浏览全部资源
扫码关注微信
六盘水师范学院 物理与电气工程学院,贵州 六盘水 553004
陈祖星(1994-),男,六盘水师范学院物理与电气工程学院讲师,研究方向为深度学习、目标检测等
冯俊杰(1983-),男,博士,六盘水师范学院物理与电气工程学院教授,研究方向为图像处理、识别研究等。
收稿:2025-04-02,
纸质出版:2026-04-15
移动端阅览
陈祖星,冯俊杰,李爽.YOLOv8-BGC:基于YOLOv8改进的光伏电池缺陷检测方法[J].软件导刊,2026,25(04):35-47.
CHEN Zuxing,FENG Junjie,LI Shuang.YOLOv8-BGC: A Defect Detection Method for Photovoltaic Cells Based on Improved YOLOv8[J].Software Guide,2026,25(04):35-47.
陈祖星,冯俊杰,李爽.YOLOv8-BGC:基于YOLOv8改进的光伏电池缺陷检测方法[J].软件导刊,2026,25(04):35-47. DOI: 10.11907/rjdk.241985.
CHEN Zuxing,FENG Junjie,LI Shuang.YOLOv8-BGC: A Defect Detection Method for Photovoltaic Cells Based on Improved YOLOv8[J].Software Guide,2026,25(04):35-47. DOI: 10.11907/rjdk.241985.
电致发光(EL)成像是检测光伏(PV)模块的一种有效方法。EL图像提供的高空间分辨率,可检测PV组件表面最细微的缺陷。然而,EL图像的分析通常是一个手动过程,成本高昂、耗时长,需要具备识别不同类型缺陷的专业知识。为此,提出一种改进YOLOv8的轻量化光伏电池缺陷检测算法YOLOv8-BGC。首先,结合CNN与Transformer的优势,提出一种能提取光伏电池缺陷图像全局特征信息与局部特征信息的BOT模块,以适应光伏电池缺陷特征;其次,在骨干网络末端和颈部网络中引入坐标注意力机制(GAM),降低信息碎片化并增强全局维度特征交互,以增强模型的运作效率、特征描述与解析能力;最后,在YOLOv8颈部网络中使用C2fGhost模块,减少特征通道融合过程中的浮点运算量,降低模型参数量,提升特征表达性能。实验表明,在不同光伏电池缺陷的数据集上,改进后的YOLOv8-BGC相较于原模型YOLOv8的模型参数、计算量分别减少6.7%、8.5%,mAP50提升3%,在轻量化的同时提升了模型准确率,实时性更强,相较于其他算法也具有一定优势,可满足工业部署要求。
Electroluminescence (EL) imaging is an effective method for detecting photovoltaic (PV) modules. The high spatial resolution provided by EL images can detect the slightest defects on the surface of PV modules. However, the analysis of EL images is usually a manual process that is costly, time-consuming, and requires specialized knowledge of different types of defects. Therefore, a lightweight photovoltaic cell defect detection algorithm YOLOv8-BGC is proposed to improve YOLOv8. Firstly, combining the advantages of CNN and Transformer, a BOT module is proposed that can extract global and local feature information of photovoltaic cell defect images to adapt to the defect features of photovoltaic cells; Secondly, coordinate attention mechanism (GAM) is introduced at the end of the backbone network and the neck network to reduce information fragmentation and enhance global dimensional feature interaction, thereby improving the operational efficiency, feature description, and parsing ability of the model; Finally, the C2fGhost module is used in the YOLOv8 neck network to reduce floating-point operations during feature channel fusion, decrease model parameter count, and improve feature expression performance. Experiments have shown that on datasets with different defects in photovoltaic cells, the improved YOLOv8-BGC reduces model parameters and computational complexity by 6.7% and 8.5% respectively compared to the original YOLOv8 model, and increases mAP50 by 3%. It improves model accuracy and real-time performance while being lightweight. Compared with other algorithms, it also has certain advantages and can meet industrial deployment requirements.
EL-RASHIDY M A . An efficient and portable solar cell defect detection system [J]. Neural Computing and Application , 2022 , 34 ( 21 ): 18497 - 18509 . doi: 10.1007/s00521-022-07464-2 http://dx.doi.org/10.1007/s00521-022-07464-2
SHAHSAVARI A , YAZDI F T , YAZDI H T . Potential of solar energy in Iran for carbon dioxide mitigation [J]. International Journal of Environmental Science and Technology , 2019 , 16 ( 1 ): 507 - 524 . doi : 10.1007/s13762-018-1779-7 http://dx.doi.org/10.1007/s13762-018-1779-7
JIAO L , ZHAO J . A survey on the new generation of deep learning in image processing [J]. IEEE Access , 2019 , 7 : 172231 - 172263 . doi: 10.1109/ACCESS.2019.2956508 http://dx.doi.org/10.1109/ACCESS.2019.2956508
XIE L S , ZHU W Z , XIE K K , et al . Photovoltaic cell EL defect image detection model based on improved YOLOv5s [J]. Foreign Electronic Measurement Technology , 2023 , 42 ( 6 ): 93 - 102 . doi: 10.19652/j.cnki.femt.2304821 http://dx.doi.org/10.19652/j.cnki.femt.2304821
谢林森 , 朱文忠 , 谢康康 , 等 . 基于改进YOLOv5s的光伏电池EL缺陷图像检测模型 [J]. 国外电子测量技术 , 2023 , 42 ( 6 ): 93 - 102 . doi: 10.19652/j.cnki.femt.2304821 http://dx.doi.org/10.19652/j.cnki.femt.2304821
ZHOU Y , YAN Y Z , CHEN H Y , et al . Photovoltaic cell defect detection based on improved YOLOv8 [J]. Progress in Lasers and Optoelectronics , 2024 , 61 ( 8 ): 245 - 255 . doi: 10.3788/LOP231622 http://dx.doi.org/10.3788/LOP231622
周颖 , 颜毓泽 , 陈海永 , 等 . 基于改进YOLOv8的光伏电池缺陷检测 [J]. 激光与光电子学进展 , 2024 , 61 ( 8 ): 245 - 255 . doi: 10.3788/LOP231622 http://dx.doi.org/10.3788/LOP231622
WANG F B , LI W H . Photovoltaic cell EL image defect detection based on improved lightweight U-Net model [J]. Electronic Measurement Technology , 2024 , 47 ( 5 ): 102 - 111 .
汪方斌 , 李文豪 . 基于改进轻量化U-Net模型的光伏电池EL图像缺陷检测 [J]. 电子测量技术 , 2024 , 47 ( 5 ): 102 - 111 .
BUERHOP C , WIRSCHING S , BEMM A , et al . Evolution of cell cracks in PV modules under field and laboratory conditions [J]. Progress in Photovoltaics: Research and Applications , 2018 , 26 : 261 - 272 . doi: 10.1002/pip.2975 http://dx.doi.org/10.1002/pip.2975
BREITENSTEIN O , BAUER J , BOTHE K , et al . Luminescence imaging versus lock-in thermography on solar cells and wafers [C]// Proceedings of the 26th European Photovoltaic Solar Energy Conference and Exhibition , 2011 : 1031 - 1038 . doi: 10.4229/26THEUPVSEC2011-2CO.13.5 http://dx.doi.org/10.4229/26THEUPVSEC2011-2CO.13.5
PALLATHADKA H , RAMIREZ-ASIS E H , LOLI-POMA T P , et al . Applications of artificial intelligence in business management [J]. E-commerce and Finance , 2021 , 80 ( 3 ): 2610 - 2613 .
TOMÁNEK P , ŠKARVADA P , MACKŮ R , et al . Detection and localization of defects in monocrystalline silicon solar cell [EB/OL]. https://onlinelibrary.wiley.com/doi/10.1155/2010/805325 https://onlinelibrary.wiley.com/doi/10.1155/2010/805325 . doi: 10.1155/2010/805325 http://dx.doi.org/10.1155/2010/805325
YI X T , SHAN Y F . Photovoltaic cell internal defect detection based on improved Faster R-CNN [J]. Journal of Electronic Measurement and Instruments , 2021 , 35 ( 1 ): 40 - 47 . doi: 10.13382/j.jemi.B2003300 http://dx.doi.org/10.13382/j.jemi.B2003300
伊欣同 , 单亚峰 . 基于改进Faster R-CNN的光伏电池内部缺陷检测 [J]. 电子测量与仪器学报 , 2021 , 35 ( 1 ): 40 - 47 . doi: 10.13382/j.jemi.B2003300 http://dx.doi.org/10.13382/j.jemi.B2003300
TAO Z Y , YI T J , LIN S , et al . Surface defect recognition of solar cells based on lightweight M-CNN [J]. Journal of Solar Energy , 2024 , 45 ( 6 ): 341 - 348 .
陶志勇 , 易廷军 , 林森 , 等 . 轻量化M-CNN的太阳电池表面缺陷识别 [J]. 太阳能学报 , 2024 , 45 ( 6 ): 341 - 348 .
ZHANG M Q , XING F D , LIU D . External defect detection of substation equipment based on improved Faster R-CNN [J]. Journal of Intelligent Systems , 2024 , 19 ( 2 ): 290 - 298 .
张铭泉 , 邢福德 , 刘冬 . 基于改进Faster R-CNN的变电站设备外部缺陷检测 [J]. 智能系统学报 , 2024 , 19 ( 2 ): 290 - 298 .
DU G Z , LU M X , JI Z X , et al . Research on apple defect detection method based on improved CNN [J]. Food and Machinery , 2023 , 39 ( 6 ): 155 - 160 .
杜国真 , 卢明星 , 季泽旭 , 等 . 基于改进CNN的苹果缺陷检测方法研究 [J]. 食品与机械 , 2023 , 39 ( 6 ): 155 - 160 .
SU B , CHEN H , CHEN P , et al . Deep learning-based solar cell manufacturing defect detection with complementary attention network [J]. IEEE Transactions on Industrial Informatics , 2020 , 17 ( 6 ): 4084 - 4095 . doi: 10.1109/tii.2020.3008021 http://dx.doi.org/10.1109/tii.2020.3008021
SU B , CHEN H , ZHOU Z . BAF-detector: an efficient CNN based detector for photovoltaic cell defect detection [J]. IEEE Transactions on Industrial Electronics , 2021 , 69 ( 3 ): 3161 - 3171 . doi: 10.1109/tie.2021.3070507 http://dx.doi.org/10.1109/tie.2021.3070507
HE K , ZHANG X , REN S , et al . Deep residual learning for image recognition [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2016 : 770 - 778 . doi: 10.1109/cvpr.2016.90 http://dx.doi.org/10.1109/cvpr.2016.90
GIRSHICK R , DONAHUE J , DARRELL T , et al . Rich feature hierarchies for accurate object detection and semantic segmentation [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2014 : 580 - 587 . doi: 10.1109/cvpr.2014.81 http://dx.doi.org/10.1109/cvpr.2014.81
GIRSHICK R . Fast R-CNN [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2015 : 580 - 587 . doi: 10.1109/iccv.2015.169 http://dx.doi.org/10.1109/iccv.2015.169
REN S Q , HE K M , GIRSHICK R , et al . Faster R-CNN: towards real-time object detection with region proposal networks [C]// Proceedings of the IEEE Transactions on Pattern Analysis and Machine Intelligence , 2016 : 1137 - 1149 . doi: 10.1109/tpami.2016.2577031 http://dx.doi.org/10.1109/tpami.2016.2577031
HAN J R . Research on classification and detection of EL defects in solar cells under class imbalance [D]. Tianjing : Hebei University of Technology , 2020 .
韩江锐 . 类别不均衡下的太阳能电池EL缺陷分类与检测问题研究 [D]. 天津 : 河北工业大学 , 2020 .
LIU B , HUANG X , YANG Q . Research on detection technology of photovoltaic cells based on GoogLeNet and EL [J]. Electronic Product Reliability and Environmental Testing , 2019 , 1 : 150 - 155 .
SIMONYAN K , ZISSERMAN A . Very deep convolutional networks for large-scale image recognition[DB/OL] . https://arxiv.org/abs/1409.1556 https://arxiv.org/abs/1409.1556 .
TAO Y F , JIANG L , DA M . Steel surface defect detection algorithm based on RCD-YOLO [J/OL]. Control Engineering , 2025-11-29 . https://doi.org/10.14107/j.cnki.kzgc.20240426 https://doi.org/10.14107/j.cnki.kzgc.20240426 .
陶友凤 , 姜麟 , 大妹 . 基于RCD-YOLO的钢材表面缺陷检测算法 [J/OL]. 控制工程 , 2025-11-29 . https://doi.org/10.14107/j.cnki.kzgc.20240426 https://doi.org/10.14107/j.cnki.kzgc.20240426 .
LIAO J , LIU K X , YANG Y Q , et al . Research on rice disease identification model in natural environment based on RDN-YOLO [J]. Transactions of the Chinese Society of Agricultural Machinery , 2024 , 55 ( 8 ): 233 - 242 .
廖娟 , 刘凯旋 , 杨玉青 , 等 . 基于RDN-YOLO的自然环境下水稻病害识别模型研究 [J]. 农业机械学报 , 2024 , 55 ( 8 ): 233 - 242 .
LIU X S , DU Z W , NIE R , et al . Effect of medical X-ray image input resolution on rotator cuff fracture recognition in YOLO network [J]. Journal of the Army Medical University , 2023 , 45 ( 22 ): 2327 - 2333 .
刘学思 , 杜振伟 , 聂瑞 , 等 . 医用X线图像输入分辨率对转子间骨折识别YOLO网络效果的影响 [J]. 陆军军医大学学报 , 2023 , 45 ( 22 ): 2327 - 2333 .
FANG C , WANG S , LIU G H , et al . Spatio-temporal distribution characteristics of arctic ice vortices based on SAR satellite observations [J]. Journal of Space Science , 2023 , 43 ( 6 ): 1125 - 1134 . doi: 10.11728/cjss2023.06.2023-0088 http://dx.doi.org/10.11728/cjss2023.06.2023-0088
房超 , 汪胜 , 刘桂红 , 等 . 基于SAR卫星观测的北极冰涡时空分布特征 [J]. 空间科学学报 , 2023 , 43 ( 6 ): 1125 - 1134 . doi: 10.11728/cjss2023.06.2023-0088 http://dx.doi.org/10.11728/cjss2023.06.2023-0088
YAO Y , WANG G , FAN J . WT-YOLOX: an efficient detection algorithm for wind turbine blade damage based on YOLOX [J]. Energies , 2023 , 16 : 3776 . doi: 10.3390/en16093776 http://dx.doi.org/10.3390/en16093776
LIU L , LI P , WANG D , et al . A wind turbine damage detection algorithm designed based on YOLOv8 [J]. Applied Soft Computing , 2024 , 154 : 111364 . doi: 10.1016/j.asoc.2024.111364 http://dx.doi.org/10.1016/j.asoc.2024.111364
YU H , WANG J , HAN Y , et al . Research on an intelligent identification method for wind turbine blade damage based on CBAM-BiFPN-YOLOV8 [J]. Processes , 2024 , 12 ( 1 ): 205 . doi: 10.3390/pr12010205 http://dx.doi.org/10.3390/pr12010205
LIU Y , ZHENG Y , SHAO Z , et al . Defect detection of the surface of wind turbine blades combining attention mechanism [J]. Advanced Engineering Informatics , 2024 , 59 : 102292 . doi: 10.1016/j.aei.2023.102292 http://dx.doi.org/10.1016/j.aei.2023.102292
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
鄂公网安备42010602004949号