Abstract
In the field of new energy photovoltaics, efficient defect detection of Tunnel Oxide Passivated Contact solar cells is crucial for ensuring power generation efficiency and stability. Addressing the limitations of traditional manual vision and image processing techniques in terms of efficiency and accuracy under high-throughput and complex conditions, this study proposes an improved lightweight convolutional neural network model based on the YOLOv5 algorithm. The model integrates three enhancement approaches: Channel Attention plus Generative Adversarial Networks, Squeeze-and-Excitation, and Convolutional Block Attention Module to bolster the model’s capability to recognize key features. By automating feature extraction and incorporating attention mechanisms, the model significantly improves the efficiency and accuracy of defect detection in photovoltaic wafers. Experimental results demonstrate that the enhanced model excels in detecting small targets and complex backgrounds on the PVEL-AD dataset while maintaining low computational costs, indicating promising application prospects and practical value. This research not only enhances detection performance but also provides effective technical support for quality control and maintenance management in the photovoltaic industry.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Tyagi, V.V., Rahim, N.A.A., Rahim, N.A., et al.: Progress in solar PV technology: research and achievement. Renew. Sustain. Energy Rev. 20, 443–461 (2013)
Stanga, P.E., Tsamis, E., Papayannis, A., et al.: Swept-source optical coherence tomography Angio™ (Topcon Corp, Japan): technology review. OCT Angiography Retinal Macular Dis. 56, 13–17 (2016)
Ren, Z., Fang, F., Yan, N., et al.: State of the art in defect detection based on machine vision. Int. J. Precis. Eng. Manuf.-Green Technol. 9(2), 661–691 (2022)
Wu, W., Liu, H., Li, L., et al.: Application of local fully Convolutional Neural Network combined with YOLO v5 algorithm in small target detection of remote sensing image. PLoS ONE 16(10), e0259283 (2021)
Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_1
Creswell, A., White, T., Dumoulin, V., et al.: Generative adversarial networks: an overview. IEEE Sig. Process. Mag. 35(1), 53–65 (2018)
Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)
He, K., Gkioxari, G., Dollár, P., et al.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)
Tasyurek, M.: SDPH: a new technique for spatial detection of path holes from huge volume high-resolution raster images in near real-time. J. Real-Time Image Process. 21(3) (2024). https://doi.org/10.1007/s11554-024-01451-7
Jocher, G., Chaurasia, A., Stoken, A., et al.: ultralytics/yolov5: v6. 2-YOLOv5 classification models, apple M1, reproducibility, ClearML and Deci. AI integrations. Zenodo (2022)
Fang, Y., Guo, X., Chen, K., et al.: Accurate and automated detection of surface knots on sawn timbers using YOLO-V5 model. BioResources 16(3), 5390 (2021)
Ting, L., Baijun, Z., Yongsheng, Z., et al.: Ship detection algorithm based on improved YOLO V5. In: 2021 6th International Conference on Automation, Control and Robotics Engineering (CACRE), pp. 483–487. IEEE (2021)
Karthi, M., Muthulakshmi, V., Priscilla, R., et al.: Evolution of YOLO-V5 algorithm for object detection: automated detection of library books and performace validation of dataset. In: 2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), pp. 1–6. IEEE (2021)
Huang, B., Huang, T., Xu, J., Min, J., Hu, C., Zhang, Z.: RCNU-Net: reparameterized convolutional network with convolutional block attention module for improved polyp image segmentation. Biomed. Sig. Process. Control 93, 106138 (2024)
Li, R., Wu, Y.: Improved YOLO v5 wheat ear detection algorithm based on attention mechanism. Electronics 11(11), 1673 (2022)
Zhang, J., Chen, X., Wei, H., Zhang, K.: A lightweight network for photovoltaic cell defect detection in electroluminescence images based on neural architecture search and knowledge distillation. Appl. Energy 355, 122184 (2023)
Liu, Z., Lin, Y., Cao, Y., et al.: Swin Transformer: hierarchical vision transformer using shifted windows (2021). https://doi.org/10.48550/arXiv.2103.14030
Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection (2017). https://doi.org/10.1109/CVPR.2018.00644
PVEL-AD Dataset. http://nave.vr3i.com/downfile/view.action
Acknowledgement
The authors would like to express their sincere gratitude to the funding bodies that have supported this research. This work was partially supported by the project “Legal Protection of Big Data Transaction Security in Hubei Province” under Grant Number 19ZD077, which is funded by the Hubei Province. This support has been critical in exploring the legal and ethical dimensions related to the application of AI Holographic Cabin technology in various domains, including data security and privacy concerns.
Additionally, we acknowledge the financial assistance provided by the Hubei Provincial Department of Education’s Research Project, specifically for the project titled “Deep Learning-Based Abnormal State Detection System for Transformer Oil Leakage in 110 kV Substations,” with Project Number B2021362. This funding has been instrumental in advancing the development of the deep learning algorithms and their application in the AI Holographic Cabin for improved monitoring and diagnostic capabilities.
We would also like to thank the project teams and collaborators for their invaluable contributions, insights, and efforts throughout the research process. Their dedication has been essential to the success of this study.
Funding
This research was supported by the project “New Engineering Background Undergraduate Students’ Engineering Cognition and Innovation Ability Training Research” under Grant Number 2019GA066, which is aimed at fostering the engineering cognition and innovative capabilities of new undergraduates in the context of new engineering education. The project has provided the necessary funding for the development and implementation of the AI Holographic Cabin technology, as well as the associated research activities detailed in this paper.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Pang, X. et al. (2025). Defect Detection Network for TOPCon Solar Cells Based on Improved YOLOv5 and CBAM Mechanism. In: Zhang, Y., Cai, T., Zhang, LJ. (eds) Big Data – BigData 2024. BIGDATA 2024. Lecture Notes in Computer Science, vol 15422. Springer, Cham. https://doi.org/10.1007/978-3-031-77088-3_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-77088-3_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-77087-6
Online ISBN: 978-3-031-77088-3
eBook Packages: Computer ScienceComputer Science (R0)