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

Power transmission line foreign matter and environment abnormal state detection method

A transmission line and abnormal state technology, applied in the field of image recognition, can solve the problems of real-time monitoring of unfavorable transmission lines, slow down the detection speed, consume large computing resources, etc., to achieve the effect of ensuring speed, accurate output results, and accurate target detection

Pending Publication Date: 2022-03-25
STATE GRID FUJIAN ELECTRIC POWER RES INST +1
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the two-stage algorithm with good effect is to use the generated candidate target area to locate and classify the target, such as Fast RCNN, Faster RCNN, RFCN, etc., but generating candidate areas will consume a lot of computing resources and reduce the detection speed, which is not conducive to Real-time monitoring of transmission lines

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
  • Power transmission line foreign matter and environment abnormal state detection method
  • Power transmission line foreign matter and environment abnormal state detection method
  • Power transmission line foreign matter and environment abnormal state detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present application mainly targets foreign matter and environment abnormal state in transmission lines, these foreign matter and environment abnormalities may cause transmission line to run malfunction, timely detection and clean up foreign matter to eliminate abnormal state, and ensure that power transmission line is safe and stable. Incidental transmission line inspection efficiency is improved, the present application provides a method of detecting transmission line foreign objects and anomalous state detection. In particular, the present invention provides a method for detecting a state of transmission line foreign matter and an environmental abnormal state. The method is based on YOLOV4, and the various parameters in the fine tuning network optimizes the detection efficiency of transmission line foreign objects and abnormal states, joining the Coordiante Attension attention mechanism to improve the focus of the model to the target characteristics, thereby enhancing...

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 discloses a transmission line foreign matter and environment abnormal state detection method. According to the method, aiming at various conditions, such as various suspended foreign matters, bird nests and the like, which may cause abnormity of the power transmission line, on the power transmission line, effective detection of the foreign matters and abnormal states of the power transmission line is realized by embedding a Coordinate Attention module on a fine-tuned YOLOv4 model, so that the accuracy of target detection is ensured, and the speed of model training test is also ensured. The model fine tuning enables the network to be more efficient when detecting the foreign matter and abnormal state data set of the power transmission line, and the embedding of the Coordinate Attention module helps the model to pay more attention to the target feature area when extracting the target feature, so that the final output result is more accurate.

Description

Technical field [0001] The present application relates to the field of image recognition, and more particularly to a transmission line foreign body and an environmental abnormal state detection method. Background technique [0002] my country's power grid is the world's largest interoperable Internet power system. With the construction of the grid, the scale of transmission lines is expanding, and the challenges are constantly upgrading. Common foreign objects including the transmission line include a Bird's Nest, a kite, a kite, a plastic bag. These foreign objects can cause short circuits and trigger a hill, smoke, so that the power system has failed, bringing huge gab to the country and people. Economic loss and safety hazards, so it is important to detect and clean up foreign affixions. Since the distribution of transmission lines is wide, it is often distributed in some people's smoke, environmentally complex areas, and the traditional artificial inspection work is low, and ...

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): G06V20/10G06K9/62G06N3/04G06N3/08G06V10/25G06V10/44G06V10/80G06V10/82
CPCG06N3/08G06N3/045G06F18/253
Inventor 杨彦黄建业林爽郑州刘冰倩廖飞龙辛宇晨李扬笛陈锦铭
Owner STATE GRID FUJIAN ELECTRIC POWER RES INST
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