A method for enhancing the accuracy of industrial bearing surface defect detection

Deep learning models often encounter challenges when detecting surface defects on industrial bearings, including inaccurate feature extraction caused by random shapes and multi-scale defects, as well as high leakage rates of small objects in complex multi-object scenes. To address these challenges, a YOLOv8n-based method (YOLOv8-IWDD) is proposed for detecting bearing surface defects. Firstly, the ImplicitHead detection head is introduced, which utilises implicit addition and multiplication to highlight key features. This enhancement improves feature extraction, resulting in improved detection accuracy for small objects, especially in complex multi-object scenarios, and effectively reduces missed detections. Secondly, the Inner-WIoU loss function optimises bounding box localisation, enabling the model to better handle randomly shaped defects, accelerate convergence, and enhance localisation accuracy. In addition, dynamic label assignment and dynamic sampling strategies are proposed to achieve flexible adjustment of sample assignment and sampling method, which further improves the detection accuracy and robustness. These strategies enhance the model’s robustness in handling multi-scale and complex shape defects. The experimental results show that YOLOv8-IWDD improves mAP0.5 by 2.9%, mAP0.5:0.95 by 9.4%, precision by 2.2%, and recall by 6.5% compared with the YOLOv8n model. The method achieves promising results in detecting surface defects on industrial bearings.