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

Steel rail surface damage detection method based on pulse coupling neural network

A technology of pulse-coupled neural and detection methods, applied in biological neural network models, neural architectures, image data processing, etc., can solve problems such as difficulty in comprehensive coverage, low degree of intelligence, limited and one-sided detection results, etc.

Inactive Publication Date: 2020-09-04
东莞灵虎智能科技有限公司
View PDF6 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it is difficult to accurately capture the changes of rail surface defects from the perspective of gray value comparison alone, and it is also difficult to achieve comprehensive coverage of damage types. It lacks digital conversion expression, lacks flexibility, and cannot meet the needs of different defect processing.
This method only extracts the geometric features of the suspicious defect rectangular area, and judges whether it is a rail defect based on this feature. The detection results obtained are too limited and one-sided. There are disadvantages of manual intervention

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
  • Steel rail surface damage detection method based on pulse coupling neural network
  • Steel rail surface damage detection method based on pulse coupling neural network
  • Steel rail surface damage detection method based on pulse coupling neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0076] The present invention will be further described below through specific embodiments in conjunction with the accompanying drawings. These embodiments are only used to illustrate the present invention, and are not intended to limit the protection scope of the present invention.

[0077] A rail surface damage detection method based on pulse-coupled neural network detects the position and size of rail surface defects and classifies them through the analysis and processing of image data, and finally points out the type of track defects, which includes the following four steps:

[0078] S1, image preprocessing;

[0079] S2, preliminary detection of defects based on pulse-coupled neural network;

[0080] S3, accurate calculation of features;

[0081] S4, defect classification.

[0082] In the step S1, in the data filtering process of extracting the track part in the image, the present invention adopts the horizontal projection method to extract the rail surface image, because...

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 the field of rail transit and steel rail flaw detection, in particular to a steel rail surface flaw detection method based on a pulse coupling neural network, which realizes recognition and detection of steel rail surface flaws through the following steps: S1, image preprocessing; S2, performing preliminary defect detection based on a pulse coupling neural network; S3, accurately calculating features; and S4, performing defect classification. The method has the advantages that feasible, efficient and flexible algorithm support is provided for intelligent detection andsteel rail surface defect recognition, the accuracy and efficiency of steel rail surface damage judgment are improved, the cost of manual steel rail detection is reduced, and rail breakage accidents are effectively prevented.

Description

technical field [0001] The invention relates to the fields of transportation, industrial monitoring, digital image processing and pattern recognition, in particular to a detection method for rail surface damage based on a pulse-coupled neural network. Background technique [0002] China has a vast territory, deep inland, large population, unbalanced distribution of resources, and unbalanced industrial layout. Railway transportation, which has the characteristics of safety, economy, all-weather transportation, and large capacity, has outstanding comparative advantages among various transportation methods, and is an important national priority. The transportation infrastructure has a special and important position and role in economic and social development. Accelerating the development of railways has become the consensus of all aspects of the domestic society. However, with the expansion of the railway network and the increase in the demand for railway maintenance and repair...

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): G06T7/00G06K9/62G06N3/04G06N3/06
CPCG06T7/0004G06N3/061G06N3/049G06N3/045G06F18/241
Inventor 梁帆余旸
Owner 东莞灵虎智能科技有限公司
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