Unmanned aerial vehicle intelligent inspection identification method for power transmission tower

A technology of intelligent patrol inspection and recognition method, which is applied in scene recognition, character and pattern recognition, computer parts and other directions, can solve the problems of not being able to judge insulator faults or defects well, time-consuming and labor-intensive, etc., and achieve edge fast computing, The effect of preventing large-scale power outages

Active Publication Date: 2021-08-10
国网湖北省电力有限公司黄石供电公司 +1
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problem that the traditional way of manual inspection is time-consuming and laborious, and it is impossible to judge whether the insulator has a fault or defect, and to provide a UAV intelligent inspection identification method for transmission towers

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
  • Unmanned aerial vehicle intelligent inspection identification method for power transmission tower
  • Unmanned aerial vehicle intelligent inspection identification method for power transmission tower
  • Unmanned aerial vehicle intelligent inspection identification method for power transmission tower

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] In this embodiment, an image intelligent inspection system for a UAV includes an image acquisition module, an image preprocessing module, a feature extraction module, a feature fusion module, a prediction and judgment module, and a fault reporting module.

[0019] see figure 1 , the image acquisition module described in the present embodiment adopts the unmanned aerial vehicle to carry the SHD10T3 camera platform, which can collect optical zoom visible light images and infrared images, and the visible light images of insulators are taken by the platform, collected once every 3 seconds, and simultaneously Output the HDMI real-time signal, and the captured images are uniformly stored in the image database of the TF card for subsequent module processing; one end of the HDMI real-time signal is connected to the air terminal of the DJI flight control, and the video stream signal is transmitted back to the flight controller to display the real-time picture. The other end is c...

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 an unmanned aerial vehicle intelligent inspection identification method for a power transmission tower, wherein an intelligent inspection system is adopted to inspect an insulator, and the intelligent inspection system comprises an image acquisition module carried by an unmanned aerial vehicle, a preprocessing module, a feature extraction module, a feature fusion module, a prediction judgment module and a fault reporting module. The identification method specifically comprises the following steps: 1) shooting an image of the insulator and transmitting the image to the preprocessing module; 2) performing non-local average denoising processing on the image and inputting the image into a feature extraction module; 3) adopting a neural feature extraction network to extract insulator shape features and fault features;4) carrying out feature fusion on the extracted high-dimensional features, and 5) judging the features through a prediction regression network. According to the power transmission tower insulator fault identification method, real-time identification of the power transmission tower insulator fault is rapidly and accurately achieved, and the maintenance efficiency of the insulator is improved.

Description

technical field [0001] The invention relates to the technical field of fault inspection and maintenance of electric transmission towers, in particular to an intelligent inspection and identification method of an unmanned aerial vehicle for electric transmission towers. Background technique [0002] Today has entered the era of artificial intelligence and big data, and deep learning and neural networks have developed rapidly. The power grid occupies a very important position in our country, and the maintenance of the power grid is also important. The construction of a smart grid has been continuously valued. The overhead transmission line is a steel frame structure facility that erects the conductor to keep it away from the ground. Insulators play the role of connecting wires and fittings in overhead transmission lines. Whether there is a hidden trouble in the insulator will have a great impact on the stable operation of the power grid. Seriously, it will cause the insulator...

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): G06K9/00G06K9/32G06K9/62G06T5/00G06T7/00
CPCG06T5/002G06T7/0002G06V20/13G06V10/25G06F18/23213G06F18/253
Inventor 刘斌熊国友高浦润卢波杨泽明杨斌曹天恩杨光灿杨涛胡芳芳
Owner 国网湖北省电力有限公司黄石供电公司
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