Abstract: A welding defect detection algorithm YOLO-SBRS based on YOLOv8n is proposed for welding defects with characteristics of multi-scale, complex shape and vulnerable to background interference. First, Spatial and Channel Reconstruction Convolution(SCConv) is used to improve the C2f module of the backbone network; At the same time, a Spatial Pyramid Pooling Fast Average Pooling with BiFormer Attention Module (SPPF_ABF) is designed, which replaces the maximum pooling of the original SPPF module with the average pooling operation, and introduces a two-layer routing transformer attention mechanism; Secondly, a Reparameterized Generalized Feature Pyramid Network (RepGFPN) is used to optimize the feature fusion part; Finally, based on the principle of parameter sharing and the introduction of a Module Combining Space-To-Depth and Non-Strided Convolutional Layers (SPD_Conv), the detection head is improved to achieve lightweight and improve the detection capability of the network for complex defects. Experimental results show that the accuracy of the improved algorithm and mean Average Precision at 50% Intersection over Union (mAP50) are improved by 3.1% and 2.8% respectively,which provide an efficient and feasible solution for welding defect detection.