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

Intelligent detection method for bolt pin missing of power transmission tower based on an attention mechanism

A technology of attention and transmission towers, applied in computer parts, image analysis, instruments, etc., can solve the problems of time-consuming and laborious detection, inaccurate detection, etc.

Active Publication Date: 2020-12-04
HEFEI UNIV OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention aims to solve the deficiencies in the above-mentioned prior art, and proposes a detection method for missing pins of transmission tower bolts based on an attention mechanism, in order to solve the problem of time-consuming and laborious detection of missing pins, or inaccurate detection, and improve Real-time detection, and accurate detection of the missing state of tiny pins under complex backgrounds, so as to meet the actual needs of accuracy and speed

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
  • Intelligent detection method for bolt pin missing of power transmission tower based on an attention mechanism
  • Intelligent detection method for bolt pin missing of power transmission tower based on an attention mechanism
  • Intelligent detection method for bolt pin missing of power transmission tower based on an attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0079] In this embodiment, a method for detecting the absence of transmission tower bolts and pins based on the attention mechanism is carried out as follows:

[0080] Step 1. Preprocess the transmission tower pin image set to obtain the preprocessed pin image set. In this embodiment, first use random cropping to convert the image into a square, and then uniformly reset the image using bilinear interpolation The size is 448*448, and then de-shaking and anti-noise processing is performed. Finally, in order to facilitate convergence, the image is unified and normalized;

[0081] Step 2. Use the generative confrontation network GANs to expand the preprocessed pin image set to obtain the expanded pin image set. The generated samples do not necessarily have pins or meet expectations, and the samples need to be manually screened , the filtered sample set is mixed with the original sample set to form an effective sample set. In this example, there are 100 original samples and 500 sel...

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 intelligent detection method for bolt pin missing of a power transmission tower based on an attention mechanism. The method comprises the steps: 1, preprocessing a power transmission tower pin image set; 2, constructing a perturbb neural network model based on an attention mechanism; 3, constructing a multi-level identification network by utilizing the model in the step2; 4, performing feature fusion on multi-level network output by using Sugeno fuzzy integration, and outputting a detection result. According to the invention, the problem that pin missing detection wastes time and labor or is inaccurate can be solved, the real-time performance of detection is improved, and the missing state of the micro pin under a complex background can be accurately detected, so that the actual requirements of accuracy and rapidness are met.

Description

technical field [0001] The invention relates to high-voltage transmission line inspection technology, image recognition technology, and the fields of fuzzy integration, and in particular to a transmission tower pin defect detection method based on deep learning and multi-feature fusion. Background technique [0002] my country carries the electricity demand of 1.3 billion people. With the rapid development of my country's comprehensive national strength, people's living standards and quality of life continue to improve, which brings about the rapid increase of electrical equipment and the continuous increase in electricity demand. increased. Whether it is industrial electricity or domestic electricity, transmission towers are the most commonly used supports for high-voltage transmission lines. Most of them at home and abroad use hot-rolled equilateral angle steel and space steel structures connected by bolts. With the rapid development of the steel industry and the continuou...

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
IPC IPC(8): G06K9/32G06K9/62G06N3/04G06T7/00
CPCG06T7/0002G06V10/25G06N3/045G06F18/214Y04S10/50
Inventor 李帷韬管会敏彭思遥邓雅丽吴刚
Owner HEFEI UNIV OF TECH
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