1.武汉科技大学机械传动与制造工程湖北省重点实验室 武汉 430081; 2.武汉科技大学冶金装备及其控制教育部重点实验室 武汉 430081
TN911.73;TP183
国家自然科学基金面上项目(51874217)、国家重点专项（2018YFC1902400）资助
Liu Huaiguang
1.Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering，Wuhan University of Science and Technology， Wuhan 430081,China； 2.Key Laboratory of Metallurgical Equipment and Control Technology (Ministry of Education), Wuhan University of Science and Technology，Wuhan 430081, ChinaTang Bo
1.Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering，Wuhan University of Science and Technology， Wuhan 430081,China； 2.Key Laboratory of Metallurgical Equipment and Control Technology (Ministry of Education), Wuhan University of Science and Technology，Wuhan 430081, China1.Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering，Wuhan University of Science and Technology， Wuhan 430081,China; 2.Key Laboratory of Metallurgical Equipment and Control Technology (Ministry of Education), Wuhan University of Science and Technology，Wuhan 430081, China
太阳能电池片的内部缺陷是降低电流传导效率的主要原因，通过EL或PL成像后的图像缺陷强弱变化较大，直接进行阈值分割会造成漏检。本文提出了一种全注意力FSA-UNet网络，用于太阳能电池片混合缺陷分割。针对缺陷分层特点，设计出了特征增强模块，提升弱缺陷的分辨能力，同时改进骨干特征提取网络，加快了强缺陷的检出效率。本算法能精确分割出单晶硅片的多种缺陷，为了验证本文算法的有效性，将本文算法与U-net、DeepLabV3+进行的比较，最佳MIOU达到了77.9%，突出了本算法的优势。
The internal defects of solar cells are the main reason for reducing the current conduction efficiency. The intensity of image defects after imaging by Electrolumine-scence （EL) or Photoluminescence （PL) varies greatly, and direct threshold segmentation will cause missed detection. This paper proposes a full-attention FSA-UNet network for hybrid defect segmentation in solar cells. Aiming at the characteristics of defect stratification, a feature enhancement module is designed to improve the ability to distinguish weak defects, and at the same time improve the backbone feature extraction network to speed up the detection efficiency of strong defects. This algorithm can accurately segment a variety of defects in single crystal silicon wafers. In order to verify the effectiveness of the algorithm in this paper, comparing the algorithm in this paper with U-net and DeepLabV3+, the best MIOU reaches 77.9%, which highlights the advantages of this algorithm.
吴俊良,刘怀广,汤勃.基于全注意力FSA-UNet网络的单晶电池片混合缺陷检测[J].电子测量技术,2023,46(12):98-104
复制
