Unlock instant, AI-driven research and patent intelligence for your innovation.

Selection method for laser image characteristic quantity related to steel-rail abrasion loss

A technology of image feature quantity and rail wear, which is applied in the detection field, can solve the problems of low detection efficiency, stay at the level of theoretical research, and cannot realize step-by-step detection, and achieve the effect of convenient calculation and convenient wear width and depth

Active Publication Date: 2018-06-08
DALIAN NATIONALITIES UNIVERSITY
View PDF10 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, in my country, there are main methods such as contact fixture measurement, eddy current detection, and optical triangulation measurement in rail wear detection in China. The detection results often depend on the attitude of the detection workers and the experience of using the instrument. These methods have low detection efficiency and low detection accuracy. High and many other problems can no longer meet the needs of the current high-speed development
Although there is now a detection equipment that uses lasers to detect the surface wear of rails, it cannot achieve accurate step-by-step detection, and other detection methods are only at the level of theoretical research.

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
  • Selection method for laser image characteristic quantity related to steel-rail abrasion loss
  • Selection method for laser image characteristic quantity related to steel-rail abrasion loss
  • Selection method for laser image characteristic quantity related to steel-rail abrasion loss

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0012] Example 1: An automatic rail wear detection method. Collect the laser image of the rail and compare it with the laser light strip image of the complete rail to determine whether the detected rail is abraded. If the rail is abraded, the collected laser image Laser image processing is performed, and the laser image processing includes image preprocessing and image edge extraction. After laser image processing, laser image feature quantities related to rail wear are selected and extracted to calculate rail wear depth and width. Wherein: the extracted laser image feature quantity related to the rail wear is more than one of the following feature quantities:

[0013] 1) The length of the two straight sections of the laser image l A And l B ;

[0014] 2) The width difference e between the two linear laser images;

[0015] 3) The longitudinal position difference z of the two linear laser images;

[0016] 4) The length of the transition section between the two linear laser images l C ...

Embodiment 2

[0045] Example 2: As a supplement to the technical solution of Example 1, or as a separate example: the wear mainly occurs on the head of the rail, and the wear includes top surface wear and side wear. These two values ​​must be tested at the same time. , To comprehensively judge the degree of rail wear. In this embodiment, a high-intensity narrow beam is used. The plane of the laser and the beam is at an angle of 60° with the surface of the steel rail under test. The high-resolution area CCD image sensor is located directly above the laser image to capture the laser image. The beam image of the worn rail surface is curved, and the width and depth of the rail wear are determined by the position and degree of the bending point.

[0046] The rail wear automatic detection device includes: a line laser, CCD image sensor, microprocessor, execution unit, display and sound and light alarm unit and interface unit. The CCD image sensor collects the laser image, and the obtained image inf...

Embodiment 3

[0071] Embodiment 3: A steel rail wear detection device, including a word line laser, a CCD image sensor and a microprocessor, the plane of the word line beam emitted by the word line laser and the surface of the measured rail are at a 60° angle, and the CCD image sensor Located directly above the plane where the line beam is located, the input end of the microprocessor receives the rail image information collected by the CCD image sensor and executes the rail wear detection method. The detection method may be the detection method in Embodiment 1. The laser is irradiated at a certain angle with the surface of the rail to ensure that the two laser images formed on the surface when the rail is worn are not in a straight line in the direction perpendicular to the rail; 60° is for the two images to form a special triangle on the worn section. That is, a 60° right-angled triangle, so that it is convenient to calculate the width and depth of wear.

[0072] As an embodiment, the detecti...

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 a selection method for the laser image characteristic quantity related to the steel-rail abrasion loss, and belongs to the field of detection. When a combination for judging the laser image characteristic quantity is selected, it is hypothesized that M is a characteristic sample set collected in a fixed-point mode on a steel rail with abrasion, the set comprises N fixed-point laser image characteristic quantities for reflecting abrasion, relation-degree coefficients are selected as metric parameters, two laser image characteristics are related to redundancy characteristics, one of the two laser image characteristics is only selected as the laser image characteristic quantity for judging steel-rail abrasion to obtain the combination capable of effectively judging thesteel-rail abrasion width and depth with the fewest laser image characteristic quantities, and some characteristic quantity of steel-rail abrasion is obtained after calculation through the characteristic quantity combination.

Description

[0001] This application is a divisional application with application number 201610765945.1, application date 2016-08-30, and the title of the invention "Automatic Rail Wear Detection Device". Technical field [0002] The invention belongs to the field of detection, and relates to an automatic rail wear detection device, in particular to a rail wear automatic detection device based on a line laser image processing and a microprocessor that can effectively detect the rail head surface abrasion depth and width. Background technique [0003] Railway is the main artery of transportation. Compared with other modes of transportation, heavy-duty railway transportation has developed rapidly around the world due to its large volume and low cost. In rail equipment, steel rail is the most important component, which directly bears the load of the train and guides the running of the wheels. Whether the technical condition of the rail is intact directly affects whether the train can run safely, ...

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): B61K9/08
CPCB61K9/08
Inventor 张秀峰王娟孙进生
Owner DALIAN NATIONALITIES UNIVERSITY