基于深度学习的太阳能电池板表面缺陷检测及分类  

Detection and Classification of Surface Defects on Solar Cell Panels Based on Deep Learning

作　　者：涂俊博 曾佳林 唐越新 吴晨曦 刘晓宇[1] Tu Junbo;Zeng Jialin;Tang Yuexin;Wu Chenxi;Liu Xiaoyu(School of Mechanical Engineering,Sichuan University,Chengdu 610065,Sichuan,China)

机构地区：[1]四川大学机械工程学院,四川成都610065

出　　处：《激光与光电子学进展》2025年第2期446-455,共10页Laser & Optoelectronics Progress

基　　金：2024年国家级大学生创新创业训练计划(202410610101)。

摘　　要：针对目前太阳能电池板缺陷检测中对小目标缺陷检测精度不高、分类不准的问题,提出一种适用于小目标检测的改进轻量型YOLOv5s太阳能电池板缺陷检测模型。首先用SiLU激活函数替换原激活函数,优化模型收敛速度,增强其泛化性能;其次使用C3TR模块和卷积块注意力模块重新优化主干特征采样结构,提高模型对不同类型缺陷尤其是小目标缺陷的识别能力;接着将内容感知特征重组引入到特征提取网络,在不增加模型权重的同时提高检测精度和检测速率;最后加入动态非单调损失函数WIoUv3来动态匹配预测框和真实框,增强小目标数据集和噪声的鲁棒性。实验结果显示,改进模型的平均精度均值(mAP@0.5)为95.9%,对大面积裂缝、星形缺陷的分类精度达到98.0%,检测速度达到75.133 frame/s,模型轻量化且检测快捷,满足工业生产的需要。To solve the problems of the low-accuracy detection or inaccurate classification of small target defects in solar cell panel defect detection,an improved lightweight YOLOv5s solar cell panel defect detection model suitable for small target detection is proposed in this study.First,an SiLU activation function is used to replace the original activation function to optimize the convergence speed and enhance the generalization ability of the model.Second,the C3TR and convolution block attention modules are used to re-optimize the backbone feature sampling structure to improve the recognition ability for different defect types,especially small target defects.Third,the content-aware re-assembly of features is realized in the feature extraction network to improve the detection accuracy and detection speed without increasing the model weight.Finally,a dynamic nonmonotonic loss function WIoUv3 is added to the dynamic matching prediction box and real frame to enhance the robustness of small target datasets and noise.Experimental results show that the mean average precision(mAP@0.5)of the proposed model is 95.9%and that its classification accuracies for large-area cracks and star-shaped scratches reach 98.0%and detection speed reaches 75.133 frame/s,demonstrating its lightweight nature and rapidness that meet the requirements of industrial production.

关 键 词：深度学习 太阳能电池 内容感知特征重组 注意力机制 C3TR 

分 类 号：TM914.4[电气工程—电力电子与电力传动] TP391.4[自动化与计算机技术—计算机应用技术]