一种基于机器视觉的MIM涡轮叶片表面微裂纹识别方法
By employing machine vision-based methods, utilizing photometric stereo vision and topological singularity index analysis, microcracks in MIM turbine blades are accurately identified, solving the detection challenges under complex curvature and porosity interference, and achieving efficient and accurate microcrack identification and quality assessment.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- LIANYUNGANG FUTURE HIGH TECH CO LTD
- Filing Date
- 2026-03-31
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to accurately identify microcracks in MIM turbine blades under complex curvature and porosity interference, leading to false positives and false negatives, which impacts aero-engine safety.
A machine vision-based approach is adopted to acquire the original image sequence through multi-angle light source illumination. By combining photometric stereo vision solution and model projection alignment, a normal residual map is obtained. Global statistical analysis and differential operator operations are performed to calculate the topological singularity index and crack significance index. The maximum entropy threshold method is used for segmentation and skeletonization extraction to generate a defect heat map and perform quality rating and data binding.
It enables accurate identification of microcracks under complex curvature and porosity interference, reduces the false judgment rate, improves detection accuracy and stability, supports automated sorting and full life cycle data management, and meets production needs.
Smart Images
Figure CN121937455B_ABST