Foreign object intrusion detection method for power transmission channel based on deep learning

A transmission channel and foreign body intrusion technology, applied in the fields of image processing, power grid operation and maintenance, filtering algorithm, deep learning, semantic segmentation, can solve the problems of intrusion transmission channel, shortened limit discharge distance of high-voltage lines, poor anti-interference ability, etc., to achieve enhanced Target features, ease of distance measurement, and the effect of improving robustness

Active Publication Date: 2022-06-24
INTEGRATED ELECTRONICS SYST LAB
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] In the process of power transmission, there are mainly two types of problems: one is that due to strong winds and other reasons, the distance between conductors becomes smaller, and the limit discharge distance of high-voltage lines is shortened, which endangers the safety of transmission lines and even causes large-scale power outages; Large operating equipment such as cranes invade the transmission channel, often causing damage to the transmission line
However, its effect is not ideal in complex weather environments, and its anti-interference ability is poor

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
  • Foreign object intrusion detection method for power transmission channel based on deep learning
  • Foreign object intrusion detection method for power transmission channel based on deep learning
  • Foreign object intrusion detection method for power transmission channel based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0028] The embodiment of the present invention is described by taking the intrusion detection of a hoisting machine in a power transmission channel as an example. like figure 1 As shown, it is a flowchart of the intrusion detection of a power transmission channel hoisting machine according to an embodiment of the present invention, including the following steps:

[0029] S1. Image input of power transmission channel.

[0030] S2, us...

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 relates to a deep learning-based foreign object intrusion detection method for a power transmission channel. Aiming at the overhead line wire in the power transmission channel, the improved Mask-RCNN wire detection method is used to realize the semantic segmentation of the wire; the intrusion detection is performed on the distance between the wire and the foreign object At the same time, an optimized deduplication algorithm was proposed to obtain a more accurate pixel-level shape of the wire; the method of monocular distance measurement was used when the foreign object invaded, and the distance between the wire and the foreign object was obtained by converting the reference object; for the detection of foreign object intrusion in the transmission channel , adopt the method of real-time monitoring and early warning to carry out monitoring and early warning. The present invention uses the guide image for the power transmission channel to carry out guided filtering, enhances the characteristics of the target, weakens the impact caused by the weather, and improves the robustness; proposes an improved Mask R-CNN algorithm to divide the target into pixel levels, which is convenient for distance measurement; proposes a new algorithm Fit the shape of the wire and remove the weight to improve the accuracy.

Description

technical field [0001] The invention belongs to the technical field of power grid operation and maintenance, and in particular relates to a deep learning-based foreign object intrusion detection method in a transmission channel, involving filtering algorithms, image processing, deep learning, semantic segmentation and other fields, and can be used for detecting the intrusion of lifting machinery into a transmission channel, etc. Abnormal conditions that endanger the safe operation of the power grid. Background technique [0002] In the process of power transmission, there are mainly two types of problems: First, due to strong winds and other reasons, the distance between wires becomes smaller, and the limit discharge distance of high-voltage lines is shortened, which endangers the safety of transmission lines, and even causes large-scale power outages; Large-scale operation equipment such as cranes invades the transmission channel, often causing damage to the transmission li...

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 Patents(China)
IPC IPC(8): G06V10/25G06V10/26G06V10/30
CPCG06V10/30G06V10/25G06V10/267
Inventor 张合宝田圣柯卢闽王建功林国春刘晓亮
Owner INTEGRATED ELECTRONICS SYST LAB
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