Railway vehicle wheel set tread 3D image detection method

Abstract

The invention discloses a rail vehicle wheel set tread 3D image detection method, which comprises the following steps: (1) when a train approaches an incoming line sensor, acquiring a train incoming line signal, and entering a train receiving state; the speed measurement radar obtains the real-time passing speed of the train, the train number recognition mechanism obtains the number of the passing train, and the positioning device obtains the position of each wheel and starts the corresponding tread image acquisition equipment to acquire a wheel tread image; acquiring and combining each wheel on a single side through a plurality of pairs of tread image acquisition devices so as to obtain a wheel tread image covering a complete tread, and matching the acquired wheel tread image information with a vehicle number; and (2) processing the acquired image to form a 2D image of the wheel tread and a 3D image of a corresponding area, and analyzing and calculating the 3D image data to obtain the rim thickness, the Qr value and tread wear information. According to the invention, through coordination work of multiple groups of tread image acquisition devices, non-stop on-line real-time detection of the full-circumference tread of the wheel is realized.

Description

technical field [0001] The invention specifically relates to the technical field of tread image detection, in particular to a 3D image detection method of a wheelset tread of a rail vehicle. Background technique [0002] Rail transit occupies a relatively important position in the field of freight and passenger transport due to its advantages of large transportation volume, speed, safety and reliability. In recent years, my country's rail transit industry has developed rapidly. The construction of rail transit network has become a business card for urban development. Rail transit has gradually become the first choice for citizens to travel, effectively solving the problem of public transportation congestion in major cities. . [0003] As the core part of rail transit, trains may experience abnormality of car body parts during operation, which seriously threatens the safe running of trains. Among them, the wheels of the train run directly on the train track, and the working ...

AI Technical Summary

Problems solved by technology

[0004] At this stage, most of the detection methods for wheel treads are still mainly based on manual visual inspection. It is necessary to park the vehicle in the maintenance garage, and then arrange maintenance personnel to perform tread detection on each wheel individually. Manual detection is not only inefficient, labor-intensive, and The detection accuracy and stability are affected by human subjective factors, and the wheel tread is covered by the car body and the track by nearly half during the static detection process, making it difficult to check the condition of the entire wheel tread area

In addition, there are devices on the market that use images to detect wheel tread damage, but these devices mostly use 2D cameras to collect plane images. The objective factors such as the unclear boundary between the two-dimensional image data make it difficult to identify and detect the defects of three-dimensional objects through the analysis of two-dimensional image data, resulting in low detection rate, low repeatability and other shortcomings, and it is impossible to effectively distinguish stains on the tread, scratches, etc. Marks and other interference and real damage can easily cause false alarms and affect the detection efficiency of staff

Images