Solar Panels Fault Classification using an Optimized Moment-Based Feature Extraction Method
Ismail NAOUADIR, Omar EL OGRI, Jaouad EL-MEKKAOUI, Mohamed BENSLIMANE, Amal HJOUJI
Abstract. Solar panel fault detection and classification are of paramount importance for the success of renewable energies, as they mitigate wasting power and help solar farms stay efficient. In this paper we propose a novel feature extraction methods based on Krawtchouk moments and their parameters, using the simulated annealing optimization algorithm we can find the appropriate parameters which make the moments focus on regions where the physical or electrical damage is located, this way we can feed the classification model only most relevant features, and combined with a small but efficient convolutional neural network model, we achieved an area under curve of 99.48%, 98.96% precision, 98.61% recall, and 99.58% F1 score.
Keywords
Solar Panel Classification, Krawtchouk Moments, Image Moments, Convolutional Neural Networks, Image Classification
Published online 4/25/2026, 8 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Ismail NAOUADIR, Omar EL OGRI, Jaouad EL-MEKKAOUI, Mohamed BENSLIMANE, Amal HJOUJI, Solar Panels Fault Classification using an Optimized Moment-Based Feature Extraction Method, Materials Research Proceedings, Vol. 64, pp 455-462, 2026
DOI: https://doi.org/10.21741/9781644904091-57
The article was published as article 57 of the book Energy Futures
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] I. Naouadir, O. E. Ogri, J. E. Mekkaoui, M. Benslimane, and A. Hjouji, ‘Celestial Object Detection in Astronomical Images Using MSE and Jacobi Moments’, Statistics, Optimization & Information Computing, vol. 12, no. 3, Art. no. 3, Feb. 2024. https://doi.org/10.19139/soic-2310-5070-1959.
[2] Y. Aakam, O. El Ogri, J. El-Mekkaoui, M. Benslimane, and A. Hjouji, ‘Efficient 2D and 3D Image Classification and Compression Using Dual-Hahn Moments’, 2024, pp. 312–324. https://doi.org/10.1007/978-3-031-68660-3_29.
[3] Y. Aakam, O. El Ogri, J. El-Mekkaoui, M. Benslimane, and A. Hjouji, ‘Optimal image 2D/3D by Krawtchouk moments and ABC algorithm’, Statistics Optimization & Information Computing, vol. 12, pp. 672–684, Feb. 2024. https://doi.org/10.19139/soic-2310-5070-1960.
[4] P.-T. Yap, P. Raveendran, and S.-H. Ong, Krawtchouk moments as a new set of discrete orthogonal moments for image reconstruction, vol. 1. 2002, p. 912. https://doi.org/10.1109/IJCNN.2002.1005595.
[5] P.-T. Yap, R. Paramesran, and S.-H. Ong, ‘Image analysis by Krawtchouk moments’, IEEE Transactions on Image Processing, vol. 12, no. 11, Art. no. 11, Nov. 2003. https://doi.org/10.1109/TIP.2003.818019.
[6] R. F. Pamungkas, I. B. K. Y. Utama, and Y. M. Jang, ‘A Novel Approach for Efficient Solar Panel Fault Classification Using Coupled UDenseNet’, Sensors, vol. 23, no. 10, p. 4918, Jan. 2023. https://doi.org/10.3390/s23104918.
[7] R. H. Fonseca Alves, G. A. de Deus Júnior, E. G. Marra, and R. P. Lemos, ‘Automatic fault classification in photovoltaic modules using Convolutional Neural Networks’, Renewable Energy, vol. 179, pp. 502–516, Dec. 2021. https://doi.org/10.1016/j.renene.2021.07.070.
[8] D. Korkmaz and H. Acikgoz, ‘An efficient fault classification method in solar photovoltaic modules using transfer learning and multi-scale convolutional neural network’, Engineering Applications of Artificial Intelligence, vol. 113, p. 104959, Aug. 2022. https://doi.org/10.1016/j.engappai.2022.104959.
[9] ‘Solar Panel Images Clean and Faulty Images’. Accessed: Aug. 08, 2025. [Online]. Available: https://www.kaggle.com/datasets/pythonafroz/solar-panel-images
[10] C. Wang, C. Deng, and S. Wang, ‘Imbalance-XGBoost: leveraging weighted and focal losses for binary label-imbalanced classification with XGBoost’, Pattern Recognition Letters, vol. 136, pp. 190–197, Aug. 2020. https://doi.org/10.1016/j.patrec.2020.05.035.
[11] R. A. M. Rudro et al., ‘SPF-Net: Solar panel fault detection using U-Net based deep learning image classification’, Energy Reports, vol. 12, pp. 1580–1594, Dec. 2024. https://doi.org/10.1016/j.egyr.2024.07.044.
[12] C. J. Ejiyi et al., ‘SolarSynthNet (SSN): A deep learning framework for binary and multiclass classification of damaged or obstructed solar panels using images’, Renewable Energy, vol. 256, p. 124224, Jan. 2026. https://doi.org/10.1016/j.renene.2025.124224.
