基于改进YOLOv10n的轻量级轴承表面缺陷检测方法及系统
By improving the FCF full-scale connection module and MOBFFN forward network architecture of the YOLOv10 network, the problems of insufficient multi-scale feature extraction capability and low robustness of YOLOv10 in bearing surface defect detection are solved, and efficient bearing surface defect detection is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- YANCHENG INST OF TECH
- Filing Date
- 2024-11-22
- Publication Date
- 2026-07-17
AI Technical Summary
The existing YOLOv10 network suffers from insufficient multi-scale feature extraction capability, low model robustness, and slow inference speed in bearing surface defect detection, making it difficult to achieve a balance between accuracy and efficiency.
By constructing the FCF full-scale connection module and the MOBFFN feedforward network architecture, the YOLOv10 network is improved, including interpolation upsampling, channel concatenation, feature enhancement and multi-branch convolution processing, forming the FM-NET algorithm model, which enhances feature extraction capability and model expression efficiency.
It significantly improves the model's robustness and inference speed in complex scenarios while maintaining high accuracy, achieving a good balance between accuracy and efficiency.
Smart Images
Figure CN119624897B_ABST