Automatic Solder Defect Detection in Electronic Components Using Transformer Architecture

In order to adapt to the high standard of defect detection in industrial production for electronic component soldering and to address the issues of unbalanced integrated circuit (IC) defect samples and the difficulty of defect detection and segmentation, this article proposes a model based on the Swin transformer architecture for automatic detection and segmentation of solder defects in electronic components. The approach involves feeding real defect samples collected from industrial production into the cycle-generative adversarial network (Cycle-GAN), which generates a balanced and sufficient sample dataset through adversarial generation. The Swin transformer framework is then applied to the current mainstream Mask R-CNN, resulting in an improved network model named Swin transformer-based mask R-CNN (ST-mask-rcnn). This model effectively detects IC pin soldering defects and solder joints of surface-mounted devices (SMDs). The experimental results demonstrate that the proposed method successfully addresses the sample imbalance problem in electronic components. It achieves a 6% and 18% improvement in mean average precision (mAP) for IC pin soldering defects and SMD resistive solder joints detection, respectively. Additionally, it enhances the segmentation accuracy to 99.81% and 99.92%, with improved detection speed.