基于CBS-YOLOv8的光伏组件缺陷检测

郭建; 王蕊; 钟琪峰

doi:10.19912/j.0254-0096.tynxb.2025-0730

PDF(1852 KB)

太阳能学报 ›› 2026, Vol. 47 ›› Issue (9) : 280-287. DOI: 10.19912/j.0254-0096.tynxb.2025-0730

基于CBS-YOLOv8的光伏组件缺陷检测

郭建, 王蕊, 钟琪峰

作者信息 +

DEFECT DETECTION OF PHOTOVOLTAIC MODULES BASED ON CBS-YOLOV8

Guo Jian, Wang Rui, Zhong Qifeng

Author information +

文章历史 +

摘要

针对光伏组件缺陷检测中存在的检测精度低、小目标漏检率高及网络参数量偏大等问题,提出一种基于YOLOv8的轻量级改进模型CBS-YOLOv8（CBAM-BiFPN-SIoU-YOLOv8）。在特征提取阶段通过嵌入的CBAM注意力模块强化缺陷区域的特征表征,在多尺度特征融合中采用双向特征金字塔网络（BiFPN）,并改良SIoU损失函数提升边界框回归精度,进一步结合知识蒸馏技术构建教师-学生协同训练框架,实现模型压缩与性能迁移。实验结果表明：改进后模型在自建光伏组件EL图像数据集上的mAP_0.5达到87.50%,较原始YOLOv8提升7.20个百分点;经蒸馏压缩的CBS-YOLOv8模型参数量降低75.42%,检测精度仅下降0.45个百分点,在保持检测精度的同时满足轻量化需求。

Abstract

Aiming at the problems existing in the defect detection of photovoltaic modules, such as low detection accuracy, high missed detection rate of small targets and large number of network parameters, a lightweight improved model CBS-YOLOv8（CBAM-BiFPN-SIoU-YOLOv8） based on YOLOv8 is proposed. In the feature extraction stage, the feature representation of the defect area is strengthened through the embedded CBAM attention module. In multi-scale feature fusion, the bidirectional feature pyramid network （BiFPN） is adopted, and the SIoU loss function is improved to enhance the bounding box regression accuracy. Furthermore, knowledge distillation technology is integrated to construct a teacher-student collaborative training framework to achieve model compression and performance transfer. The experimental results show that the mAP_0.5 of the improved model on the self-built photovoltaic module EL image dataset reaches 87.50%, which is 7.20 percentage points higher than that of the original YOLOv8. The number of parameters of the CBS-YOLOv8 model after distillation and compression decreased by 75.42%, and the detection accuracy only dropped by 0.45percentage points, meeting the lightweight requirements while maintaining the detection accuracy.

导出引用

郭建, 王蕊, 钟琪峰. 基于CBS-YOLOv8的光伏组件缺陷检测[J]. 太阳能学报. 2026, 47(9): 280-287 https://doi.org/10.19912/j.0254-0096.tynxb.2025-0730

Guo Jian, Wang Rui, Zhong Qifeng. DEFECT DETECTION OF PHOTOVOLTAIC MODULES BASED ON CBS-YOLOV8[J]. Acta Energiae Solaris Sinica. 2026, 47(9): 280-287 https://doi.org/10.19912/j.0254-0096.tynxb.2025-0730

中图分类号： TP183 TP391.41

参考文献

[1] Zhu J H, Zhou D Q, Lu R S, et al.C2DEM-YOLO: improved YOLOv8 for defect detection of photovoltaic cell modules in electroluminescence image[J]. Nondestructive Testing and Evaluation, 2025, 40(1): 309-331.
[2] 霍爱清, 张书涵, 杨玉艳, 等. 密集交通场景中改进YOLOv3目标检测优化算法[J]. 计算机工程与科学, 2023, 45(5): 878-884.
Huo A Q, Zhang S H, Yang Y Y, et al.An improved YOLOv3 target detection optimization algorithm in dense traffic scenarios[J]. Computer Engineering & Science, 2023, 45(5): 878-884.
[3] 田浩, 周强, 贺晨龙. 基于多尺度特征融合的光伏组件缺陷检测[J]. 计算机工程与应用, 2024, 60(3): 340-347.
Tian H, Zhou Q, He C L.Defect detection of photovoltaic modules based on multi-scale feature fusion[J]. Computer Engineering and Applications, 2024, 60(3): 340-347.
[4] Tan L, Liu Z K, Huang X K, et al.A transformer-based UAV instance segmentation model TF-YOLOv7[J]. Signal, Image and Video Processing, 2024, 18(4): 3299-3308.
[5] 孙铁强, 于洪健, 宋超, 等. 轻量级重参数化的PCB缺陷检测算法[J]. 组合机床与自动化加工技术, 2025(4): 118-123, 128.
Sun T Q, Yu H J, Song C, et al.Lightweight re-parameterized PCB defect detection algorithm[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2025(4): 118-123, 128.
[6] 杜娟, 南晓林, 晋美娟, 等. 改进YOLOv8的带钢表面缺陷检测技术[J]. 组合机床与自动化加工技术, 2025(4): 167-172.
Du J, Nan X L, Jin M J, et al.Improved YOLOv8 strip surface defect detection technology[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2025(4): 167-172.
[7] 张冀, 王文彬, 余洋. 基于RFCARep-YOLOv8n的光伏电池缺陷检测算法[J]. 计算机工程与应用, 2025, 61(3): 131-143.
Zhang J, Wang W B, Yu Y.Defect detection of photovoltaic cells based on RFCARep-YOLOv8n[J]. Computer Engineering and Applications, 2025, 61(3): 131-143.
[8] 刘义艳, 郝婷楠, 贺晨, 等. 基于DBBR-YOLO的光伏电池表面缺陷检测[J]. 图学学报, 2024, 45(5): 913-921.
Liu Y Y, Hao T N, He C, et al.Photovoltaic cell surface defect detection based on DBBR-YOLO[J]. Journal of Graphics, 2024, 45(5): 913-921.
[9] Wang Y, Chen X Q, Li J Q, et al.Convolutional block attention module-multimodal feature-fusion action recognition: enabling miner unsafe action recognition[J]. Sensors, 2024, 24(14): 4557.
[10] 赵陆阳, 刘长良, 刘卫亮, 等. 基于CBAM-DSC-UNet模型的时空风速预测算法[J]. 太阳能学报, 2024, 45(10): 497-505.
Zhao L Y, Liu C L, Liu W L, et al.Spatio-temporal wind speed prediction algorithm based on CBAM-DSC-UNet model[J]. Acta Energiae Solaris Sinica, 2024, 45(10): 497-505.
[11] 朱永红, 吴松涛. 基于改进的YOLOv8n瓷砖缺陷检测与分类方法[J]. 陶瓷学报, 2024, 45(6): 1255-1264.
Zhu Y H, Wu S T.Defect detection and classification method of ceramic tiles based on improved YOLOv8n[J]. Journal of Ceramics, 2024, 45(6): 1255-1264.
[12] Lawal O M.Real-time cucurbit fruit detection in greenhouse using improved YOLO series algorithm[J]. Precision Agriculture, 2024, 25(1): 347-359.
[13] 廖丽瑛, 刘洪. 基于改进YOLOv8的绝缘子自爆缺陷检测[J]. 电子测量技术, 2024, 47(18): 138-144.
Liao L Y, Liu H.Self-explosion defect detection of insulator based on improved YOLOv8[J]. Electronic Measurement Technology, 2024, 47(18): 138-144.
[14] 杨丽, 杨晨晨, 杨耿煌, 等. 改进YOLOv8的光伏电池缺陷检测算法[J]. 电子测量技术, 2025, 48(1): 92-99.
Yang L, Yang C C, Yang G H, et al.Improved photovoltaic cell defect detection for YOLOv8[J]. Electronic Measurement Technology, 2025, 48(1): 92-99.
[15] 任喜伟, 余杰, 韩欣, 等. 基于改进YOLOv5s网络的光伏组件缺陷检测方法[J]. 太阳能学报, 2025, 46(3): 428-434.
Ren X W, Yu J, Han X, et al.Photovoltaic module defect detection method based on improved YOLOV5s network[J]. Acta Energiae Solaris Sinica, 2025, 46(3): 428-434.
[16] Li X Y, Wang F P, Wang W, et al.DM-YOLOX aerial object detection method with intensive attention mechanism[J]. The Journal of Supercomputing, 2024, 80(9): 12790-12812.
[17] 张润梅, 潘晨飞, 陈梓华, 等. 改进YOLOv8的焊缝表面缺陷检测算法[J]. 光电工程, 2025, 52(3): 240296.
Zhang R M, Pan C F, Chen Z H, et al.Improved weld surface defect detection algorithm from YOLOv8[J]. Opto-electronic Engineering, 2025, 52(3): 240296.
[18] 刘雄彪, 杨贤昭, 陈洋, 等. 基于CIoU改进边界框损失函数的目标检测方法[J]. 液晶与显示, 2023, 38(5): 656-665.
Liu X B, Yang X Z, Chen Y, et al.Object detection method based on CIoU improved bounding box loss function[J]. Chinese Journal of Liquid Crystals and Displays, 2023, 38(5): 656-665.
[19] 麻斯亮, 许勇. 最小点距离的边界框回归损失函数及其应用[J]. 小型微型计算机系统, 2024, 45(11): 2695-2701.
Ma S L, Xu Y.Bounding box regression loss function based on minimum point distance and its application[J]. Journal of Chinese Computer Systems, 2024, 45(11): 2695-2701.
[20] Xing Z Q, Chen X, Pang F Q.DD-YOLO: an object detection method combining knowledge distillation and differentiable architecture search[J]. IET Computer Vision, 2022, 16(5): 418-430.
[21] Gou J P, Yu B S, Maybank S J, et al.Knowledge distillation: a survey[J]. International Journal of Computer Vision, 2021, 129(6): 1789-1819.
[22] 张琳, 薄敬东, 龚瑞昆, 等. 基于改进YOLOv5s的红外船舶目标检测算法[J]. 电光与控制, 2024, 31(9): 38-44.
Zhang L, Bo J D, Gong R K, et al.An infrared ship target detection algorithm based on improved YOLOv5s[J]. Electronics Optics & Control, 2024, 31(9): 38-44.
[23] 罗志聪, 何陈涛, 陈登捷, 等. 基于轻量化YOLOv8s-GD的自然环境下百香果快速检测模型[J]. 农业机械学报, 2024, 55(8): 291-300.
Luo Z C, He C T, Chen D J, et al.Passion fruit rapid detection model based on lightweight YOLOv8s-GD[J]. Transactions of the Chinese Society for Agricultural Machinery, 2024, 55(8): 291-300.