基于重参数化的光伏电池缺陷检测算法  

Photovoltaic cell defect detection algorithm based on reparameterization

作　　者：杨丽[1,2] 邓靖威 段海龙[1,2] 杨晨晨 李凤泉 Yang Li;Deng Jingwei;Duan Hailong;Yang Chenchen;Li Fengquan(School of Automation and Electrical Engineering,Tianjin University of Technology and Education,Tianjin 300222,China;Tianjin Key Laboratory of Information Sensing and Intelligent Control,Tianjin University of Technology and Education,Tianjin 300222,China;Tianjin Jinghong Intelligent Technology Co.,Ltd.,Tianjin 300222,China)

机构地区：[1]天津职业技术师范大学自动化与电气工程学院,天津300222 [2]天津职业技术师范大学天津市信息传感与智能控制重点实验室,天津300222 [3]天津经泓智能科技有限公司,天津300222

出　　处：《电子测量技术》2025年第5期184-192,共9页Electronic Measurement Technology

基　　金：天津市教委科研计划项目(2022ZD036);天津市“揭榜挂帅”科技计划项目(2023JB02)资助。

摘　　要：针对光伏电池电致发光图像缺陷的复杂背景干扰不均、形状多变和缺陷多尺度等问题,提出了一种基于重参数化的光伏电池缺陷检测算法OM-Detector。首先结合广义高效层聚合网络和在线重参数化,提出了OREPANCSPELAN4模块,引入重参数化有效地通过梯度下降优化算法进行训练,在提升精度的同时降低了模型参数量,使模型轻量化;其次,在颈部网络中引入了多尺度卷积注意力模块,抑制复杂背景的干扰,提高模型检测细小缺陷的准确率;最后,结合重参数化特征提取—融合模块和多尺度卷积注意力模块,构建光伏电池缺陷检测器。使用光伏电池异常检测数据集对算法性能进行验证,实验结果表明,与YOLOv8检测网络相比,平均精度均值提升了2.5%,参数量降低了29%,推理速度加快了5.7%,优于目前的主流目标检测算法,能快速、准确地对光伏电池表面缺陷进行检测。A defect detection algorithm OM-Detector based on reparameterization was proposed to solve the problems of uneven background interference,variable shape and multi-scale defects in electroluminescence image of photovoltaic cells.Firstly,OREPANCSPELAN4 module is proposed by combining generalized high-efficiency layer aggregation network and online reparameterization.The introduction of heavy parameterization can effectively train through gradient descent optimization algorithm,which can improve the accuracy and reduce the number of model parameters,making the model lightweight.Secondly,a multi-scale convolutional attention module is introduced into the neck network to suppress the interference of complex background and improve the accuracy of the model to detect fine defects.Finally,a defect detector is constructed by combining the heavy parametric feature extraction-fusion module and the multi-scale convolution attention module.The performance of the algorithm was verified by using the photovoltaic cell anomaly detection data set.The experimental results showed that compared with the YOLOv8 detection network,the mean average precision was increased by 2.5%,the number of parameters was reduced by 29%,and the reasoning speed was accelerated by 5.7%,which was superior to the current mainstream target detection algorithm and could detect the surface defects of photovoltaic cells quickly and accurately.

关 键 词：缺陷检测 重参数化 注意力机制 

分 类 号：TN41[电子电信—微电子学与固体电子学]