针对太阳电池电致发光图像中缺陷种类复杂、人工检测效率低的问题,提出一种基于Mamba与卷积神经网络的缺陷检测方法。该方法通过融合卷积神经网络的局部特征提取能力与Mamba结构的全局信息捕获优势,克服了单一架构在复杂场景中的局限性。Mamba结构引入轻量级注意力机制,动态调节不同层次特征的权重,增强全局信息感知能力。结合卷积神经网络后,该模型既能提取局部细节特征,又能高效融合全局上下文信息,从而显著提升了缺陷检测的精度与性能。经过大量实验证明,所提方法具有模型参数量小、检测精度高和鲁棒性强等优点,显著提升了太阳电池的缺陷检测效果。
Abstract
In order to address the problems of complex defect types and low efficiency of manual detection in solar cell electroluminescence images, a defect detection method based on Mamba and convolutional neural networks is proposed. The method overcomes the limitations of a single architecture in complex scenarios by fusing the local feature extraction capability of convolutional neural networks with the global information capture advantage of Mamba structures. The Mamba structure introduces a lightweight attention mechanism that dynamically adjusts the weights of features at different levels to enhance global information perception capability. Combined with convolutional neural networks, the model can both extract local detailed features and efficiently fuse global contextual information, thus significantly improving the accuracy and performance of defect detection. After a large amount of experiments, it is proved that the proposed method has the advantages of a low number of model’s parameters, high detection accuracy and strong robustness, which significantly improves the defect detection performance of solar cells.
关键词
光伏电池 /
电致发光 /
深度学习 /
状态空间算法 /
缺陷检测 /
轻量化
Key words
solar cells /
electroluminescence /
deep learning /
state space methods /
defect detection /
lightweighting
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] LI G Q, AKRAM M W, JIN Y, et al.Thermo-mechanical behavior assessment of smart wire connected and busbarPV modules during production, transportation, and subsequent field loading stages[J]. Energy, 2019, 168: 931-945.
[2] PAGGI M, BERARDONE I, INFUSO A, et al.Fatigue degradation and electric recovery in Silicon solar cells embedded in photovoltaic modules[J]. Scientific reports, 2014, 4: 4506.
[3] TOMÁNEK P, ŠKARVADA P, MACKŮ R, et al. Detection and localization of defects in monocrystalline silicon solar cell[J]. Advances in optical technologies, 2010, 2010: 805325.
[4] OSAWA S, NAKANO T, MATSUMOTO S, et al.Fault diagnosis of photovoltaic modules using AC impedance spectroscopy[C]//2016 IEEE International Conference on Renewable Energy Research and Applications(ICRERA). Birmingham, UK, 2017: 210-215.
[5] HE Y Z, DU B L, HUANG S D.Noncontact electromagnetic induction excited infrared thermography for photovoltaic cells and modules inspection[J]. IEEE transactions on industrial informatics, 2018, 14(12): 5585-5593.
[6] DEITSCH S, CHRISTLEIN V, BERGER S, et al.Automatic classification of defective photovoltaic module cells in electroluminescence images[J]. Solar energy, 2019, 185: 455-468.
[7] EBNER R, ZAMINI S, UJVARI G.Defect analysis in different photovoltaic modules using electroluminescence (EL) and infrared (IR)-thermography[C]//25th European Photovoltaic Solar Energy Conference and Exhibition. Valencia, Spain, 2010: 333-336.
[8] KÖNTGES M, SIEBERT M, HINKEN D, et al. Quantitative analysis of PV-modules by electroluminescence images for quality control[C]//Proceedings of the 24th European Photovoltaic Solar Energy Conference. Hamburg, Germany, 2009: 21-24.
[9] 彭自然, 张颖清, 肖伸平, 等. 基于YOLOv5的太阳电池表面缺陷检测[J]. 太阳能学报, 2024, 45(6): 368-375.
PENG Z R, ZHANG Y Q, XIAO S P, et al.Surface defect detection of solar cells based on YOLOv5[J]. Acta energiae solaris sinica, 2024, 45(6): 368-375.
[10] 刘涛, 孙会, 卞佰成, 等. 多尺度特征融合的太阳电池表面缺陷检测[J]. 太阳能学报, 2025, 46(2): 342-349.
LIU T, SUN H, BIAN B C, et al.Surface defect detection of solar cells based on multi-scale feature fusion[J]. Acta energiae solaris sinica, 2025, 46(2): 342-349.
[11] AKRAM M W, LI G Q, JIN Y, et al.CNN based automatic detection of photovoltaic cell defects in electroluminescence images[J]. Energy, 2019, 189: 116319.
[12] TANG W Q, YANG Q, XIONG K X, et al.Deep learning based automatic defect identification of photovoltaic module using electroluminescence images[J]. Solar energy, 2020, 201: 453-460.
[13] XIE X Y, LAI G Z, YOU M Y, et al.Effective transfer learning of defect detection for photovoltaic module cells in electroluminescence images[J]. Solar energy, 2023, 250: 312-323.
[14] GU A, DAO T. Mamba: linear-time sequence modeling with selective state spaces[EB/OL].2023: arXiv: 2312.00752. https://arxiv.org/abs/2312.00752.
[15] FUKUSHIMA K.Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position[J]. Biological cybernetics, 1980, 36(4): 193-202.
[16] SU B Y, ZHOU Z, CHEN H Y.PVEL-AD: a large-scale open-world dataset for photovoltaic cell anomaly detection[J]. IEEE transactions on industrial informatics, 2023, 19(1): 404-413.
[17] KINGMA D P, BA J. Adam: a method for stochastic optimization[EB/OL].2014: arXiv: 1412.6980. https://arxiv.org/abs/1412.6980.
[18] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16×16 words: transformers for image recognition at scale[EB/OL].2020: arXiv: 2010.11929. https://arxiv.org/abs/2010.11929.
[19] LIU Z, LIN Y T, CAO Y, et al.Swin transformer: hierarchical vision transformer using shifted windows[C]//2021 IEEE/CVF International Conference on Computer Vision (ICCV). Montreal, QC, Canada, 2022: 9992-10002.
[20] LIU Y, TIAN Y, ZHAO Y et al. Vmamba: visual state space model[C]//Advances in Neural Information Processing Systems 37. Vancouver, Canada, 2024: 103031-103063.
基金
国家自然科学基金（62203224）; 上海市地方能力建设项目（22010501300）
PDF(1771 KB)
