnecting link can greatly save the labor operation and maintenance investment in the station, and the construction pace of the intelligent transformer substation is promoted.
According to some embodiments, the following technical scheme is adopted in the disclosure:
the utility model provides a transformer substation's isolation switch state automatic identification system, is including patrolling and examining robot, processing system and control system, it is provided with binocular camera on the robot to patrol and examine, binocular camera is used for gathering the image that transformer substation kept apart the switch, control system controls patrols and examines the removal of robot to give processing system with the image transmission, processing system is configured into and constructs the degree of deep learning algorithm model, according to the image of the isolation switch state identification of off-line collection, and the manual work keeps apart the switch mark, trains mark data, utilizes the degree of deep learning algorithm model after the training to the isolation switch image that the on-line obtained, handles, obtains the kind, the position and the state that opens and shuts of switch.
The processing system is a deep learning algorithm model carried on the inspection robot.
The inspection robot is provided with a power supply system, and the power supply system is used for supplying power to the inspection robot, the processing system and the control system.
A transformer substation isolation switch state automatic identification method comprises the following steps:
acquiring an image for identifying the state of the isolation switch off line, manually marking the isolation switch, and training marked data by using a deep learning algorithm model to identify the type and the state of the isolation switch;
deploying the trained deep learning algorithm model to the transformer substation inspection robot to enable the transformer substation inspection robot to have an identification function;
and receiving a picture of the inspection robot on the isolation switch at the set position, and processing the image by using the trained deep learning algorithm model to obtain the type, position and opening and closing state of the switch.
The specific process of training the labeled data by the deep learning algorithm model to identify the type and the state of the knife switch comprises the following steps:
the method comprises the steps that an intelligent inspection robot of a transformer substation acquires images of isolation switches under various scenes, and manually marks the types, positions and opening and closing states of the isolation switches;
constructing a deep convolutional neural network, extracting image characteristics by using a convolutional layer, reducing image space dimensionality by using a pooling layer, enhancing the expression capability of the network by using a residual error layer, and finally abstracting an image into a G x G characteristic grid;
generating 4 candidate frames for each grid, and predicting 5 quantities for each candidate frame, wherein the quantities are respectively an x-axis central point, a y-axis central point, a knife gate width w, a height h and a confidence probability p of the knife gate;
constructing a neural network loss function;
and continuously training the neural network through forward propagation and backward propagation to obtain the recognition model.
A computer readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor of terminal equipment and executing the automatic substation isolation disconnecting link state identification method.
A terminal device comprising a processor and a computer readable storage medium, the processor being configured to implement instructions; the computer readable storage medium is used for storing a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the automatic substation isolation disconnecting link state identification method.
Compared with the prior art, the beneficial effect of this disclosure is:
the utility model provides a method and a system for automatically identifying the state of a transformer substation isolation switch, which can automatically identify the type, state and position of the transformer substation isolation switch and improve the inspection efficiency of a robot; the method realizes one-time identification of a plurality of target devices in one image, overcomes the complex configuration of the traditional disconnecting link identification, and saves a large amount of labor.
The method can automatically identify the type, the position and the opening and closing state of one or more isolation switches in the image, and realize intelligent identification.
The method uses a deep learning algorithm to construct a residual error network model, realizes one-time identification of multiple types of disconnecting links in the same visual field, and can realize positioning, type identification and state identification automatic identification of the disconnecting links at the same time; the method is suitable for various illumination conditions, the shooting angle and the recognition accuracy are high.
The method and the device have the advantages that the GPU is used for acceleration, the calculation speed is high, and the requirement of real-time calculation can be met.
The method for deep learning is an end-to-end process, the method does not need to be mixed with the traditional algorithm, development flexibility and optimization are enhanced, the neural network uses simple convolution and pooling operations, and also has operations of residual error, multi-path convolution and the like, and the expression capability and the identification accuracy of the network are enhanced.
This openly collects switch kind discernment, switch position location, three kinds of functions in an organic whole of switch open and shut state discernment, greatly alleviateed the flow, time and the human cost of development. And the grid is directly regressed by using a neural network instead of a sliding window form, and the context information of the whole image is considered, so that the identification, the positioning and the classification are more accurate.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure and are not to limit the disclosure.
Fig. 1 is an architectural diagram of the present disclosure.
The specific implementation mode is as follows:
the present disclosure is further described with reference to the following drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The utility model provides a transformer substation isolation switch state automatic identification method based on degree of depth study can be under the multi-scene automatic identification switch's kind, fix a position out the position of switch, judge out the state that opens and shuts of switch. The intelligent identification of the state of the isolation disconnecting link can greatly save the labor operation and maintenance investment in the station, and the construction pace of the intelligent transformer substation is promoted.
The transformer substation isolation disconnecting link is shot through a high-definition camera installed on the transformer substation inspection robot, the inspection robot carries out real-time calculation on a shot image through a high-performance deep learning embedded processing module, and the type, the position and the opening and closing state of the isolation disconnecting link in the image are obtained. And the recognition result is transmitted back to the back-end control center.
The system comprises the following parts:
robot is patrolled and examined to intelligence: the transformer substation self-powered inspection robot is provided with a binocular camera;
the control system comprises: controlling the inspection robot to move and coordinating the interaction of other modules;
a camera: the high-definition camera is responsible for acquiring the knife switch image;
the deep learning calculation module: and carrying a high-performance embedded processing module of the GPU.
Of course, a power supply system is also included in some embodiments: a rechargeable lithium battery module.
The processing procedure of the system specifically comprises the following steps:
step 1: the method comprises the steps of collecting images for identifying the state of the isolation switch off line, marking the isolation switch off line manually, and training marked data by using a deep learning algorithm model, so that the type and the state of the isolation switch can be identified.
Step 2: and (3) deploying the deep learning algorithm model trained in the step (1) to the transformer substation inspection robot to enable the transformer substation inspection robot to have an identification function.
And step 3: and after the inspection robot moves to a fixed position, the isolation switch is photographed, and the photographed picture is transmitted to the robot deep learning calculation module.
And 4, step 4: and (3) processing the image by using the algorithm model trained in the step (1) by using the deep learning module to obtain the type, the position and the opening and closing state of the disconnecting link.
And 5: and the inspection robot transmits the detection data to the rear-end control center in real time.
A computer readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor of terminal equipment and executing the automatic substation isolation disconnecting link state identification method.
A terminal device comprising a processor and a computer readable storage medium, the processor being configured to implement instructions; the computer readable storage medium is used for storing a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the automatic substation isolation disconnecting link state identification method.
The method for deep learning is an end-to-end process, and does not need to be mixed with the traditional algorithm, so that the flexibility and the optimization of algorithm development are enhanced, the neural network uses simple convolution and pooling operations, and also has operations of residual error, multipath convolution and the like, and the expression capability and the identification precision of the network are enhanced. The algorithm in the patent integrates three functions of knife switch type identification, knife switch position location and knife switch opening and closing state identification (which type of knife switch, position coordinates and opening and closing state can be clearly output), and the development process, time and labor cost are greatly reduced. And the algorithm is not in a sliding window form, but is a grid regressed by a neural network directly, and the context information of the whole image is taken into account, so that the identification, the positioning and the classification are more accurate.
As will be appreciated by one skilled in the art, embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Although the present disclosure has been described with reference to specific embodiments, it should be understood that the scope of the present disclosure is not limited thereto, and those skilled in the art will appreciate that various modifications and changes can be made without departing from the spirit and scope of the present disclosure.
Claims (10)
1. The utility model provides a transformer substation's isolation switch state automatic identification system which characterized by: including patrolling and examining robot, processing system and control system, it is provided with binocular camera on the robot to patrol and examine, binocular camera is used for gathering the image of transformer substation's isolation switch, control system control patrols and examines the removal of robot to transmit the image for processing system, processing system is configured into the degree of deep learning algorithm model of founding, and according to the image of the isolation switch state discernment of off-line collection, the manual work is kept apart the switch mark, trains mark data, utilizes the degree of deep learning algorithm model after the training to the isolation switch image that the on-line acquireed, handles, obtains the kind, the position and the state that opens and shuts of switch.
2. The automatic substation disconnecting link state identification system according to claim 1, characterized in that: the processing system comprises a deep learning algorithm model carried on the inspection robot.
3. The automatic substation disconnecting link state identification system according to claim 1, characterized in that: be provided with power supply system on patrolling and examining the robot, power supply system contains patrols and examines robot, processing system and control power supply system.
4. The automatic substation disconnecting link state identification system according to claim 1, characterized in that:
the processing system is configured to receive the pictures of the inspection robot on the isolation switch at the set position, and the images are processed by using the trained deep learning algorithm model to obtain the type, the position and the opening and closing state of the switch.
5. The automatic substation disconnecting link state identification system according to claim 4, wherein:
constructing a deep convolutional neural network, extracting image characteristics by using a convolutional layer, reducing image space dimensionality by using a pooling layer, enhancing the expression capability of the network by using a residual error layer, and finally abstracting an image into an GxG characteristic grid;
each grid generates 4 candidate boxes, each of which predicts 5 quantities, respectively the x-axis center point, the y-axis center point, the knife width w, the height h, and the confidence probability p of the knife.
6. The automatic substation disconnecting link state identification system according to claim 4, wherein:
the processing system is configured to construct a neural network loss function and to continuously train the neural network through forward propagation and backward propagation, resulting in a recognition model.
7. A transformer substation isolation switch state automatic identification method is characterized in that: the method comprises the following steps:
acquiring an image for identifying the state of the isolation switch off line, manually marking the isolation switch, and training marked data by using a deep learning algorithm model to identify the type and the state of the isolation switch;
deploying the trained deep learning algorithm model to the transformer substation inspection robot to enable the transformer substation inspection robot to have an identification function;
and receiving a picture of the inspection robot on the isolation switch at the set position, and processing the image by using the trained deep learning algorithm model to obtain the type, position and opening and closing state of the switch.
8. The method for automatically identifying the state of the transformer substation disconnecting link according to claim 7, wherein the method comprises the following steps: the specific process of training the labeled data by the deep learning algorithm model to identify the type and the state of the knife switch comprises the following steps:
the method comprises the steps that an intelligent inspection robot of a transformer substation acquires images of isolation switches under various scenes, and manually marks the types, positions and opening and closing states of the isolation switches;
constructing a deep convolutional neural network, extracting image characteristics by using a convolutional layer, reducing image space dimensionality by using a pooling layer, enhancing the expression capability of the network by using a residual error layer, and finally abstracting an image into an GxG characteristic grid;
generating 4 candidate frames for each grid, and predicting 5 quantities for each candidate frame, wherein the quantities are respectively an x-axis central point, a y-axis central point, a knife gate width w, a height h and a confidence probability p of the knife gate;
constructing a neural network loss function;
and continuously training the neural network through forward propagation and backward propagation to obtain the recognition model.
9. A computer-readable storage medium characterized by: a plurality of instructions are stored, and the instructions are suitable for being loaded by a processor of a terminal device and executing the automatic substation isolation disconnecting link state identification method in the claim 7 or 8.
10. A terminal device is characterized in that: the system comprises a processor and a computer readable storage medium, wherein the processor is used for realizing instructions; the computer readable storage medium is used for storing a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the automatic substation isolation disconnecting link state identification method in the claims 7 or 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911253589.5A CN111046943A (en) | 2019-12-09 | 2019-12-09 | Method and system for automatically identifying state of isolation switch of transformer substation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911253589.5A CN111046943A (en) | 2019-12-09 | 2019-12-09 | Method and system for automatically identifying state of isolation switch of transformer substation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111046943A true CN111046943A (en) | 2020-04-21 |
Family
ID=70235287
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911253589.5A Pending CN111046943A (en) | 2019-12-09 | 2019-12-09 | Method and system for automatically identifying state of isolation switch of transformer substation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111046943A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111654107A (en) * | 2020-06-11 | 2020-09-11 | 国家电网有限公司华东分部 | Equipment switch state analysis system based on image recognition |
| CN111814742A (en) * | 2020-07-29 | 2020-10-23 | 南方电网数字电网研究院有限公司 | Knife switch state identification method based on deep learning |
| CN111898481A (en) * | 2020-07-14 | 2020-11-06 | 济南信通达电气科技有限公司 | State identification method and device for pointer type opening and closing indicator |
| CN112001332A (en) * | 2020-08-26 | 2020-11-27 | 西安咏圣达电子科技有限公司 | Method, system, medium, equipment and application for monitoring working state of isolating switch |
| CN113221688A (en) * | 2021-04-28 | 2021-08-06 | 南京南瑞继保电气有限公司 | Disconnecting link state identification method and device and storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107256262A (en) * | 2017-06-13 | 2017-10-17 | 西安电子科技大学 | A kind of image search method based on object detection |
| CN107680195A (en) * | 2017-11-13 | 2018-02-09 | 国网内蒙古东部电力有限公司 | A kind of transformer station intelligent robot inspection Computer Aided Analysis System and method |
| CN107944396A (en) * | 2017-11-27 | 2018-04-20 | 国网安徽省电力有限公司经济技术研究院 | A kind of disconnecting link state identification method based on improvement deep learning |
| CN109063764A (en) * | 2018-07-26 | 2018-12-21 | 福建和盛高科技产业有限公司 | A kind of judgment method of disconnecting switch closing operation in place based on machine vision |
| CN109359636A (en) * | 2018-12-14 | 2019-02-19 | 腾讯科技（深圳）有限公司 | Video classification methods, device and server |
| CN109635806A (en) * | 2018-12-12 | 2019-04-16 | 国网重庆市电力公司信息通信分公司 | Ammeter technique for partitioning based on residual error network |
| CN109886295A (en) * | 2019-01-11 | 2019-06-14 | 平安科技（深圳）有限公司 | A kind of butterfly recognition methods neural network based and relevant device |
| CN110059556A (en) * | 2019-03-14 | 2019-07-26 | 天津大学 | A kind of transformer substation switch division condition detection method based on deep learning |
| CN110119677A (en) * | 2019-03-28 | 2019-08-13 | 东南大学 | Carbon fiber composite core cable damage testing method based on image classification network |
| KR102030628B1 (en) * | 2019-04-04 | 2019-10-10 | (주)아이엠시티 | Recognizing method and system of vehicle license plate based convolutional neural network |
| CN110334661A (en) * | 2019-07-09 | 2019-10-15 | 国网江苏省电力有限公司扬州供电分公司 | Infrared power transmission and transformation abnormal heating point target detecting method based on deep learning |
| CN114863311A (en) * | 2022-03-22 | 2022-08-05 | 国网山东省电力公司泰安供电公司 | Automatic tracking method and system for inspection target of transformer substation robot |
-
2019
- 2019-12-09 CN CN201911253589.5A patent/CN111046943A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107256262A (en) * | 2017-06-13 | 2017-10-17 | 西安电子科技大学 | A kind of image search method based on object detection |
| CN107680195A (en) * | 2017-11-13 | 2018-02-09 | 国网内蒙古东部电力有限公司 | A kind of transformer station intelligent robot inspection Computer Aided Analysis System and method |
| CN107944396A (en) * | 2017-11-27 | 2018-04-20 | 国网安徽省电力有限公司经济技术研究院 | A kind of disconnecting link state identification method based on improvement deep learning |
| CN109063764A (en) * | 2018-07-26 | 2018-12-21 | 福建和盛高科技产业有限公司 | A kind of judgment method of disconnecting switch closing operation in place based on machine vision |
| CN109635806A (en) * | 2018-12-12 | 2019-04-16 | 国网重庆市电力公司信息通信分公司 | Ammeter technique for partitioning based on residual error network |
| CN109359636A (en) * | 2018-12-14 | 2019-02-19 | 腾讯科技（深圳）有限公司 | Video classification methods, device and server |
| CN109886295A (en) * | 2019-01-11 | 2019-06-14 | 平安科技（深圳）有限公司 | A kind of butterfly recognition methods neural network based and relevant device |
| CN110059556A (en) * | 2019-03-14 | 2019-07-26 | 天津大学 | A kind of transformer substation switch division condition detection method based on deep learning |
| CN110119677A (en) * | 2019-03-28 | 2019-08-13 | 东南大学 | Carbon fiber composite core cable damage testing method based on image classification network |
| KR102030628B1 (en) * | 2019-04-04 | 2019-10-10 | (주)아이엠시티 | Recognizing method and system of vehicle license plate based convolutional neural network |
| CN110334661A (en) * | 2019-07-09 | 2019-10-15 | 国网江苏省电力有限公司扬州供电分公司 | Infrared power transmission and transformation abnormal heating point target detecting method based on deep learning |
| CN114863311A (en) * | 2022-03-22 | 2022-08-05 | 国网山东省电力公司泰安供电公司 | Automatic tracking method and system for inspection target of transformer substation robot |
Non-Patent Citations (4)
| Title |
|---|
| 温捷文;战荫伟;凌伟林;郭灿樟;: "实时目标检测算法YOLO的批再规范化处理" * |
| 郑远攀;李广阳;李晔;: "深度学习在图像识别中的应用研究综述" * |
| 马啸;邵利民;卢惠民;肖军浩;谷东亮;: "一种基于视觉感知的舰船目标智能化识别方法" * |
| 魏玮;蒲玮;刘依;: "改进YOLOv3在航拍目标检测中的应用" * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111654107A (en) * | 2020-06-11 | 2020-09-11 | 国家电网有限公司华东分部 | Equipment switch state analysis system based on image recognition |
| CN111898481A (en) * | 2020-07-14 | 2020-11-06 | 济南信通达电气科技有限公司 | State identification method and device for pointer type opening and closing indicator |
| CN111814742A (en) * | 2020-07-29 | 2020-10-23 | 南方电网数字电网研究院有限公司 | Knife switch state identification method based on deep learning |
| CN112001332A (en) * | 2020-08-26 | 2020-11-27 | 西安咏圣达电子科技有限公司 | Method, system, medium, equipment and application for monitoring working state of isolating switch |
| CN113221688A (en) * | 2021-04-28 | 2021-08-06 | 南京南瑞继保电气有限公司 | Disconnecting link state identification method and device and storage medium |
| CN113221688B (en) * | 2021-04-28 | 2024-03-19 | 南京南瑞继保电气有限公司 | Knife switch state identification method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111046943A (en) | Method and system for automatically identifying state of isolation switch of transformer substation | |
| CN110614638B (en) | Transformer substation inspection robot autonomous acquisition method and system | |
| CN111421539A (en) | Industrial part intelligent identification and sorting system based on computer vision | |
| CN110297498A (en) | A kind of rail polling method and system based on wireless charging unmanned plane | |
| CN107609502A (en) | Method and apparatus for controlling automatic driving vehicle | |
| CN111985352B (en) | AI front-end substation inspection video real-time identification method and system | |
| CN112270267B (en) | Camera shooting identification system capable of automatically capturing line faults | |
| CN109919331A (en) | A kind of airborne equipment intelligent maintaining auxiliary system and method | |
| CN110648319A (en) | Equipment image acquisition and diagnosis system and method based on double cameras | |
| CN108960134A (en) | A kind of patrol UAV image mark and intelligent identification Method | |
| CN202488597U (en) | Autonomous cooperation video monitor node apparatus for intelligent object identification and track | |
| CN109685017A (en) | A kind of ultrahigh speed real-time target detection system and detection method based on light weight neural network | |
| CN114550334A (en) | Bridge robot inspection teaching training system, method and storage medium | |
| US20230017444A1 (en) | Method for the computer-assisted learning of an artificial neural network for detecting structural features of objects | |
| CN115649501B (en) | Unmanned aerial vehicle night lighting system and method | |
| CN114202819B (en) | Substation inspection method, system and computer based on robot | |
| CN206544183U (en) | A kind of crusing robot system communicated based on wide area Internet | |
| CN208449603U (en) | A kind of cleaning table automatic detecting executive device based on manipulator | |
| CN114092624A (en) | Environment inspection system based on virtual technology | |
| CN206517529U (en) | A kind of unmanned aerial vehicle platform camera system | |
| CN106737638A (en) | One kind sorting cell-phone camera head positioning system and its location algorithm | |
| CN117111660A (en) | Unattended intelligent granary system and method | |
| CN116175586A (en) | Inspection robot and power inspection method and system based on inspection robot | |
| CN115661726A (en) | Autonomous video acquisition and analysis method for rail train workpiece assembly | |
| CN115118008A (en) | Transformer substation intelligent robot operation method |
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: 20200421 |