Image-based method for detecting qualified property of dimension of railhead cross-section contour

A technology of contour size and detection method, which is applied to measurement devices, instruments, optical devices, etc., can solve the problems of inconvenient quantification results, low degree of detection automation, inconvenient operation, etc., and achieves high degree of automation, convenient operation, and improved The effect of edge positioning accuracy

Inactive Publication Date: 2017-10-03
NANCHANG HANGKONG UNIVERSITY
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The object of the present invention is to provide a kind of image-based rail head (60kg/m) cross-sectional contour dimension qualification detection method, aims to solve the ...

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
  • Image-based method for detecting qualified property of dimension of railhead cross-section contour
  • Image-based method for detecting qualified property of dimension of railhead cross-section contour
  • Image-based method for detecting qualified property of dimension of railhead cross-section contour

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention adopts such as figure 1 The image-based qualified detection method of the rail head section is shown to realize the measurement of the fullness of the rail crown in the geometric dimension of the rail image. The specific implementation steps are as follows:

[0041] 1. Rail section image preprocessing, specifically including the following steps:

[0042] (1.1) Carry out median filtering to the collected target image to reduce noise interference;

[0043] (1.2) Use the maximum between-class variance method to perform threshold segmentation on the filtered image to obtain the binary image of the track head.

[0044] 2. The scanning method determines the lower left end point and the lower right end point of the track head, which specifically includes the following steps:

[0045] (2.1) For the binary image of the rail head obtained in the first step, use the scanning method. First, start from the upper left corner of the image, scan from left to rig...

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 image-based method for detecting a qualified property of the dimension of a railhead cross-section contour. The method comprises: preprocessing of a cross-section image of a steel rail is carried out; with a scanning method, a lower left end point and a lower right end point of a railhead are determined; a width measuring region at the railhead is determined; a measuring region of a rail crown point of the railhead is determined; a width data point and a rail crown point of railhead measurement are determined; on the basis of least square circle fitting, a data point and a rail crown point are determined by combining a circle center vector method; a rail crown plumpness detection region is determined; and rail crown plumpness qualification detection is carried out. The method has the following advantages: a singular point is removed by using a least square straight line fitting method, so that the edge positioning precision is improved; with a circle center vector method, a control point is selected, so that the rail crown positioning precision is improved; and non-destructive and non-contact detection is carried out on the railhead cross-section contour dimension by using an image processing method. The image-based method has characteristics of high automation degree, convenient operation, high efficiency and precision, and convenient storage of a quantized detection result.

Description

technical field [0001] The invention relates to a method for detecting the conformity of the cross-sectional contour dimension of a rail head, in particular to an image-based method for detecting the conformity of the cross-sectional contour dimension of a rail head (60kg / m). Background technique [0002] Qualification inspection of rail cross-section contour size is an important link in the seamless rail welding production line and an important means to ensure the quality of rails. The detection content mainly includes the parameters of rail section symmetry, rail height, rail head width, rail crown fullness and rail waist thickness. [0003] At present, our country mainly uses inspection templates in the welding production line to check the conformity of the profile dimensions of the rail head section. According to the parameters that need to be tested, use the inspection templates to carry out the clamping quantity one by one, and use the outline of the template itself to...

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): G01B11/02
CPCG01B11/02
Inventor 熊邦书刘鑫余淑真莫燕
Owner NANCHANG HANGKONG UNIVERSITY
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