Bearing outer ring surface defect area detection method

Abstract

The invention discloses a method for detecting a surface defect area of a bearing outer ring. The method comprises the steps: carrying out multi-scale decomposition on an original bearing outer ring image, solving modulus maxima of each scale, and realizing edge preselection of a defect area of the bearing outer ring; clustering the edge of the defect area on the surface of the bearing outer ring to obtain each cluster, and calculating the center of each cluster to determine a growth seed point of the defect area; taking the growth seed point as a base point, taking four neighborhood pixels of the base point as a to-be-selected growth point set, traversing each pixel in the to-be-selected growth point set, and judging whether a growth termination condition is met or not so as to realize the detection of the surface defect area of the bearing outer ring. According to the bearing outer ring surface defect area detection method, higher accuracy is shown when the problem of multi-surface multi-type defect detection of the bearing outer ring is solved, meanwhile, the robustness is higher, the method can adapt to surface defect area detection under different brightness and illumination conditions, and the detection effect better than that of other bearing surface defect detection algorithms is obtained.

Description

technical field [0001] The invention belongs to a detection method in the field of bearing defect detection, and in particular relates to a detection method for a surface defect area of ​​a bearing outer ring. Background technique [0002] Bearings are the basic parts of mechanical equipment and mechanical systems, and are widely used in various precision and complex large-scale equipment such as industrial manufacturing, energy smelting and transportation. Research on bearing defect detection and diagnosis technology has always been the focus of academia and industry. The quality of bearings is directly related to the operating status and performance of the entire mechanical equipment. According to statistics, in all rotating machinery equipment using bearings, about 30% of the failures are caused by bearing quality problems. Among the bearings with quality problems, most of them are due to cracks, wear and tear on the outer ring of the bearing. Scratches and deformation c...

AI Technical Summary

Problems solved by technology

[0005] In order to make up for the shortcomings of existing bearing surface defect detection methods, the present invention provides a bearing outer ring defect detection method based on multi-scale edge information and self-adaptive growth. Th

Images