一种基于机器视觉的发动机叶片缺陷检测方法
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHENGDU AERONAUTIC POLYTECHNIC
- Filing Date
- 2026-05-14
- Publication Date
- 2026-07-17
AI Technical Summary
Existing machine vision inspection technology suffers from low defect detection accuracy in engine blade inspection, especially in its inability to effectively separate defects and texture information at different scales, leading to missed detections and false detections.
An image pyramid is constructed using multi-scale Gaussian blur and downsampling. Defect enhancement is performed on detail images at different scales using adaptive enhancement coefficients, and then processed in conjunction with a multi-scale detail detection network.
It significantly improves the accuracy and robustness of engine blade defect detection, reduces the false negative and false positive rates, and can more accurately identify normal textures and real defects on complex surfaces.
Smart Images
Figure CN122199536B_ABST