Research on the Defect Detection System of Solar Cell Sheets based on the YOLOv9 Model

A multi-station visual detection system is proposed to address the challenge of detecting various typical defects in solar cell sheets. To improve the detection accuracy of solar cell sheet defects, optimization of the YOLOv9 object detection model is explored. The introduction of the CBAM attention mechanism into the YOLOv9 model's backbone network enhances its ability to extract typical defects. The EIOU loss function replaces the original CIOU loss function, improving both the accuracy of the detection frame and the detection speed. Dynamic Snake Convolution (DSConv) is incorporated into the model to improve its recognition capability for small target defects. The effectiveness of the multi-station visual detection system and the superiority of the optimized model are validated through comprehensive stepwise and comparative experiments across different models.