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

Electric tower bolt detection method

A detection method and electric tower technology, applied in the direction of neural learning methods, instruments, biological neural network models, etc., can solve problems such as inability to accurately detect pin dropouts, and achieve the effect of improving detection speed and reducing detection area

Pending Publication Date: 2022-04-08
国网浙江省电力有限公司龙游县供电公司
View PDF1 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The invention mainly solves the problem that the prior art cannot accurately detect whether the plug is off; it provides a method for detecting the plug of an electric tower

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
  • Electric tower bolt detection method
  • Electric tower bolt detection method
  • Electric tower bolt detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0040] A kind of electric tower plug detection method of this embodiment, such as figure 1 shown, including the following steps:

[0041] Collect the tower images collected by the UAV. The number of tower images collected is 2000-3000, and a sample database is established with the tower images as samples; the more image samples in the database, the use of these samples to After each network model is trained, higher detection accuracy can be obtained, but at the same time it will also increase the difficulty of training. Therefore, using 2000-3000 images as a sample set can take into account both detection accuracy and training difficulty.

[0042] Use the Yolo V5 model to identify the connection of the electric tower and detect the connection; according to the images collected by the drone, it can be seen that the bolts are distributed in various positions on the electric tower, but not all bolts need pins, through the image The analysis of a large number of images in the lib...

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 an electric tower bolt detection method. In order to solve the problem that whether the bolt falls off or not cannot be accurately detected in the prior art, the method comprises the steps of establishing a database, performing joint detection by utilizing a Yolo V5 model, detecting the position of the bolt and the existence of the bolt by utilizing a Fast RCNN model, performing edge extraction by utilizing a canny operator, and calculating the curvature of an edge curve to judge whether the bolt falls off or not. The detection accuracy can be improved; the connection part is firstly identified, and bolt detection is carried out on the connection part, so that the detection area is reduced, and the detection speed is improved.

Description

technical field [0001] The invention relates to the technical field of target detection in deep learning, in particular to a method for detecting electric tower pins. Background technique [0002] In recent years, drone inspections have been widely used in the power industry, especially in areas where operators are not convenient to work, drones play a great role. Line inspection is one of the most important tasks in the electric power industry. At present, drones are mostly used for inspections. The targets of drones in line inspection include but are not limited to missing anti-vibration hammers, rust, foreign objects, damaged insulator bottles, etc., and missing pins. Detection is one of the current difficulties in detection. The main reason for the difficulty in judging is that compared to electric towers, insulator bottles and foreign objects, etc., the pins are small and many. During the process of image collection by the UAV, the positions of all the pins cannot be ta...

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): G06V20/17G06V10/44G06V10/46G06V10/82G06N3/04G06N3/08
Inventor 司海涛张小龙徐小峰章华田仲旭
Owner 国网浙江省电力有限公司龙游县供电公司
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