Train wheel ultrasonic flaw detection method and system

A train wheel and ultrasonic technology, which is applied in the direction of material analysis, image data processing, and detection response signal processing using sound waves/ultrasonic waves/infrasonic waves, which can solve the problems of low reliability of detection results

CN112598654APending Publication Date: 2021-04-02BEIJING ANTIE SOFTWARE TECH
0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2021-04-02

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
Patent Text Reader

Abstract

The invention discloses a train wheel ultrasonic flaw detection method and system. The method comprises the following steps: acquiring a first image formed by an ultrasonic B-scan image of a train wheel; eliminating step echo lines and spoke plate hole echo lines in the first image to generate a second image and a step echo sound path corresponding to the step echo lines; performing binarization processing on the second image, and extracting a first connected domain set meeting condition flaw detection; and carrying out spatial distribution divergence discrimination on the first connected domain set and generating a second connected domain set used for representing the defect part. According to the invention, after the ultrasonic B-scan image is converted into a binary black-and-white image, interference echoes generated by foreign matters attached to the outer surface of a rim spoke transition region of the train wheel are identified and eliminated by calculating the spatial distribution dispersion of a black connected domain, so that the problem of false alarm of a train wheel ultrasonic flaw detection system due to foreign matters attached to the outer surface of the transitionarea is avoided, and the problem that a traditional train wheel ultrasonic flaw detection method is low in detection result reliability is solved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of rail vehicle detection, in particular to an ultrasonic judgment method and system for train wheels. Background technique

[0002] Train wheels are prone to fatigue cracks under long-term load operation. In order to ensure the safety of high-speed train operation, ultrasonic automatic flaw detection technology must be used to detect train wheel defects. For example, the mobile rim and spoke flaw detection system currently used in train maintenance in China uses advanced phased array ultrasonic flaw detection technology and conventional flaw detection technology to conduct online rim and spoke flaw detection on various types of EMU wheels to realize various types of fatigue defects and The detection of material defects, but the location of the defects in the detection results is only a single gate damage judgment based on the echo amplitude, which still requires on-site operators to manually judge and frame...

Examples

Embodiment Construction

[0020] In order to enable those skilled in the art to better understand the technical solutions of the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0021] Such as figure 1 Shown, a kind of train wheel ultrasonic judgment method comprises:

[0022] S1: Acquiring a first image composed of ultrasonic B-scan images of train wheels.

[0023] S2: Eliminate the step echo lines and the web hole echo lines in the first image to generate a second image and a step echo sound path corresponding to the step echo lines.

[0024] Further, since the line of the step echo is a horizontal straight line, the influence of the step echo can be eliminated by performing feature detection on the first image and eliminating the horizontal straight line representing the step echo included in the first image. The step echo sound path corresponding to the horizontal straight line is extracted...