Rail wear degree identification method and system

Abstract

According to a rail wear degree identification method and system provided by the invention, according to the contour characteristics of the train hub, by adopting a Kalman filtering matching trackingalgorithm, and combining an existing infrared sensor, the wheels are counted during the high-speed operation of a train, and the wear degree is judged, the accurate classification is realized, the technical difficulty is reduced, and the accuracy is improved. By adopting a multi-information fusion algorithm, according to the identified rail defect type and through the fusion judgment of the wheelnumber of the rail, the rail abrasion degree grade is outputted, a manager can monitor the operation state of the equipment at any time and any place, the rail can be maintained in time, the maintenance cost at the later equipment operation is reduced, and meanwhile the safety of the equipment operation is improved.

Description

technical field [0001] The present disclosure relates to a method and system for identifying the wear degree of a track. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art. [0003] With the development of our country's regional cities, the demand for travel increases, and the rapid development of railway traffic, with the continuous increase of passenger volume and service life, various damage problems will inevitably occur on the rails. According to the data, common rail surface damages, that is, rail surface defects mainly include cracks, peeling, scratches, wrinkles, broken rails, scars and other forms. Among them, cracks and scars are more common, and they are also particularly serious types of defects. Under the long-term rolling of the train, it is easy to cause the rail surface to peel off pieces, and the stripped pieces will in turn furthe...

AI Technical Summary

Problems solved by technology

[0005] 1. The outdoor environment is changeable, and it is impossible to collect two-dimensional images of a single variable

[0006] 2. Affected by light and shadow, the brightness of the collected image is uneven

[0007] 3. There is a gap in the construction process. The surface of the rail is rough and there are large particles, which affect the extraction of crack images. A single sensor judges the degree of damage by counting tires, which has high deployment costs, low efficiency, and inaccurate judgments.

Images