CN106022977A - Transformer substation job site safety analysis method - Google Patents
Transformer substation job site safety analysis method Download PDFInfo
- Publication number
- CN106022977A CN106022977A CN201610644792.5A CN201610644792A CN106022977A CN 106022977 A CN106022977 A CN 106022977A CN 201610644792 A CN201610644792 A CN 201610644792A CN 106022977 A CN106022977 A CN 106022977A
- Authority
- CN
- China
- Prior art keywords
- model
- transformer substation
- learning
- work
- degree
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention relates to a safety supervision technology for a transformer substation job site, in particular to a transformer substation job site safety analysis method. The problems that an existing transformer substation job site safety analysis method has multiple supervision dead zones and low supervision efficiency, and workloads of supervisors are large are solved. The transformer substation job site safety analysis method includes the following steps that video acquisition equipment is started; the video acquisition equipment acquires video data of the transformer substation job site in real time, and the acquired video data is sent to a video server in real time; the video server identifies the received video data in real time, and the identification result is sent to a computer and a center management server in real time; the computer displays the received identification result in real time; the center management server analyzes and processes the received visual identification result in real time, and a transformer substation scene database is established according to the analysis and processing result. The transformer substation job site safety analysis method is suitable for safety supervision of the transformer job site.
Description
Technical field
The present invention relates to the security control technology that work of transformer substation is on-the-spot, specifically a kind of work of transformer substation site safety analyzes method.
Background technology
The security control at work of transformer substation scene is most important link in work of transformer substation, and it is directly connected to the safety of substation equipment and staff.At present, the security control that work of transformer substation is on-the-spot is mainly artificially carried out by supervisor.But, owing to working site scope is big, staff is numerous, and supervisor's quantity is extremely limited, cause supervisor can only supervise in the way of random inspection, blind area is many, supervisory efficiency is low, supervisor's workload big thus to cause supervision, thus is difficult to ensure that the safety of substation equipment and staff.Based on this, it is necessary to invent a kind of brand-new monitoring administration method, to solve the problems referred to above that the on-the-spot monitoring administration method of existing work of transformer substation exists.
Summary of the invention
The present invention is to solve the monitoring administration method supervision problem that blind area is many, supervisory efficiency is low, supervisor's workload is big that existing work of transformer substation is on-the-spot, it is provided that a kind of work of transformer substation site safety analyzes method.
The present invention adopts the following technical scheme that realization:
A kind of work of transformer substation site safety analyzes method, and the method is to use following steps to realize:
Start video capture device；
The video data that video capture device Real-time Collection work of transformer substation is on-the-spot, and the video data collected is sent in real time to video server；
The video server video data to receiving carries out real-time identification, and sends identification result to computer and center management server in real time；
The identification result that computer docking receives shows in real time；
The visual recognition result received is analyzed and processed by center management server in real time, and sets up transformer station's scene database according to analysis processing result；
Center management server sets up transformer station's three-dimensional visualization model according to transformer station's scene database and transformer station's map, and judges whether work of transformer substation scene abnormal conditions occurs based on transformer station's three-dimensional visualization model；If abnormal conditions occurs in work of transformer substation scene, then during abnormal conditions are shown in transformer station's three-dimensional visualization model in real time, it is achieved in the security control on-the-spot to work of transformer substation.
Compared with the monitoring administration method on-the-spot with existing work of transformer substation, a kind of work of transformer substation site safety of the present invention is analyzed method and is no longer artificially supervised by supervisor, but view-based access control model identification technique, achieve and work of transformer substation scene is carried out comprehensive, efficient, intelligent security control, thus completely eliminate supervision blind area, supervisory efficiency is greatly improved, significantly reduces supervisor's workload, thus the strong guarantee safety of substation equipment and staff.
The present invention efficiently solves the on-the-spot monitoring administration method of existing work of transformer substation and supervises the problem that blind area is many, supervisory efficiency is low, supervisor's workload is big, it is adaptable to the security control that work of transformer substation is on-the-spot.
Accompanying drawing explanation
Fig. 1 is the operational process schematic diagram of center management server in the present invention.
Detailed description of the invention
A kind of work of transformer substation site safety analyzes method, and the method is to use following steps to realize:
Start video capture device；
The video data that video capture device Real-time Collection work of transformer substation is on-the-spot, and the video data collected is sent in real time to video server；
The video server video data to receiving carries out real-time identification, and sends identification result to computer and center management server in real time；
The identification result that computer docking receives shows in real time；
The visual recognition result received is analyzed and processed by center management server in real time, and sets up transformer station's scene database according to analysis processing result；
Center management server sets up transformer station's three-dimensional visualization model according to transformer station's scene database and transformer station's map, and judges whether work of transformer substation scene abnormal conditions occurs based on transformer station's three-dimensional visualization model；If abnormal conditions occurs in work of transformer substation scene, then during abnormal conditions are shown in transformer station's three-dimensional visualization model in real time, it is achieved in the security control on-the-spot to work of transformer substation.
It is on-the-spot that described video capture device is deployed in work of transformer substation；
It is indoor that described video server is deployed in transformer station's master control, and video server is connected with video capture device；
It is indoor that described computer is deployed in transformer station's master control, and computer is connected with video server by data wire；
Described center management server is deployed in transformer substation communication machine room, and center management server is connected with video server by data wire.
Described video server is DS8604SNL-SP video server.
Described computer is high-performance desktop computer.
Described center management server is iVMS-8320E center management server.
Based on following flow process, described center management server judges whether work of transformer substation scene abnormal conditions occurs:
A. typical scene multimedia database is set up:
First, the data object of multimedia database is determined；Then, it is determined that the typical scene of multimedia database, and ensure that the kind of the Sample video data of each scene is no less than 5, ensure that the quantity of similar Sample video data is no less than 100 simultaneously；The kind of described Sample video data includes: transformator sample, disconnecting switch sample, intrusion behavior sample, anomalous event sample, bus sample；Then, it is determined that the hierarchical structure of multimedia database；Described hierarchical structure includes: physical storage layer, data describing layer, Internet, filter course, client layer；Finally, according to the data object determined, typical scene, hierarchical structure, set up typical scene multimedia database, and carry out storage and the retrieval of multi-medium data based on typical scene multimedia database；
B. machine learning model is set up:
First, determine the concatenation tactic of base learner in cascade sort model, learning strategy, reasoning algorithm, confidence threshold value method to set up respectively, and according to determining that result sets up cascade sort model；Then, determine the system of selection of relation, directed graph, non-directed graph, generation or discrimination model between each stochastic variable of probability graph model respectively, and according to determining that result sets up probability graph model；Then, determine the level of degree of deep learning model learning device, mechanism respectively, and according to determining that result sets up degree of deep learning model；Finally, respectively cascade sort model, probability graph model, degree of deep learning model are verified；
C. parameter learning based on machine learning model:
First, based on typical scene multimedia database, the parameter learning of cascade sort model is carried out；Then, based on typical scene multimedia database, and use maximum likelihood estimate to carry out the parameter learning of probability graph model；Finally, based on typical scene multimedia database, and convolutional neural networks algorithm is used to carry out the parameter learning of degree of deep learning model；
D. deduction based on machine learning model:
First, decision tree, Boosting algorithm, Bagging algorithm, artificial neural network algorithm, algorithm of support vector machine is used to carry out cascade sort model, probability graph model, the supervised learning of degree of deep learning model successively；Then, cluster algorithm, Association Rule Analysis algorithm is used to carry out cascade sort model, probability graph model, the unsupervised learning of degree of deep learning model successively；Then, rough set theory, regression model is used to carry out cascade sort model, probability graph model, the semi-supervised learning of degree of deep learning model successively；Finally, cascade sort model, probability graph model, the deduction of degree of deep learning model are carried out successively according to learning outcome.
A kind of work of transformer substation site safety analyzes system (this system is used for realizing a kind of work of transformer substation site safety of the present invention and analyzes method), including video capture device, video server, computer, center management server；Video capture device is connected with video server；Video server is connected with computer and center management server respectively.
A kind of center management server (this server is used for realizing a kind of work of transformer substation site safety of the present invention and analyzes method), including with lower module:
A. typical scene multimedia database sets up module:
For determining the data object of multimedia database；Then, it is determined that the typical scene of multimedia database, and ensure that the kind of the Sample video data of each scene is no less than 5, ensure that the quantity of similar Sample video data is no less than 100 simultaneously；The kind of described Sample video data includes: transformator sample, disconnecting switch sample, intrusion behavior sample, anomalous event sample, bus sample；Then, it is determined that the hierarchical structure of multimedia database；Described hierarchical structure includes: physical storage layer, data describing layer, Internet, filter course, client layer；Finally, according to the data object determined, typical scene, hierarchical structure, set up typical scene multimedia database, and carry out storage and the retrieval of multi-medium data based on typical scene multimedia database；
B. machine learning model sets up module:
For determining the concatenation tactic of base learner in cascade sort model, learning strategy, reasoning algorithm, confidence threshold value method to set up respectively, and according to determining that result sets up cascade sort model；Then, determine the system of selection of relation, directed graph, non-directed graph, generation or discrimination model between each stochastic variable of probability graph model respectively, and according to determining that result sets up probability graph model；Then, determine the level of degree of deep learning model learning device, mechanism respectively, and according to determining that result sets up degree of deep learning model；Finally, respectively cascade sort model, probability graph model, degree of deep learning model are verified；
C. parameter learning module based on machine learning model:
For based on typical scene multimedia database, carrying out the parameter learning of cascade sort model；Then, based on typical scene multimedia database, and use maximum likelihood estimate to carry out the parameter learning of probability graph model；Finally, based on typical scene multimedia database, and convolutional neural networks algorithm is used to carry out the parameter learning of degree of deep learning model；
D. inference module based on machine learning model:
For using decision tree, Boosting algorithm, Bagging algorithm, artificial neural network algorithm, algorithm of support vector machine to carry out cascade sort model, probability graph model, the supervised learning of degree of deep learning model successively；Then, cluster algorithm, Association Rule Analysis algorithm is used to carry out cascade sort model, probability graph model, the unsupervised learning of degree of deep learning model successively；Then, rough set theory, regression model is used to carry out cascade sort model, probability graph model, the semi-supervised learning of degree of deep learning model successively；Finally, cascade sort model, probability graph model, the deduction of degree of deep learning model are carried out successively according to learning outcome.
Claims (8)
1. a work of transformer substation site safety analyzes method, it is characterised in that: the method is to use following steps to realize:
Start video capture device；
The video data that video capture device Real-time Collection work of transformer substation is on-the-spot, and the video data collected is sent in real time to video server；
The video server video data to receiving carries out real-time identification, and sends identification result to computer and center management server in real time；
The identification result that computer docking receives shows in real time；
The visual recognition result received is analyzed and processed by center management server in real time, and sets up transformer station's scene database according to analysis processing result；
Center management server sets up transformer station's three-dimensional visualization model according to transformer station's scene database and transformer station's map, and judges whether work of transformer substation scene abnormal conditions occurs based on transformer station's three-dimensional visualization model；If abnormal conditions occurs in work of transformer substation scene, then during abnormal conditions are shown in transformer station's three-dimensional visualization model in real time, it is achieved in the security control on-the-spot to work of transformer substation.
A kind of work of transformer substation site safety the most according to claim 1 analyzes method, it is characterised in that:
It is on-the-spot that described video capture device is deployed in work of transformer substation；
It is indoor that described video server is deployed in transformer station's master control, and video server is connected with video capture device；
It is indoor that described computer is deployed in transformer station's master control, and computer is connected with video server by data wire；
Described center management server is deployed in transformer substation communication machine room, and center management server is connected with video server by data wire.
A kind of work of transformer substation site safety the most according to claim 1 and 2 analyzes method, it is characterised in that: described video server is DS8604SNL-SP video server.
A kind of work of transformer substation site safety the most according to claim 1 and 2 analyzes method, it is characterised in that: described computer is high-performance desktop computer.
A kind of work of transformer substation site safety the most according to claim 1 and 2 analyzes method, it is characterised in that: described center management server is iVMS-8320E center management server.
A kind of work of transformer substation site safety the most according to claim 1 and 2 analyzes method, it is characterised in that: based on following flow process, described center management server judges whether work of transformer substation scene abnormal conditions occurs:
A. typical scene multimedia database is set up:
First, the data object of multimedia database is determined；Then, it is determined that the typical scene of multimedia database, and ensure that the kind of the Sample video data of each scene is no less than 5, ensure that the quantity of similar Sample video data is no less than 100 simultaneously；The kind of described Sample video data includes: transformator sample, disconnecting switch sample, intrusion behavior sample, anomalous event sample, bus sample；Then, it is determined that the hierarchical structure of multimedia database；Described hierarchical structure includes: physical storage layer, data describing layer, Internet, filter course, client layer；Finally, according to the data object determined, typical scene, hierarchical structure, set up typical scene multimedia database, and carry out storage and the retrieval of multi-medium data based on typical scene multimedia database；
B. machine learning model is set up:
First, determine the concatenation tactic of base learner in cascade sort model, learning strategy, reasoning algorithm, confidence threshold value method to set up respectively, and according to determining that result sets up cascade sort model；Then, determine the system of selection of relation, directed graph, non-directed graph, generation or discrimination model between each stochastic variable of probability graph model respectively, and according to determining that result sets up probability graph model；Then, determine the level of degree of deep learning model learning device, mechanism respectively, and according to determining that result sets up degree of deep learning model；Finally, respectively cascade sort model, probability graph model, degree of deep learning model are verified；
C. parameter learning based on machine learning model:
First, based on typical scene multimedia database, the parameter learning of cascade sort model is carried out；Then, based on typical scene multimedia database, and use maximum likelihood estimate to carry out the parameter learning of probability graph model；Finally, based on typical scene multimedia database, and convolutional neural networks algorithm is used to carry out the parameter learning of degree of deep learning model；
D. deduction based on machine learning model:
First, decision tree, Boosting algorithm, Bagging algorithm, artificial neural network algorithm, algorithm of support vector machine is used to carry out cascade sort model, probability graph model, the supervised learning of degree of deep learning model successively；Then, cluster algorithm, Association Rule Analysis algorithm is used to carry out cascade sort model, probability graph model, the unsupervised learning of degree of deep learning model successively；Then, rough set theory, regression model is used to carry out cascade sort model, probability graph model, the semi-supervised learning of degree of deep learning model successively；Finally, cascade sort model, probability graph model, the deduction of degree of deep learning model are carried out successively according to learning outcome.
7. work of transformer substation site safety analyzes a system, and this system is used for realizing a kind of work of transformer substation site safety as claimed in claim 1 and analyzes method, it is characterised in that: include video capture device, video server, computer, center management server；Video capture device is connected with video server；Video server is connected with computer and center management server respectively.
8. a center management server, this server is used for realizing a kind of work of transformer substation site safety as claimed in claim 1 and analyzes method, it is characterised in that: include with lower module:
A. typical scene multimedia database sets up module:
For determining the data object of multimedia database；Then, it is determined that the typical scene of multimedia database, and ensure that the kind of the Sample video data of each scene is no less than 5, ensure that the quantity of similar Sample video data is no less than 100 simultaneously；The kind of described Sample video data includes: transformator sample, disconnecting switch sample, intrusion behavior sample, anomalous event sample, bus sample；Then, it is determined that the hierarchical structure of multimedia database；Described hierarchical structure includes: physical storage layer, data describing layer, Internet, filter course, client layer；Finally, according to the data object determined, typical scene, hierarchical structure, set up typical scene multimedia database, and carry out storage and the retrieval of multi-medium data based on typical scene multimedia database；
B. machine learning model sets up module:
For determining the concatenation tactic of base learner in cascade sort model, learning strategy, reasoning algorithm, confidence threshold value method to set up respectively, and according to determining that result sets up cascade sort model；Then, determine the system of selection of relation, directed graph, non-directed graph, generation or discrimination model between each stochastic variable of probability graph model respectively, and according to determining that result sets up probability graph model；Then, determine the level of degree of deep learning model learning device, mechanism respectively, and according to determining that result sets up degree of deep learning model；Finally, respectively cascade sort model, probability graph model, degree of deep learning model are verified；
C. parameter learning module based on machine learning model:
For based on typical scene multimedia database, carrying out the parameter learning of cascade sort model；Then, based on typical scene multimedia database, and use maximum likelihood estimate to carry out the parameter learning of probability graph model；Finally, based on typical scene multimedia database, and convolutional neural networks algorithm is used to carry out the parameter learning of degree of deep learning model；
D. inference module based on machine learning model:
For using decision tree, Boosting algorithm, Bagging algorithm, artificial neural network algorithm, algorithm of support vector machine to carry out cascade sort model, probability graph model, the supervised learning of degree of deep learning model successively；Then, cluster algorithm, Association Rule Analysis algorithm is used to carry out cascade sort model, probability graph model, the unsupervised learning of degree of deep learning model successively；Then, rough set theory, regression model is used to carry out cascade sort model, probability graph model, the semi-supervised learning of degree of deep learning model successively；Finally, cascade sort model, probability graph model, the deduction of degree of deep learning model are carried out successively according to learning outcome.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610644792.5A CN106022977A (en) | 2016-08-09 | 2016-08-09 | Transformer substation job site safety analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610644792.5A CN106022977A (en) | 2016-08-09 | 2016-08-09 | Transformer substation job site safety analysis method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106022977A true CN106022977A (en) | 2016-10-12 |
Family
ID=57134608
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610644792.5A Pending CN106022977A (en) | 2016-08-09 | 2016-08-09 | Transformer substation job site safety analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106022977A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108596496A (en) * | 2018-04-25 | 2018-09-28 | 哈尔滨电气股份有限公司 | A kind of modularization mixing cloud service system for generating equipment data analysis |
| CN109581972A (en) * | 2017-09-29 | 2019-04-05 | 发那科株式会社 | Numerical control system, numerical control device, operating condition abnormality detection method and learning model group |
| CN109842682A (en) * | 2019-01-31 | 2019-06-04 | 内蒙古工业大学 | A kind of study of distributed environment safety and method for early warning based on Internet of Things |
| CN110428026A (en) * | 2019-07-18 | 2019-11-08 | 国网河北省电力有限公司 | The system and method that identification power grid infrastructure project is broken rules and regulations safely |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090032395A (en) * | 2007-09-27 | 2009-04-01 | 한국전력공사 | System and method for intelligent distribution automation |
| CN103297763A (en) * | 2013-06-14 | 2013-09-11 | 四川优美信息技术有限公司 | Monitoring system utilizing power grid intelligent videos |
| CN105807743A (en) * | 2016-03-15 | 2016-07-27 | 国网江苏省电力公司电力科学研究院 | Transformer substation equipment fault and defect analysis remote supporting system |
| CN105825337A (en) * | 2016-03-17 | 2016-08-03 | 国网安徽省电力公司信息通信分公司 | Intelligent inspection system for 500KV substation communication device |
-
2016
- 2016-08-09 CN CN201610644792.5A patent/CN106022977A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090032395A (en) * | 2007-09-27 | 2009-04-01 | 한국전력공사 | System and method for intelligent distribution automation |
| CN103297763A (en) * | 2013-06-14 | 2013-09-11 | 四川优美信息技术有限公司 | Monitoring system utilizing power grid intelligent videos |
| CN105807743A (en) * | 2016-03-15 | 2016-07-27 | 国网江苏省电力公司电力科学研究院 | Transformer substation equipment fault and defect analysis remote supporting system |
| CN105825337A (en) * | 2016-03-17 | 2016-08-03 | 国网安徽省电力公司信息通信分公司 | Intelligent inspection system for 500KV substation communication device |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109581972A (en) * | 2017-09-29 | 2019-04-05 | 发那科株式会社 | Numerical control system, numerical control device, operating condition abnormality detection method and learning model group |
| US11080610B2 (en) | 2017-09-29 | 2021-08-03 | Fanuc Corporation | Numerical control system that detects an abnormality in an operation state |
| CN109581972B (en) * | 2017-09-29 | 2021-10-26 | 发那科株式会社 | Numerical control system, numerical control device, method for checking abnormality in operating state, and learning model set |
| CN108596496A (en) * | 2018-04-25 | 2018-09-28 | 哈尔滨电气股份有限公司 | A kind of modularization mixing cloud service system for generating equipment data analysis |
| CN109842682A (en) * | 2019-01-31 | 2019-06-04 | 内蒙古工业大学 | A kind of study of distributed environment safety and method for early warning based on Internet of Things |
| CN110428026A (en) * | 2019-07-18 | 2019-11-08 | 国网河北省电力有限公司 | The system and method that identification power grid infrastructure project is broken rules and regulations safely |
| CN110428026B (en) * | 2019-07-18 | 2023-02-10 | 国网河北省电力有限公司 | System and method for identifying power grid infrastructure construction safety violation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110674772B (en) | Intelligent safety control auxiliary system and method for electric power operation site | |
| CN107274105B (en) | Linear discriminant analysis-based multi-attribute decision tree power grid stability margin evaluation method | |
| CN106022977A (en) | Transformer substation job site safety analysis method | |
| CN109726246A (en) | One kind being associated with reason retrogressive method with visual power grid accident based on data mining | |
| CN102143354B (en) | Method for recognizing and calculating galloping of transmission conductor based on video image processing | |
| CN110765848A (en) | Chemical plant personnel safety guarantee system and early warning method based on artificial intelligence image processing algorithm | |
| CN111612018A (en) | Underground pipe gallery monitoring method and system based on multi-source heterogeneous data fusion | |
| CN113469654B (en) | Multi-level safety control system of transformer substation based on intelligent algorithm fuses | |
| CN111914687B (en) | Method for actively identifying accidents based on Internet of vehicles | |
| CN115527340A (en) | Intelligent construction site safety monitoring system and method based on unmanned aerial vehicle and surveillance camera | |
| CN110334105B (en) | Stream data abnormity detection method based on Storm | |
| CN104240467A (en) | Systems and Methods for Process Alarm Reduction | |
| CN105376193A (en) | Intelligent association analysis method and intelligent association analysis device for security events | |
| CN105959162A (en) | Distributed electric power enterprise information network safety management system | |
| CN107784393A (en) | A kind of the defects of transmission line of electricity Forecasting Methodology and device | |
| CN116542956B (en) | Automatic detection method and system for fabric components and readable storage medium | |
| CN109145431A (en) | A kind of modeling method and device monitoring electric power secondary system operating status | |
| CN112291303A (en) | Multidirectional distance dynamic monitoring and early warning method based on edge calculation | |
| CN115310704A (en) | Multi-dimensional fire safety assessment early warning system based on system safety model | |
| CN114241400A (en) | Monitoring method and device of power grid system and computer readable storage medium | |
| CN112132819A (en) | Communication network management monitoring method based on artificial intelligence | |
| CN112131069B (en) | Equipment operation monitoring method and system based on clustering | |
| CN113177475A (en) | Building site distribution box on-off state identification method based on deep learning target detection | |
| CN111930982A (en) | Intelligent labeling method for power grid images | |
| Zheng et al. | Research on improvement of substation monitoring capability based on AI algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161012 |
|
| RJ01 | Rejection of invention patent application after publication |