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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


