U-Net–based semantic segmentation of defects in photovoltaic panels
Article Sidebar
Main Article Content
Abstract
This article presents a study on the semantic segmentation of defects in crystalline-silicon photovoltaic cells using U-Net–based models trained on electroluminescence (EL) images. The dataset combines laboratory-acquired images with a publicly available benchmark, both manually annotated to identify cracks, dark zones, and collector-bar discontinuities. Eight model variants were trained with controlled variations in input resolution, encoder depth, and regularization strategies. Performance was assessed using per-class precision, recall, and F1-score, complemented by visual inspection through heatmaps and overlays and by expert validation. Segmentation was robust for defects with well-defined morphology, such as dark zones and busbars; however, cracks remained more difficult to detect due to their sparse pixel representation and irregular geometry. Alternative architectures (U-Net++ and MAU-Net) were also evaluated but did not yield meaningful improvements over the optimized U-Net configuration. Overall, the results support the use of this approach for automated inspection under controlled conditions, while highlighting the need for future adaptation to more diverse operational scenarios.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
The Universidad Politécnica Salesiana of Ecuador preserves the copyrights of the published works and will favor the reuse of the works. The works are published in the electronic edition of the journal under a Creative Commons Attribution/Noncommercial-No Derivative Works 4.0 Ecuador license: they can be copied, used, disseminated, transmitted and publicly displayed.
The undersigned author partially transfers the copyrights of this work to the Universidad Politécnica Salesiana of Ecuador for printed editions.
It is also stated that they have respected the ethical principles of research and are free from any conflict of interest. The author(s) certify that this work has not been published, nor is it under consideration for publication in any other journal or editorial work.
The author (s) are responsible for their content and have contributed to the conception, design and completion of the work, analysis and interpretation of data, and to have participated in the writing of the text and its revisions, as well as in the approval of the version which is finally referred to as an attachment.
References
[1] K. G. Bedrich, M. Bliss, T. R. Betts, and R. Gottschalg, “Electroluminescence imaging of PV devices: Determining the image quality,” in 2015 IEEE 42nd Photovoltaic Specialist Conference (PVSC). IEEE, Jun. 2015, pp. 1–5. [Online]. Available: https://doi.org/10.1109/PVSC.2015.7356011
[2] T. Fuyuki and A. Kitiyanan, “Photographic diagnosis of crystalline silicon solar cells utilizing electroluminescence,” Applied Physics A, vol. 96, no. 1, pp. 189–196, Dec. 2008. [Online]. Available: http://doi.org/10.1007/s00339-008-4986-0
[3] M. Akram and J. Bai, “Defect detection in photovoltaic modules based on image-to-image generation and deep learning,” Sustainable Energy Technologies and Assessments, vol. 82, p. 104441, Oct. 2025. [Online]. Available: http://doi.org/http://doi.org/
[4] J. Wang, L. Bi, P. Sun, X. Jiao, X. Ma, X. Lei, and Y. Luo, “Deep-learning-based automatic detection of photovoltaic cell defects in electroluminescence images,” Sensors, vol. 23, no. 1, p. 297, Dec. 2022. [Online]. Available: http://doi.org/10.3390/s23010297
[5] Q. Liu, M. Liu, C. Wang, and Q. J. Wu, “An efficient CNN-based detector for photovoltaic module cells defect detection in electroluminescence images,” Solar Energy, vol. 267, p. 112245, Jan. 2024. [Online]. Available: http://doi.org/10.1016/j.solener.2023.112245
[6] J. Fioresi, D. J. Colvin, R. Frota, R. Gupta, M. Li, H. P. Seigneur, S. Vyas, S. Oliveira, M. Shah, and K. O. Davis, “Automated defect detection and localization in photovoltaic cells using semantic segmentation of electroluminescence images,” IEEE Journal of Photovoltaics, vol. 12, no. 1, pp. 53–61, Jan. 2022. [Online]. Available: http://doi.org/10.1109/jphotov.2021.3131059
[7] O. Ronneberger, P. Fischer, and T. Brox, U-Net: Convolutional Networks for Biomedical Image Segmentation. Springer International Publishing, 2015, pp. 234–241. [Online]. Available: http://doi.org/10.1007/978-3-319-24574-4_28
[8] L. Pratt, D. Govender, and R. Klein, “Defect detection and quantification in electroluminescence images of solar PV modules using U-net semantic segmentation,” Renewable Energy, vol. 178, pp. 1211–1222, Nov. 2021. [Online]. Available: http://doi.org/10.1016/j.renene.2021.06.086
[9] H. Eesaar, S. Joe, M. U. Rehman, Y. Jang, and K. T. Chong, “SEiPV-net: An efficient deep learning framework for autonomous multi-defect segmentation in electroluminescence images of solar photovoltaic modules,” Energies, vol. 16, no. 23, p. 7726, Nov. 2023. [Online]. Available: https://doi.org/10.3390/en16237726
[10] M. R. U. Rahman and H. Chen, “Defects inspection in polycrystalline solar cells electroluminescence images using deep learning,” IEEE Access, vol. 8, pp. 40 547–40 558, 2020. [Online]. Available: http://doi.org/10.1109/access.2020.2976843
[11] R. A. Mamun Rudro, K. Nur, F. A. Al Sohan, M. Mridha, S. Alfarhood, M. Safran, and K. Kanagarathinam, “SPF-Net: Solar panel fault detection using U-net based deep learning image classification,” Energy Reports, vol. 12, pp. 1580–1594, Dec. 2024. [Online]. Available: http://doi.org/10.1016/j.egyr.2024.07.044
[12] S. Deitsch, V. Christlein, S. Berger, C. Buerhop-Lutz, A. Maier, F. Gallwitz, and C. Riess, “Automatic classification of defective photovoltaic module cells in electroluminescence images,” Solar Energy, vol. 185, pp. 455–468, Jun. 2019. [Online]. Available: http://doi.org/10.1016/j.solener.2019.02.067
[13] U. Hijjawi, S. Lakshminarayana, T. Xu, and M. Rahman, “A benchmarking study of instance segmentation methods for photovoltaic cell defect detection using electroluminescence images,” Solar Energy, vol. 303, p. 114083, Jan. 2026.
[14] IEC, IEC Technical Specification 60904-13. Photovoltaic devices - Part 13: Electroluminescence of photovoltaic modules. InternationalElectrotechnicalCommission, 2018. [Online]. Available: http://doi.org/10.4229/35thEUPVSEC20182018-5CV.3.15
[15] Supervisely. (2023) Supervisely computer vision platform. Supervisely OÜ. [Online]. Available: https://upsalesiana.ec/ing35ar8r2
[16] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” 2014.
[17] A. Sohail, N. Ul Islam, A. Ul Haq, S. Ul Islam, I. Shafi, and J. Park, “Fault detection and computation of power in PV cells under faulty conditions using deep-learning,” Energy Reports, vol. 9, pp. 4325–4336, Dec. 2023.
[18] S. Deitsch, C. Buerhop-Lutz, E. Sovetkin, A. Steland, A. Maier, F. Gallwitz, and C. Riess, “Segmentation of photovoltaic module cells in uncalibrated electroluminescence images,” Machine Vision and Applications, vol. 32, no. 4, May 2021.
[19] C. Buerhop-Lutz, S. Deitsch, A. Maier, F. Gallwitz, S. Berger, B. Doll, J. Hauch, C. Camus, and C. Brabec, “A benchmark for visual identification of defective solar cells in electroluminescence imagery,” 35th European Photovoltaic Solar Energy Conference and Exhibition; 1287-1289, 2018. [Online]. Available: http://doi.org/10.4229/35THEUPVSEC20182018-5CV.3.15