Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Isolation switch state identification method in traction substation

A technology for traction substations and isolating switches, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve problems such as detection rate decline, and achieve strong robustness and scene adaptability

Active Publication Date: 2021-02-05
SOUTHWEST JIAOTONG UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, HOG is very sensitive to arbitrary changes in the target or background, while SIFT features have little effect on smooth edges. When the target is not clear enough, the detection rate of HOG features drops

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
  • Isolation switch state identification method in traction substation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The method of the invention can be used for isolating switches of different traction substations, and can accurately identify the state of the isolating switches for monitoring video images of the isolating switches of various substations.

[0025] Specifically, when using the method of the present invention to identify the state of the disconnector, first use the disconnector image captured by the fixed camera in the traction substation or the unmanned aerial vehicle camera equipment to form the disconnector image library, and normalize the size of the disconnector image The size is 256 × 256 × 3 pixels, and then use the labeling software to segment the area and label the state of the isolation switch. The isolation switch image and the labeling results together constitute the isolation switch data set. Input the data set into the multi-task learning network for isolation switch segmentation and state recognition, which is mainly composed of two stages. The first stage ...

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

The invention provides an isolation switch state identification method in a traction substation, and relates to the technical field of intelligent monitoring of railway traction substations. Accordingto the method, isolation switch segmentation and state identification are carried out by constructing a multi-task learning network, and the method is mainly composed of two stages: the first stage isolation switch segmentation network comprises an input layer, a coding layer, a decoding layer, a feature fusion module and an output layer, wherein a strip-shaped pooling module and a pyramid pooling module in the decoding layer and the feature fusion module can effectively extract a rotary knife switch and other irregular-shaped features of the isolation switch and accurately segment the isolation switch; and the second-stage disconnecting switch identification network comprises an input layer, a feature extraction layer, a full connection layer and an output layer, and a global context module of the feature extraction layer can effectively extract global context information of a disconnecting switch image, thereby accurately identifying three states of on, semi-on and off of the isolation.

Description

technical field [0001] The invention relates to the technical field of intelligent monitoring of railway traction substations. Background technique [0002] As the most widely used and installed equipment in the power grid system, the disconnector is one of the key factors to determine whether the substation can operate safely. Once the isolating switch fails, it will cause serious failure and economic loss. Therefore, in the process of inspection, whether the isolating switch is working normally is an important inspection task. The traditional power inspection method mainly relies on manual inspection, which is time-consuming, has a long inspection cycle, and is easily affected by the subjective judgment of the inspection personnel. It is of great significance to find a method for identifying the state of the isolating switch that can reduce human resources and is convenient and efficient. The emergence of drones and high-definition cameras has made it possible to take i...

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): G06K9/62G06K9/34G06N3/04G06N3/08
CPCG06N3/08G06V10/267G06V2201/06G06N3/045G06F18/214
Inventor 权伟卢学民冯宽向梦陈锦雄
Owner SOUTHWEST JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com