Steel rail defect recognition method and system based on ultrasonic signals, and electronic device

A defect identification and ultrasonic technology, which is applied in the analysis of solids using sonic/ultrasonic/infrasonic waves, material analysis using sonic/ultrasonic/infrasonic waves, and railway auxiliary equipment, etc. High accuracy and high recognition efficiency

Pending Publication Date: 2019-10-11
创新奇智(青岛)科技有限公司
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the problem of insufficient accuracy in existing rail defect identification methods based on ultrasonic signals, the present invention provides a rail defect identification method based on ultrasonic signals

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 defect recognition method and system based on ultrasonic signals, and electronic device
  • Steel rail defect recognition method and system based on ultrasonic signals, and electronic device
  • Steel rail defect recognition method and system based on ultrasonic signals, and electronic device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038]In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the accompanying drawings and implementation examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0039] see figure 1 , the first embodiment of the present invention provides a rail defect identification method based on ultrasonic signals, including the following steps:

[0040] Step S1: Obtain an ultrasonic signal for detecting rail defects, the ultrasonic signal includes a plurality of signal points having depth information and width information of the rail, and the plurality of signal points form at least one rail defect.

[0041] It can be understood that the ultrasonic signal is a plurality of discrete point values, and each point value represents the specific position of ...

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 provides a steel rail defect recognition method based on ultrasonic signals, wherein an ultrasonic signal diagram for detecting steel rail defects is acquired, wherein the ultrasonic signal diagram comprises a plurality of signal points with depth information and width information of a steel rail, the ultrasonic signal diagram is input into a plurality of RGB channels, the pluralityof output images are subjected to feature enhancement and then are overlapped, a superposition image is obtained, an initial recognition neural network is trained on the basis of a preset rectangularframe and the superposition image, and a steel rail defect recognition neural network is obtained. The ultrasonic signals are processed through a plurality of RGB channels to obtain signal points corresponding to the defects so as to determine the outline of the defects, and a plurality of signal points corresponding to the defects are positioned on the basis of a preset rectangular frame, so as to recognize the location and the type of the defects; and the method has the advantages of being more accurate in recognition of the defects and high in recognition efficiency.

Description

【Technical field】 [0001] The invention relates to the field of computer identification of rail defects, in particular to a rail defect identification method, system and electronic equipment based on ultrasonic signals. 【Background technique】 [0002] Ultrasonic rail flaw detection is a commonly used rail defect detection method at present. Ultrasonic flaw detectors are used to detect rail defects. [0003] However, in the existing ultrasonic rail flaw detection method, the ultrasonic wave pattern emitted by the rail is usually analyzed based on the ultrasonic flaw detector, but some normal structures in the rail will also reflect the ultrasound, forming dense echo patterns, such as: bolts Holes, rail joints, holes, wire holes, resulting in frequent false alarms and insufficient accuracy. 【Content of invention】 [0004] In order to overcome the problem of insufficient accuracy in existing rail defect recognition methods based on ultrasonic signals, the present invention pr...

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): G01N29/44G01N29/04B61K9/10G06T7/00G06T7/11
CPCG01N29/4454G01N29/4481G01N29/4427G01N29/04B61K9/10G06T7/0004G06T7/11G06T2207/20081G06T2207/20084
Inventor 张发恩凌明艾国
Owner 创新奇智(青岛)科技有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap