Surface Defect Detection Network for Lithium-ion Battery Electrode Sheets

Lithium-ion batteries have become a dominant energy storage technology, widely used in critical applications such as electric vehicles, consumer electronics, and large-scale energy storage systems. As a key component, electrode sheets significantly influence battery performance and safety; defects occurring during their manufacturing process can degrade functionality and pose potential safety risks. Therefore, accurate and efficient defect detection during electrode sheet production is essential. However, the presence of multiple defect types and the high similarity among defect features often cause conventional detection networks to suffer from missed or false detections. To overcome these challenges, this paper proposes an enhanced detection network, termed YOLOv8s_AD. First, DSCDownsample utilizes convolutional layers with varying receptive fields to capture multi-scale features, thereby minimizing information loss during downsampling and preserving critical feature details. Second, the C2f_CDW module is deployed in shallow layers to extract local spatial features, while the C2f_CIB module is applied in deeper layers to capture global contextual information. This hierarchical design reduces feature redundancy and enhances the capability to distinguish diverse defect patterns. Finally, the proposed Cross Neck structure in the neck facilitates comprehensive cross-scale and cross-location feature interactions, enabling global fusion of information from multiple network layers to improve representation capacity. Experimental results demonstrate that YOLOv8s_AD reduces the number of parameters and GFLOPs by 43.5% and 41.4% respectively, while increasing mAP@50 and mAP@[50:-95] by 0.4% and 4.5%. These improvements indicate that the proposed network achieves superior detection performance with reduced computational complexity.