Fluorescent magnetic particle flaw detection method and detection system based on image processing

Abstract

The present invention provides an image-processing-based fluorescent magnetic powder flaw detection test method comprising the following steps: first, using a color CCD camera to photograph a workpiece with a fluorescent magnetic powder liquid attached to the surface, then successively extracting a R image layer, a G image layer and a B image layer of a workpiece color photograph; then separately performing pixel gain processing on the extracted R image layer, G image layer and B image layer; superimposing the R image layer and the G image layer, subtracting the B image layer from a superimposing-processed image, and finally according to length, width, area and length-width ratio of a suspected defect pattern on a final image, determining whether a suspected defect is a crack. By creative superimposing and subtraction processing of the image layers on the workpiece color photograph, an image of fluorescent magnetic powder accumulated on a workpiece real crack can be effectively highlighted, and determination of whether the workpiece meets quality requirements can be facilitated.

Description

technical field [0001] The invention relates to the field of magnetic particle flaw detection, in particular to a method and system for magnetic particle flaw detection of bearing rollers based on image processing. Background technique [0002] Rail transportation such as trains, subways, and light rails has become more and more important in the national economy because of its advantages such as large capacity and fast speed, and the safety of rail transportation has also been paid more and more attention by people. During the operation of rail transit, the wheel bearing is the key component of its operation. The wheel bearing is mainly composed of the inner ring, the outer ring and the rollers located between the inner and outer rings. In order to ensure the safety of the vehicle operation, in the production process of the wheel bearing, Flaw detection must be carried out on each component of the wheel bearing to ensure that each component meets the quality requirements. A...

AI Technical Summary

Problems solved by technology

Although this algorithm can realize the detection of magnetic particle traces to a certain extent, it still cannot completely distinguish many pseudo cracks, so this intelligent detection system for magnetic particle flaw detection defects is not practical

Images