Scholarlink

Solar photovoltaic (PV) cells are the primary elements of the PV power generation process, and their quality directly influences the overall efficiency and reliability of the power generation. Visual inspection of PV electroluminescence (EL) images in the factory is a classical method for defect detection, but it is a time-consuming and labor-intensive process. Therefore, an improved YOLOv8 model YOLOv8-DGN was proposed for EL images. In this paper, we introduced depthwise separable convolution (DWConv) and GhostConv into YOLOv8n to reduce the number of parameters and computational complexity. To improve the model’s detection performance on small-size defects, the Normalized Gaussian Wasserstein distance (NWD) was employed to replace the original loss function of YOLOv8. The experimental results showed that the proposed model YOLOv8-DGN was superior to the baseline model YOLOv8, with a mAP50 of 91.68% while parameters, FLOPs and weights decreased by 0.46M, 0.8G and 0.9MB, respectively. Compared to other SOTA models, YOLOv8-DGN also achieves superior detection results and is more suitable for some industrial hardware-constrained environments.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Electroluminescence Image-Based Automated Defect Detection for Solar Photovoltaic Cells

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Yufei Zhang,
  • Xu Zhang,
  • Dawei Tu

摘要

Solar photovoltaic (PV) cells are the primary elements of the PV power generation process, and their quality directly influences the overall efficiency and reliability of the power generation. Visual inspection of PV electroluminescence (EL) images in the factory is a classical method for defect detection, but it is a time-consuming and labor-intensive process. Therefore, an improved YOLOv8 model YOLOv8-DGN was proposed for EL images. In this paper, we introduced depthwise separable convolution (DWConv) and GhostConv into YOLOv8n to reduce the number of parameters and computational complexity. To improve the model’s detection performance on small-size defects, the Normalized Gaussian Wasserstein distance (NWD) was employed to replace the original loss function of YOLOv8. The experimental results showed that the proposed model YOLOv8-DGN was superior to the baseline model YOLOv8, with a mAP50 of 91.68% while parameters, FLOPs and weights decreased by 0.46M, 0.8G and 0.9MB, respectively. Compared to other SOTA models, YOLOv8-DGN also achieves superior detection results and is more suitable for some industrial hardware-constrained environments.