针对太阳电池表面缺陷问题,在深度学习模型YOLOv5的基础上进行优化与改进。首先,为充分利用深层、浅层和原始的特征信息,加强特征融合,设计具有跨连接结构的特征金字塔网络（ScFPN）。其次,为加强多重感受野融合,基于SPPF构建SPPFCSPC模块,通过最大池化层获得不同感受野,提升算法对于不同尺度太阳电池缺陷检测的鲁棒性。最后,采用ASD-IoU作为边界框损失函数,提升边框回归的速度与精度。实验结果表明,改进后的YOLOv5模型mAP@（0.50~0.95）达到83.1%,相比于YOLOv5模型,平均精度提高3.3个百分点,表明该文模型更加适合于太阳电池表面缺陷检测。
Abstract
To solve the surface defect problem of solar cells, the deep learning model YOLOv5 is optimized and improved. Firstly, in order to make full use of deep, shallow and original feature information and strengthen feature fusion, a feature pyramid network （ScFPN） with cross-connection structure is designed. Secondly, in order to strengthen the fusion of multiple receptive fields, the SPPFCSPC module is constructed based on SPPF, and different receptive fields are obtained through the maximum pooling layer, which improves the robustness of the algorithm for the defect detection of solar cells of different scales. Finally, ASD-IoU is used as the bounding loss function to improve the speed and precision of the bounding regression. The experimental results show that the improved YOLOv5 model mAP@（0.50-0.95） reaches 83.1%, and the average accuracy is increased by 3.3 percentage points compared with the YOLOv5 model, indicating that this model is more suitable for surface defect detection of solar cells.
关键词
深度学习 /
太阳电池 /
缺陷 /
卷积神经网络 /
目标检测 /
图像处理
Key words
deep learning /
solar cell /
defect /
convolutional neural network /
object detection /
image processing
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] BROOKS W S M, LAMB D A, IRVINE S J C. IR reflectance imaging for crystalline Si solar cell crack detection[J]. IEEE journal of photovoltaics, 2015, 5(5): 1271-1275.
[2] 时亚涛, 戴芳, 杨畅民. 太阳能光伏电池缺陷检测[J]. 电子测量与仪器学报, 2020, 34(4): 157-164.
SHI Y T, DAI F, YANG C M.Defect detection of solar photovoltaic cell[J]. Journal of electronic measurement and instrumentation, 2020, 34(4): 157-164.
[3] 汪方斌, 张彦福, 王峰, 等. 光伏电池电致发光偏振图像融合与缺陷检测[J]. 电子测量技术, 2022, 45(19): 143-149.
WANG F B, ZHANG Y F, WANG F, et al.Photovoltaic cell electroluminescence polarization image fusion and defect detection[J]. Electronic measurement technology, 2022, 45(19): 143-149.
[4] 王宇, 孙智权, 赵不贿. 基于机器视觉的太阳能电池硅片隐裂检测[J]. 组合机床与自动化加工技术, 2019(12): 95-97, 102.
WANG Y, SUN Z Q, ZHAO B H.Silicon wafer crack detection of solar cells based on machine vision[J]. Modular machine tool & automatic manufacturing technique, 2019(12): 95-97, 102.
[5] 钱晓亮, 张鹤庆, 张焕龙, 等. 基于视觉显著性的太阳能电池片表面缺陷检测[J]. 仪器仪表学报, 2017, 38(7): 1570-1578.
QIAN X L, ZHANG H Q, ZHANG H L, et al.Solar cell surface defect detection based on visual saliency[J]. Chinese journal of scientific instrument, 2017, 38(7): 1570-1578.
[6] 刘磊, 王冲, 赵树旺, 等. 基于机器视觉的太阳能电池片缺陷检测技术的研究[J]. 电子测量与仪器学报, 2018, 32(10): 47-52.
LIU L, WANG C, ZHAO S W, et al.Research on solar cells defect detection technology based on machine vision[J]. Journal of electronic measurement and instrumentation, 2018, 32(10): 47-52.
[7] 蒋兴群, 刘波, 宋力, 等. 基于改进YOLO-v3的风力机叶片表面损伤检测识别[J]. 太阳能学报, 2023, 44(3): 212-217.
JIANG X Q, LIU B, SONG L, et al.Surface damage detection and recognition of wind turbine blade based on improved YOLO-v3[J]. Acta energiae solaris sinica, 2023, 44(3): 212-217.
[8] 周颖, 毛立, 张燕, 等. 改进CNN的太阳电池缺陷识别方法研究[J]. 太阳能学报, 2020, 41(12): 69-76.
ZHOU Y, MAO L, ZHANG Y, et al.Research on defect detection and classification for solar cells based on improved convolutional neural network[J]. Acta energiae solaris sinica, 2020, 41(12): 69-76.
[9] 王道累,李超,李明山, 等. 基于深度卷积神经网络的光伏组件热斑检测[J]. 太阳能学报, 2022, 43(1): 412-417.
WANG D L, LI C, LI M S, et al.Solar photovoltaic modules hot spot detection based on deep convolutional neural networks[J]. Acta energiae solaris sinica, 2022, 43(1): 412-417.
[10] WEI S Q, LI X X, DING S H, et al.Hotspots Infrared detection of photovoltaic modules based on Hough line transformation and Faster-RCNN approach[C]//2019 6th International Conference on Control, Decision and Information Technologies (CoDIT). Paris, France, 2019: 1266-1271.
[11] 张文彪, 马永华, 白晓静, 等. 基于改进Faster R-CNN的太阳能电池板缺陷识别[J]. 电网技术, 2022, 46(7): 2593-2600.
ZHANG W B, MA Y H, BAI X J, et al.Defect identification of solar panels using improved Faster R-CNN[J]. Power system technology, 2022, 46(7): 2593-2600.
[12] 高天洋. 基于卷积神经网络的太阳能电池板故障识别[D]. 北京: 华北电力大学, 2021.
GAO T Y.Fault identification of solar panels based on convolution neural networks[D]. Beijing: North China Electric Power University, 2021.
[13] 王文胜, 李继旺, 吴波, 等. 基于YOLOv5交通标志识别的智能车设计[J]. 国外电子测量技术, 2021, 40(10): 158-164.
WANG W S, LI J W, WU B, et al.Smart car design based on traffic sign recognition via YOLOv5[J]. Foreign electronic measurement technology, 2021, 40(10): 158-164.
[14] 吕禾丰, 陆华才. 基于YOLOv5算法的交通标志识别技术研究[J]. 电子测量与仪器学报, 2021, 35(10): 137-144.
LYU H F, LU H C.Research on traffic sign recognition technology based on YOLOv5 algorithm[J]. Journal of electronic measurement and instrumentation, 2021, 35(10): 137-144.
[15] 张宏群, 班勇苗, 郭玲玲, 等. 基于YOLOv5的遥感图像舰船的检测方法[J]. 电子测量技术, 2021, 44(8): 87-92.
ZHANG H Q, BAN Y M, GUO L L, et al.Detection method of remote sensing image ship based on YOLOv5[J]. Electronic measurement technology, 2021, 44(8): 87-92.
[16] 邱天衡, 王玲, 王鹏, 等. 基于改进YOLOv5的目标检测算法研究[J]. 计算机工程与应用, 2022, 58(13): 63-73.
QIU T H, WANG L, WANG P, et al.Research on object detection algorithm based on improved YOLOv5[J]. Computer engineering and applications, 2022, 58(13): 63-73.
基金
湖南省教育厅重点科研项目（22A0423）; 湖南省自科基金（2023JJ60267; 2022JJ50073）
PDF(2475 KB)
