Coal mining machine part production quality inspection method and system based on machine vision

By combining the differences in shadow morphology under multiple illumination angles with broadband reflectance data, the problem of distinguishing between pseudo-defects and real damage in existing technologies has been solved, thereby improving the accuracy and reliability of coal mining machine component inspection.

CN122545517BActive Publication Date: 2026-09-18CHINA COAL TECH GRP INFORMATION TECH CO LTD
2 Cites 0 Cited by

Patent Information

Application Number
CN202611039183.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2026-07-14
Publication Date
2026-09-18
Estimated Expiration
2046-07-14

AI Technical Summary

Technical Problem

Existing machine vision-based methods for inspecting coal mining machine components struggle to distinguish between pseudo-defects caused by surface deposits and genuine physical damage to the component substrate, leading to a decrease in the accuracy of quality inspection results.

Method used

By combining shadow morphology differences under multiple illumination angles and broadband reflectance data, the pseudo-defects caused by surface attachments and the real physical damage to the component substrate can be distinguished through shadow mutation factor and spectral authenticity score.

Benefits of technology

It improves the accuracy and reliability of quality inspection, reduces the false judgment rate, and enables effective differentiation between false defects and real damage.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present application relates to the technical field of defect detection, in particular to a coal mining machine part production quality inspection method and system based on machine vision, wherein the coal mining machine part production quality inspection method based on machine vision comprises: determining a general defect area on the surface of the part; determining a shadow mutation factor of each general defect area based on the difference in shadow appearance under different illumination angles; obtaining wide spectrum reflectivity data, and determining the reflectivity curve offset degree and the spectral authenticity score of each general defect area based on the wide spectrum reflectivity data; determining the defect authenticity confidence of each general defect area; and determining the authenticity of the general defect area. The present application realizes the effective distinction between the pseudo-defects caused by surface attachments and the real physical damage of the part substrate by fusing the technical information of two orthogonal dimensions of stereo light shadow appearance difference and wide spectrum excitation characteristics, and comprehensively evaluating the physical appearance mutation degree and spectral response difference of the general defect area on the surface of the coal mining machine part.
Need to check novelty before this filing date? Find Prior Art