CN110351536A - A kind of substation abnormality detection system, method and device - Google Patents
A kind of substation abnormality detection system, method and device Download PDFInfo
- Publication number
- CN110351536A CN110351536A CN201910770280.7A CN201910770280A CN110351536A CN 110351536 A CN110351536 A CN 110351536A CN 201910770280 A CN201910770280 A CN 201910770280A CN 110351536 A CN110351536 A CN 110351536A
- Authority
- CN
- China
- Prior art keywords
- substation
- abnormal
- module
- image
- model
- 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
- 230000005856 abnormality Effects 0.000 title claims abstract description 46
- 238000001514 detection method Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 26
- 230000002159 abnormal effect Effects 0.000 claims abstract description 54
- 230000007613 environmental effect Effects 0.000 claims abstract description 22
- 230000006870 function Effects 0.000 claims abstract description 22
- 230000005540 biological transmission Effects 0.000 claims abstract description 16
- 238000004519 manufacturing process Methods 0.000 claims abstract description 4
- 238000012544 monitoring process Methods 0.000 claims description 23
- 238000007726 management method Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012790 confirmation Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 claims description 5
- 230000004069 differentiation Effects 0.000 claims description 4
- 238000004880 explosion Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000013500 data storage Methods 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000011895 specific detection Methods 0.000 claims description 3
- 238000003780 insertion Methods 0.000 claims 1
- 230000037431 insertion Effects 0.000 claims 1
- 238000007689 inspection Methods 0.000 abstract description 6
- 230000008901 benefit Effects 0.000 abstract description 4
- 230000006872 improvement Effects 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013450 outlier detection Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
Classifications
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B19/00—Alarms responsive to two or more different undesired or abnormal conditions, e.g. burglary and fire, abnormal temperature and abnormal rate of flow
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a kind of substation abnormality detection system, method and device, substation abnormality detection system includes front-end video collection module, network transmission module, supervision and management center, abnormal alarm module, data memory module；Front-end video collection module includes the web camera with intelligent detecting function, intelligent algorithm module is integrated in web camera, intelligent algorithm module uses the unsupervised anomaly detection algorithm based on production confrontation study, and intelligent algorithm module for being used for quickly detecting equipment ambient enviroment extremely.The present invention uses the web camera with intelligent detecting function to carry out abnormality detection collected environmental information, only exports there may be abnormal pictorial information, facilitates the transmission of data；There is better robustness and adaptability compared to traditional Anomaly target detection algorithm, have uninterruptedly with timely advantage, reduce the probability of direct surveillance's missing inspection and discovery not in time, reduce the security risk of substation.
Description
Technical field
The present invention relates to power equipment monitoring technical field, in particular to a kind of substation abnormality detection system, side
Method and device.
Background technique
Remote districts or unattended substation are needed to guarantee the operational safety of substation to substation
Explosion of Transformer, the transformer equipment of appearance smolder on fire, non-working person or animal intrusion etc. abnormal conditions be monitored concurrently
Warning message out, generally use the mode of artificial inspection and remote camera monitoring in the prior art obtaining inside substation and
The variation of ambient conditions, in this way by tour personnel carry out daily on-the-spot make an inspection tour observation device situation and power station ambient conditions or
It is that the continuous picture for observing monitor found the abnormal situation, and gives a warning carry out the sequence of operations such as barrier gate protection in time.
However, in the actual operation process, the mode low efficiency of this manual patrol or video surveillance, to staff's
Workload is larger, and exist due to the carelessness of staff cause abnormal conditions discovery not in time or there are the feelings of missing inspection
Condition can not save so as to later period examination alarm condition in the form of picture.
Summary of the invention
The main purpose of the present invention is to provide a kind of substation abnormality detection system, method and device, Ke Yiyou
Effect solves the problems in background technique.
To achieve the above object, the invention provides the following technical scheme: a kind of substation abnormality detection system, is used for
Detect the environmental abnormality information of substation, including front-end video collection module, network transmission module, supervision and management center, exception
Alarm module, data memory module；The front-end video collection module includes the web camera with intelligent detecting function, institute
It states and is integrated with intelligent algorithm module in web camera, the intelligent algorithm module is used based on production confrontation study without prison
Outlier Detection Algorithm is superintended and directed, the intelligent algorithm module for being used for quickly detecting equipment ambient enviroment extremely.
Preferably, the front-end video collection module is detected for being monitored in real time to substation's ambient enviroment
When abnormal, the monitoring information that will acquire is sent to supervision and management center by network transmission module.
Preferably, the web camera is placed near substation equipment, for realizing substation abnormality detection
Function, the web camera uses embedded real-time operating system, after the identification of intelligent algorithm module, to may have exception
Image be sent to supervision and management center through network transmission module, and upload to web server simultaneously.
Preferably, the network transmission module, the abnormal monitoring information transmission for obtaining front-end video collection module
To supervision and management center；The supervision and management center for the monitoring information that receiving front-end video acquisition module transmits, and docks
The monitoring information of receipts makees further judgement, when confirmation has abnormal occur, alarms；The abnormal alarm module, for pair
The abnormal conditions of supervision and management center confirmation are alarmed to remind staff to go processing exception information；The data store mould
Block can upload to cloud or local position for storing the picture of acknowledged environmental abnormality to facilitate staff to carry out
Later period examination.
Preferably, the environmental abnormality information includes Explosion of Transformer, transformer equipment is smoldered, personnel or animal invade three
Class.
Preferably, the intelligent algorithm module includes: to utilize depth convolution to the specific detection identification process of environmental abnormality
Confrontation generates network DCGAN and is trained to normal substation, generates the model under the scene, then passes through generation
Each frame image of model treatment video, to generate the comparison diagram and difference value of each frame image, given threshold can to export
The abnormal picture of energy.
Preferably, the intelligent algorithm module specific steps are as follows:
S1, pass through convolutional neural networks, build generation model and the discrimination model in DCGAN model；Generate appointing for model
Business is that corresponding immediate normal environment image is generated from given picture；Discrimination model is generated to current producer
Image makes differentiation.
S2, circular form generation confrontation network is built on the basis of step S1, so that the structure of network forms closed loop；It is following
In the generation confrontation network model of ring, the generator of use is the image composer for generating normal condition, uses GA-NIt indicates；Simultaneously
Also build arbiter DN, for differentiating current producer GA-NWhether the image of generation is normal picture.
S3, according to the model in above-mentioned steps S1 and S2, establish loss function, and with the method for stochastic gradient descent to whole
A model optimizes；Wherein, loss function includes two parts altogether, and first part is from given image to normal picture
Arbiter loss:
Second part is the loss of generator:
All loss functions of above-mentioned model are added, the loss function of entire model is obtained:
LDCGAN(G, D)=LGAN(GA-N,DN,x,z)+LDC(GA-N,DN,x,z)
S4, using stochastic gradient descent method, model is trained with environment normal image data base, until optimization
Convergence, finally obtains generator GA-N, which is the mapping relations by image procossing for environment normal picture.
Preferably, in the step S1, the detailed process for generating model progress environmental abnormality detection is utilized are as follows: utilize generation
Device GA-N, using image as input, obtain the normal image of environment, the difference by calculating original image and generation image is examined
Survey environmental abnormality situation.
A kind of substation method for detecting abnormality, including following method and step:
Data acquisition and processing: substation's ambient enviroment is monitored in real time, to acquire substation's ambient enviroment video
Data are measured in real time ambient video data, to detect the abnormal picture in ambient video data；
Data upload: to detecting that there may be abnormal pictorial informations to upload to monitoring management end；
Anomaly analysis and processing: to upload to monitoring management end there may be abnormal pictures to be analyzed comprehensively, it is right
Picture without exception is removed, and when determination has abnormal picture, is alarmed；
Abnormal data storage: there is abnormal picture to save confirmation, facilitate subsequent examination.
A kind of substation abnormal detector, comprising:
Reservoir, for storing computer program；
Processor executes above-mentioned substation method for detecting abnormality for loading computer program.
Compared with prior art, the invention has the following beneficial effects:
1) present invention carries out abnormal inspection to collected environmental information using the web camera with intelligent detecting function
It surveys, only exports there may be abnormal pictorial information, facilitate the transmission of data.
2) present invention provides web services, and user directly can be accessed or be controlled intelligent network camera by IP address.
3) present invention has better robustness and adaptability compared to traditional Anomaly target detection algorithm, has uninterrupted
Timely advantage reduces the probability of direct surveillance's missing inspection and discovery not in time, reduces the security risk of substation, avoid
Manual patrol it is cumbersome and inefficient.
Detailed description of the invention
Fig. 1 is overview flow chart of the present invention；
Fig. 2 is work flow diagram of the present invention.
Specific embodiment
To be easy to understand the technical means, the creative features, the aims and the efficiencies achieved by the present invention, below with reference to
Specific embodiment, the present invention is further explained.
Embodiment 1
A kind of substation abnormality detection system, for detecting the environmental abnormality information of substation, including head end video
Acquisition module, network transmission module, supervision and management center, abnormal alarm module, data memory module.
Front-end video collection module includes the web camera with intelligent detecting function, is integrated with intelligence in web camera
Energy algoritic module, intelligent algorithm module use the unsupervised anomaly detection algorithm based on production confrontation study, intelligent algorithm mould
Block for being used for quickly detecting equipment ambient enviroment extremely.
Front-end video collection module when detecting abnormal, will be obtained for being monitored in real time to substation's ambient enviroment
The monitoring information got is sent to supervision and management center by network transmission module.
Web camera is placed near substation equipment, for realizing the function of substation abnormality detection, network
Video camera uses embedded real-time operating system, after the identification of intelligent algorithm module, to may have abnormal image to pass through network
Defeated module is sent to supervision and management center, and uploads to web server simultaneously, and the user on network can be watched with logon web page end
Camera review, and video camera can be controlled.
Network transmission module, the abnormal monitoring information for obtaining front-end video collection module are transmitted in monitoring management
The heart.
Supervision and management center is believed for the monitoring information that receiving front-end video acquisition module transmits, and to received monitoring
Breath makees further judgement, when confirmation has abnormal occur, alarms.
Abnormal alarm module, for alarming the abnormal conditions that supervision and management center confirms to remind staff to go
Handle exception information.
Data memory module can upload to cloud or local position for storing the picture of acknowledged environmental abnormality
To facilitate staff to carry out later period examination.
Environmental abnormality information includes Explosion of Transformer, transformer equipment is smoldered, personnel or animal invade three classes.
Intelligent algorithm module includes: to fight to generate network using depth convolution to the specific detection identification process of environmental abnormality
DCGAN is trained normal substation, generates the model under the scene, then the model treatment video by generating
Each frame image, to generate the comparison diagram and difference value of each frame image, if it is normal picture, then the comparison diagram that generates
With the difference very little of original image, if it is abnormal image, then the image that generates and original image it is widely different, pass through given threshold
To export possible abnormal picture.
Intelligent algorithm module specific steps are as follows:
S1, pass through convolutional neural networks, build generation model and the discrimination model in DCGAN model；Generate appointing for model
Business is that corresponding immediate normal environment image is generated from given picture, is the pith for completing environmental abnormality detection；
Discrimination model is then that the image generated to current producer makes differentiation.
S2, circular form generation confrontation network is built on the basis of step S1, so that the structure of network forms closed loop；It is following
In the generation confrontation network model of ring, the generator of use is the image composer for generating normal condition, uses GA-NIt indicates；Simultaneously
Also build arbiter DN, for differentiating current producer GA-NWhether the image of generation is normal picture.
S3, according to the model in above-mentioned steps S1 and S2, establish loss function, and with the method for stochastic gradient descent to whole
A model optimizes；Wherein, loss function includes two parts altogether, and first part is from given image to normal picture
Arbiter loss:
Second part is the loss of generator:
All loss functions of above-mentioned model are added, the loss function of entire model is obtained:
LDCGAN(G, D)=LGAN(GA-N,DN,x,z)+LDC(GA-N,DN,x,z)
S4, using stochastic gradient descent method, model is trained with environment normal image data base, until optimization
Convergence, finally obtains generator GA-N, which is the mapping relations by image procossing for environment normal picture.
In step S1, the detailed process for generating model progress environmental abnormality detection is utilized are as follows: utilize generator GA-N, will scheme
As obtaining the normal image of environment as input, environmental abnormality is detected by calculating original image and generating the difference of image
Situation.
By using above-mentioned technical proposal, the present invention uses the web camera with intelligent detecting function to collected
Environmental information carries out abnormality detection, and only exports there may be abnormal pictorial information, facilitates the transmission of data；It can timely send out
Reveal existing abnormal conditions and there is continual advantage, avoids because abnormal conditions caused by personnel's reason cannot be sent out in time
The generation of repairing delay and major accident, reduces the security risk of substation caused by existing.
Embodiment 2
A kind of substation method for detecting abnormality, including following method and step:
Data acquisition and processing: substation's ambient enviroment is monitored in real time, to acquire substation's ambient enviroment video
Data are measured in real time ambient video data, to detect the abnormal picture in ambient video data；
Data upload: to detecting that there may be abnormal pictorial informations to upload to monitoring management end；
Anomaly analysis and processing: to upload to monitoring management end there may be abnormal pictures to be analyzed comprehensively, it is right
Picture without exception is removed, and when determination has abnormal picture, is alarmed；
Abnormal data storage: there is abnormal picture to save confirmation, facilitate subsequent examination.
Embodiment 3
A kind of substation abnormal detector, comprising:
Reservoir, for storing computer program；
Processor executes the substation method for detecting abnormality of above-described embodiment for loading computer program.
The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the above embodiments and description only describe this
The principle of invention, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these changes
Change and improvement all fall within the protetion scope of the claimed invention.The claimed scope of the invention by appended claims and its
Equivalent thereof.
Claims (10)
1. a kind of substation abnormality detection system, for detecting the environmental abnormality information of substation, including head end video is adopted
Collect module, network transmission module, supervision and management center, abnormal alarm module, data memory module；It is characterized by: before described
Holding video acquisition module includes the web camera with intelligent detecting function, is integrated with intelligent algorithm in the web camera
Module, the intelligent algorithm module use the unsupervised anomaly detection algorithm based on production confrontation study, the intelligent algorithm
Module for being used for quickly detecting equipment ambient enviroment extremely.
2. a kind of substation abnormality detection system according to claim 1, which is characterized in that the head end video is adopted
Collect module, for being monitored in real time to substation's ambient enviroment, when detecting abnormal, the monitoring information that will acquire passes through
Network transmission module is sent to supervision and management center.
3. a kind of substation abnormality detection system according to claim 2, which is characterized in that the web camera
It is placed near substation equipment, for realizing the function of substation abnormality detection, the web camera is using insertion
Formula real time operating system, after the identification of intelligent algorithm module, to may there is abnormal image to be sent to prison through network transmission module
Administrative center is controlled, and uploads to web server simultaneously.
4. a kind of substation abnormality detection system according to claim 2, which is characterized in that the network transmission mould
Block, the abnormal monitoring information for obtaining front-end video collection module are transmitted to supervision and management center；In the monitoring management
The heart makees further judgement for the monitoring information that receiving front-end video acquisition module transmits, and to received monitoring information, when true
Recognize when having abnormal occur, alarms；The abnormal alarm module, the abnormal conditions for confirming to supervision and management center carry out
Alarm is to remind staff to go processing exception information；The data memory module, for storing acknowledged environmental abnormality
Picture can upload to cloud or local position to facilitate staff to carry out later period examination.
5. a kind of substation abnormality detection system according to claim 1, which is characterized in that the environmental abnormality letter
Breath includes Explosion of Transformer, transformer equipment is smoldered, personnel or animal invade three classes.
6. a kind of substation abnormality detection system according to claim 3, which is characterized in that the intelligent algorithm mould
Block includes: to fight to generate network (referred to as: DCGAN) to normal using depth convolution to the specific detection identification process of environmental abnormality
Substation be trained, generate the model under the scene, then by generate model treatment video each frame figure
Picture, to generate the comparison diagram and difference value of each frame image, given threshold is to export possible abnormal picture.
7. a kind of substation abnormality detection system according to claim 6, which is characterized in that the intelligent algorithm mould
Block specific steps are as follows:
S1, pass through convolutional neural networks, build generation model and the discrimination model in DCGAN model；Generate model task be
Corresponding immediate normal environment image is generated from given picture；Discrimination model is then the image generated to current producer
Make differentiation.
S2, circular form generation confrontation network is built on the basis of step S1, so that the structure of network forms closed loop；In circulation
It generates in confrontation network model, the generator of use is the image composer for generating normal condition, uses GA-NIt indicates；It also takes simultaneously
Build arbiter DN, for differentiating current producer GA-NWhether the image of generation is normal picture.
S3, according to the model in above-mentioned steps S1 and S2, establish loss function, and with the method for stochastic gradient descent to entire mould
Type optimizes；Wherein, loss function includes two parts altogether, and first part is the differentiation from given image to normal picture
Device loss:
Second part is the loss of generator:
All loss functions of above-mentioned model are added, the loss function of entire model is obtained:
LDCGAN(G, D)=LGAN(GA-N,DN,x,z)+LDC(GA-N,DN,x,z)
S4, using stochastic gradient descent method, model is trained with environment normal image data base, until optimization receive
It holds back, finally obtains generator GA-N, which is the mapping relations by image procossing for environment normal picture.
8. a kind of substation abnormality detection system according to claim 7, which is characterized in that in the step S1,
Utilize the detailed process for generating model progress environmental abnormality detection are as follows: utilize generator GA-N, using image as input, obtain ring
The normal image in border detects environmental abnormality situation by calculating original image and generating the difference of image.
9. a kind of substation method for detecting abnormality, which is characterized in that including following method and step:
Data acquisition and processing: monitoring substation's ambient enviroment in real time, to acquire substation's ambient enviroment video data,
Ambient video data are measured in real time, to detect the abnormal picture in ambient video data；
Data upload: to detecting that there may be abnormal pictorial informations to upload to monitoring management end；
Anomaly analysis and processing: to upload to monitoring management end there may be abnormal pictures to be analyzed comprehensively, to being no different
Normal picture is removed, and when determination has abnormal picture, is alarmed；
Abnormal data storage: there is abnormal picture to save confirmation, facilitate subsequent examination.
10. a kind of substation abnormal detector characterized by comprising
Reservoir, for storing computer program；
Processor executes substation method for detecting abnormality as claimed in claim 9 for loading computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910770280.7A CN110351536A (en) | 2019-08-20 | 2019-08-20 | A kind of substation abnormality detection system, method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910770280.7A CN110351536A (en) | 2019-08-20 | 2019-08-20 | A kind of substation abnormality detection system, method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110351536A true CN110351536A (en) | 2019-10-18 |
Family
ID=68180868
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910770280.7A Pending CN110351536A (en) | 2019-08-20 | 2019-08-20 | A kind of substation abnormality detection system, method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110351536A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110909707A (en) * | 2019-12-02 | 2020-03-24 | 天津大海云科技有限公司 | Video inspection system and method based on generating type countermeasure network |
| CN110971826A (en) * | 2019-12-06 | 2020-04-07 | 长沙千视通智能科技有限公司 | Video front-end monitoring device and method |
| CN111274876A (en) * | 2020-01-09 | 2020-06-12 | 国网江苏省电力有限公司徐州供电分公司 | Scheduling monitoring method and system based on video analysis |
| CN111368624A (en) * | 2019-10-28 | 2020-07-03 | 北京影谱科技股份有限公司 | Loop detection method and device based on generation of countermeasure network |
| CN111582165A (en) * | 2020-05-07 | 2020-08-25 | 广东中立建设有限公司 | Electric power distribution station room monitored control system |
| CN112132051A (en) * | 2020-09-24 | 2020-12-25 | 广东电网有限责任公司广州供电局 | Power distribution room safety identification system and identification method thereof |
| CN113194295A (en) * | 2021-04-30 | 2021-07-30 | 重庆天智慧启科技有限公司 | Monitoring data storage system |
| CN113542221A (en) * | 2021-06-15 | 2021-10-22 | 四川英得赛克科技有限公司 | Method and system for judging tampering of sensor data of intelligent substation, electronic equipment and storage medium |
| CN114093117A (en) * | 2021-10-11 | 2022-02-25 | 北京精英***科技有限公司 | Fire control management and control method and device |
| CN115761267A (en) * | 2022-12-27 | 2023-03-07 | 四川数聚智造科技有限公司 | Detection method for solving outdoor low-frequency image acquisition abnormity |
| CN115937601A (en) * | 2022-12-27 | 2023-04-07 | 四川数聚智造科技有限公司 | Transformer substation abnormity detection method based on normal sample modeling |
| CN116248830A (en) * | 2022-12-17 | 2023-06-09 | 航天行云科技有限公司 | Wild animal identification method, terminal and system based on space-based Internet of things |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104333736A (en) * | 2014-10-28 | 2015-02-04 | 山东大学 | Intelligent recognition monitoring system and method for unmanned substation |
| CN107016406A (en) * | 2017-02-24 | 2017-08-04 | 中国科学院合肥物质科学研究院 | The pest and disease damage image generating method of network is resisted based on production |
| CN107563509A (en) * | 2017-07-17 | 2018-01-09 | 华南理工大学 | A kind of dynamic adjustment algorithm for the condition DCGAN models that feature based returns |
| CN109460708A (en) * | 2018-10-09 | 2019-03-12 | 东南大学 | A kind of Forest fire image sample generating method based on generation confrontation network |
| CN109584221A (en) * | 2018-11-16 | 2019-04-05 | 聚时科技(上海)有限公司 | A kind of abnormal image detection method generating confrontation network based on supervised |
| CN109980781A (en) * | 2019-03-26 | 2019-07-05 | 惠州学院 | A kind of transformer substation intelligent monitoring system |
-
2019
- 2019-08-20 CN CN201910770280.7A patent/CN110351536A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104333736A (en) * | 2014-10-28 | 2015-02-04 | 山东大学 | Intelligent recognition monitoring system and method for unmanned substation |
| CN107016406A (en) * | 2017-02-24 | 2017-08-04 | 中国科学院合肥物质科学研究院 | The pest and disease damage image generating method of network is resisted based on production |
| CN107563509A (en) * | 2017-07-17 | 2018-01-09 | 华南理工大学 | A kind of dynamic adjustment algorithm for the condition DCGAN models that feature based returns |
| CN109460708A (en) * | 2018-10-09 | 2019-03-12 | 东南大学 | A kind of Forest fire image sample generating method based on generation confrontation network |
| CN109584221A (en) * | 2018-11-16 | 2019-04-05 | 聚时科技(上海)有限公司 | A kind of abnormal image detection method generating confrontation network based on supervised |
| CN109980781A (en) * | 2019-03-26 | 2019-07-05 | 惠州学院 | A kind of transformer substation intelligent monitoring system |
Non-Patent Citations (1)
| Title |
|---|
| 罗佳等: "生成式对抗网络研究综述", 《仪器仪表学报》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111368624A (en) * | 2019-10-28 | 2020-07-03 | 北京影谱科技股份有限公司 | Loop detection method and device based on generation of countermeasure network |
| CN110909707A (en) * | 2019-12-02 | 2020-03-24 | 天津大海云科技有限公司 | Video inspection system and method based on generating type countermeasure network |
| CN110971826A (en) * | 2019-12-06 | 2020-04-07 | 长沙千视通智能科技有限公司 | Video front-end monitoring device and method |
| CN111274876A (en) * | 2020-01-09 | 2020-06-12 | 国网江苏省电力有限公司徐州供电分公司 | Scheduling monitoring method and system based on video analysis |
| CN111274876B (en) * | 2020-01-09 | 2024-02-13 | 国网江苏省电力有限公司徐州供电分公司 | Scheduling monitoring method and system based on video analysis |
| CN111582165A (en) * | 2020-05-07 | 2020-08-25 | 广东中立建设有限公司 | Electric power distribution station room monitored control system |
| CN111582165B (en) * | 2020-05-07 | 2024-02-09 | 广东中立建设有限公司 | Monitoring system for power distribution station room |
| CN112132051A (en) * | 2020-09-24 | 2020-12-25 | 广东电网有限责任公司广州供电局 | Power distribution room safety identification system and identification method thereof |
| CN113194295A (en) * | 2021-04-30 | 2021-07-30 | 重庆天智慧启科技有限公司 | Monitoring data storage system |
| CN113542221B (en) * | 2021-06-15 | 2023-11-03 | 四川英得赛克科技有限公司 | Method and system for judging falsification of sensor data of intelligent substation, electronic equipment and storage medium |
| CN113542221A (en) * | 2021-06-15 | 2021-10-22 | 四川英得赛克科技有限公司 | Method and system for judging tampering of sensor data of intelligent substation, electronic equipment and storage medium |
| CN114093117A (en) * | 2021-10-11 | 2022-02-25 | 北京精英***科技有限公司 | Fire control management and control method and device |
| CN116248830A (en) * | 2022-12-17 | 2023-06-09 | 航天行云科技有限公司 | Wild animal identification method, terminal and system based on space-based Internet of things |
| CN115761267B (en) * | 2022-12-27 | 2023-06-16 | 四川数聚智造科技有限公司 | Detection method for solving outdoor low-frequency image acquisition abnormality |
| CN115937601B (en) * | 2022-12-27 | 2023-08-08 | 四川数聚智造科技有限公司 | Transformer substation anomaly detection method based on normal sample modeling |
| CN115937601A (en) * | 2022-12-27 | 2023-04-07 | 四川数聚智造科技有限公司 | Transformer substation abnormity detection method based on normal sample modeling |
| CN115761267A (en) * | 2022-12-27 | 2023-03-07 | 四川数聚智造科技有限公司 | Detection method for solving outdoor low-frequency image acquisition abnormity |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110351536A (en) | A kind of substation abnormality detection system, method and device | |
| EP3279700B1 (en) | Security inspection centralized management system | |
| CN103514694B (en) | A kind of intrusion detection monitoring system | |
| CN104333736B (en) | Unmanned substation's intelligent recognition monitoring system and method | |
| CN104966375B (en) | A kind of safety defense monitoring system | |
| CN106412501B (en) | A kind of the construction safety behavior intelligent monitor system and its monitoring method of video | |
| CN110492607A (en) | A kind of intelligent substation condition monitoring system based on ubiquitous electric power Internet of Things | |
| CN109448291A (en) | A kind of behavior video monitoring system applied to construction site | |
| CN107403158A (en) | A kind of personnel video frequency identifying method on duty and intelligent subscriber information carrying means | |
| WO2018232846A1 (en) | Large-scale peripheral security monitoring method and system | |
| CN108200405A (en) | A kind of video monitoring system based on recognition of face | |
| CN107272488A (en) | A kind of electric power logistics comprehensive monitoring system | |
| CN208207842U (en) | Power distribution room safety management system | |
| CN117235443A (en) | Electric power operation safety monitoring method and system based on edge AI | |
| CN110602453B (en) | Internet of things big data intelligent video security monitoring system | |
| CN115496640A (en) | Intelligent safety system of thermal power plant | |
| CN205959355U (en) | Intelligent monitoring system | |
| CN107547867A (en) | A kind of outside transformer substation video monitoring system and monitoring method | |
| CN110361050A (en) | A kind of hydrographic information forecasting system based on wireless sensor network | |
| CN117081917A (en) | Intelligent gateway based on AI (advanced technology attachment) internet of things sewage treatment operation and maintenance management | |
| TATAMA | Engineering and deploying a cheap recognition security system on a raspberry pi platform for a rural settlement | |
| CN116246445A (en) | Knowledge-graph-based warehouse safety multi-source Internet-of-things data early warning method | |
| CN115396751A (en) | Cabinet security system with intelligent medical equipment state detection function and control method | |
| CN111277789A (en) | Video-based community security method and device, electronic equipment and storage medium | |
| CN111432175A (en) | Intelligent recognition abnormal behavior alarm system |
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: 20191018 |