A method of detecting a bearing

By driving the inner ring of the bearing to rotate, which in turn causes the rollers to rotate, and combining a high frame rate camera and image processing algorithms, the problems of low detection efficiency and incompleteness in existing technologies are solved, and efficient and high-precision full-circumference detection of bearing rollers is achieved.

CN122108587APending Publication Date: 2026-05-29HUANGSHI BANGKE TECH CO LTD

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
HUANGSHI BANGKE TECH CO LTD
Filing Date
2026-01-15
Publication Date
2026-05-29

AI Technical Summary

Technical Problem

Existing bearing roller inspection technologies suffer from low inspection efficiency and incomplete inspection. Individual inspection modes are cumbersome, and post-assembly inspection is limited by structural constraints, resulting in the omission of defects and failing to meet the demands of high-precision and high-efficiency production.

Method used

By driving the inner ring of the bearing without an outer ring to rotate, the roller can simultaneously revolve and rotate. Combined with high frame rate shooting by a camera and image preprocessing, the YOLO series algorithm is used for defect detection to ensure that the entire circumference of the roller is captured and identified.

Benefits of technology

It achieves high efficiency and high precision in full-circumference inspection of bearing rollers, reduces defect omissions, and improves production efficiency and product quality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122108587A_ABST
    Figure CN122108587A_ABST
Patent Text Reader

Abstract

The application belongs to the field of bearing detection, and particularly relates to a method for detecting a bearing, comprising the following steps: S1: driving a bearing inner ring without an outer ring to rotate, and rotating rollers while rotating the bearing inner ring to be detected; S2: photographing the rollers in S1 by using a camera, a photographing frame rate of the camera, wherein the photographing frame rate is the photographing frame number of a single roller rotation period; the rotation period of the single roller is T, the rotation speed of the roller is n, the pitch diameter of the roller is D, the diameter of the roller is d, the taper coefficient of the roller is K, and the rotation speed of the bearing inner ring to be detected is n0; S3: pre-processing the photographed image; and S4: detecting defects of the pre-processed image in S3. The application makes the rollers simultaneously have two motion states of revolution and rotation, and sets the photographing frame rate of the camera based on the size characteristics of the bearing to be detected, so that the camera can capture the arc surface image of each roller of the bearing to be detected at the most efficient photographing rhythm, and the detection efficiency is greatly improved.
Need to check novelty before this filing date? Find Prior Art