Surface Defect Detection of Bearing Rings Based on an Improved YOLOv5 Network

Abstract

Considering the characteristics of complex texture backgrounds, uneven brightness, varying defect sizes, and multiple defect types of the bearing surface images, a surface defect detection method for bearing rings is proposed based on improved YOLOv5. First, replacing the C3 module in the backbone network with a C2f module can effectively reduce the number of network parameters and computational complexity, thereby improving the speed and accuracy of the backbone network. Second, adding the SPD module into the backbone and neck networks enhances their ability to process low-resolution and small-object images. Next, replacing the nearest-neighbor upsampling with the lightweight and universal CARAFE operator fully utilizes feature semantic information, enriches contextual information, and reduces information loss during transmission, thereby effectively improving the model’s diversity and robustness. Finally, we constructed a dataset of bearing ring surface images collected from industrial sites and conducted numerous experiments based on this dataset. Experimental results show that the mean average precision (mAP) of the network is 97.3%, especially for dents and black spot defects, improved by 2.2% and 3.9%, respectively, and that the detection speed can reach 100 frames per second (FPS). Compared with mainstream surface defect detection algorithms, the proposed method shows significant improvements in both accuracy and detection time and can meet the requirements of industrial defect detection.

Keywords

• bearing ring
• surface defect detection
• deep learning
• YOLOv5