A workpiece surface defect detection and decision method based on credibility evaluation and intelligent review

CN122243860BActive Publication Date: 2026-08-28ANHUI UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202610079516.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2026-01-21
Publication Date
2026-08-28
Estimated Expiration
2046-01-21

AI Technical Summary

Technical Problem

然而在对质量一致性要求严苛的精密制造领域,检测结果的决策可靠性仍有问题

Benefits of technology

1、本发明在传统缺陷检测与评分基础上,引入了一套多层次可信度评估与动态复核机制,显著提升了检测系统的可靠性、决策透明性与工业适用性。通过构建综合可信度分数,从分类置信度、特征稳定性、缺陷区域一致性三个维度对每次评分结果进行量化评估,极大地增强了结果的可解释性与决策参考价值。

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122243860B_ABST
    Figure CN122243860B_ABST
Patent Text Reader

Abstract

The present application relates to the technical field of workpiece surface defect detection, and particularly relates to a workpiece surface defect detection and decision method based on credibility evaluation and intelligent review. The method adopts hierarchical module design: an image acquisition module synchronously collects workpiece surface images through visible light and polarized light cameras; a data preprocessing module performs fusion, denoising, enhancement and standardization processing on the images; a data analysis module extracts features and completes defect classification and quantitative scoring; a judgment and review module performs credibility evaluation and critical state intelligent review on the scoring results to improve decision reliability; and a result output module generates a structured report and links with production line MES and PLC systems through an interface to realize automatic alarm and sorting of defective workpieces.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • New energy automobile part surface defect testing method based on computer vision

    CN119091186A

  • Metallographic defect intelligent detection system and method based on improved YOLOv11

    CN120931651A