Scholarlink

<p>With the rapid advancement of the photovoltaic industry, the surface quality of solar cell wafers critically affects power generation efficiency and operational lifespan. Traditional inspection methods suffer from low efficiency, inconsistent criteria, and high false detection rates. Deep learning-based surface defect detection offers marked advantages. We systematically examine state-of-the-art techniques, such as YOLO and Mask R-CNN, in terms of detection accuracy, speed, and model lightweighting. By comparing conventional and deep learning approaches, it summarizes current challenges and highlights future directions, including multimodal fusion and edge computing adaptation, to provide theoretical guidance for efficient, accurate, and real-time defect detection.</p>

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

Solar Cell Defect Detection Based on Deep Learning Algorithms: A Review

  • 期刊论文

  • 发表日期：

    2026年7月11日

查看全文
  • Laixiang Xu,
  • Mengyuan Zhu,
  • Xiaomin Yang,
  • Weihao Wang,
  • Shengyuan Yang

摘要

With the rapid advancement of the photovoltaic industry, the surface quality of solar cell wafers critically affects power generation efficiency and operational lifespan. Traditional inspection methods suffer from low efficiency, inconsistent criteria, and high false detection rates. Deep learning-based surface defect detection offers marked advantages. We systematically examine state-of-the-art techniques, such as YOLO and Mask R-CNN, in terms of detection accuracy, speed, and model lightweighting. By comparing conventional and deep learning approaches, it summarizes current challenges and highlights future directions, including multimodal fusion and edge computing adaptation, to provide theoretical guidance for efficient, accurate, and real-time defect detection.