Microcomputer anti-misoperation processing method for artificial intelligence transformer substation

A technology of artificial intelligence and processing methods, applied in electrical components, circuit devices, information technology support systems, etc., can solve the problems of inability to achieve post-event traceability, inability to realize intelligent early warning of accidents, inability to monitor, etc., to achieve video surveillance and prevention. The effect of misintegration, efficiency improvement, and precision improvement

Pending Publication Date: 2021-04-30
JINZHOU ELECTRIC POWER SUPPLY COMPANY OF STATE GRID LIAONING ELECTRIC POWER SUPPLY +1
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It is impossible to realize the "post-tracing" of accidents, let alone monitor specific events and user behaviors, and it is impossible to realize "intelligent early warning" of accidents

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Microcomputer anti-misoperation processing method for artificial intelligence transformer substation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] As shown in the figure, the artificial intelligence substation microcomputer error prevention processing method involved in the present invention, its steps are:

[0025] Step 1 Set up multiple cameras at the equipment site of the substation, collect the video signals of each camera in the substation and transmit them to the computer, and the computer saves the video signals;

[0026] Step 2 builds an artificial intelligence OpenCV vision library in the computer, utilizes GPU parallel processing technology, transfers the workload of the application program calculation-intensive part to the GPU, and runs the remaining program codes by the CPU, thereby improving the operating speed of video analysis. The GPU uses NVIDIA CUDA Universal Parallel Computing Framework;

[0027] Step 3 Construct a deep neural network to recognize images and realize operator behavior analysis, judgment and monitoring;

[0028] Step 4 Integrate video monitoring, intelligent analysis, behavior mo...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

According to the invention, real-time monitoring and behavior analysis are carried out on an operator, non-standard operation and behaviors are intervened, video monitoring and error prevention are integrated, and post-event tracing of an accident can be realized; and an intelligent analysis function is achieved, specific events and user behaviors are monitored, and intelligent early warning of accidents is achieved. A method comprises the following steps: erecting a plurality of cameras on a transformer substation equipment site, acquiring video signals of the cameras in a transformer substation, and transmitting the video signals to a computer; building an artificial intelligence OpenCV visual library, and utilizing a GPU parallel processing technology; and constructing a deep neural network to recognize the image, and realizing behavior analysis, judgment and monitoring of an operator. Video monitoring, intelligent analysis, behavior monitoring and anti-misoperation locking technologies are deeply fused, and when a specific behavior is found, an alarm is automatically generated to inform monitoring personnel of timely early warning, linkage and processing.

Description

technical field [0001] The invention relates to an artificial intelligence substation microcomputer error prevention processing method integrated with video intelligent recognition technology, and belongs to the field of substation microcomputer error prevention locking systems. Background technique [0002] In traditional monitoring, the camera is the eye of security monitoring, and video analysis, extraction, early warning, alarm, retrieval and fault diagnosis are all done by human eyes, so traditional security monitoring is completed by electronic eyes + artificial brain Monitor the operation of the system. With the development of artificial intelligence and video processing technology, the application of intelligent recognition technology is becoming more and more extensive. Through the upgrade and optimization of traditional video surveillance, the image of the camera is collected in real time and further analyzed. When a specific behavior is found, an alarm is automati...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): H02J13/00
CPCH02J13/00006Y02B90/20Y04S40/12
Inventor 高凯王强韩锦刚赵阳魏凯
Owner JINZHOU ELECTRIC POWER SUPPLY COMPANY OF STATE GRID LIAONING ELECTRIC POWER SUPPLY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap