Thermal-Aware Attention-Driven Deep Learning for Intelligent Solar Panel Defect Detection
Abstract
As global awareness of climate change grows, renewable energy sources like solar power have become increasingly important. Photovoltaic (PV) systems, which convert sunlight into electricity using solar cells, are widely used due to their sustainability, low maintenance costs, and ease of installation. However, PV panels often suffer from defects such as cracks, hot spots, and shading, which can significantly reduce energy conversion efficiency and, if left undetected, lead to system failure. To address this, the paper proposes a deep learning classification model that combines Inception modules, Attention mechanisms, and Bi-directional Long Short-Term Memory to detect solar panel defects from thermal infrared images. The model is trained and evaluated on a public dataset containing 5,352 thermal images of solar panels, with labels indicating the presence or absence of thermal defects. Three data partitioning strategies are applied to assess model performance under different validation conditions and key evaluation metrics. The proposed model achieved an accuracy of 91.56%, an AUC of 0.9677, and an F1-Score of 95.33%. Furthermore, a user-friendly graphical interface has been developed to allow users to upload thermal images and receive instant classification results. This system enhances defect detection efficiency, supports preventive maintenance, extends panel lifespan, and reduces long-term operational costs in solar energy systems.
References
J. Pastuszak and P. W?gierek, “Photovoltaic Cell Generations and Current Research Directions for Their Development,” Materials, vol. 15, no. 16, p. 5542, Aug. 2022, doi: 10.3390/ma15165542. A. Shaik, A. Balasundaram, L. S. Kakarla, and N. Murugan, “Deep Learning-Based Detection and Segmentation of Damage in Solar Panels,” Automation, vol. 5, no. 2, pp. 128–150, May 2024, doi: 10.3390/automation5020009. J. C. Sánchez Barroso, N. Barth, J. P. M. Correia, S. Ahzi, and M. A. Khaleel, “A computational analysis of coupled thermal and electrical behavior of PV panels,” Sol. Energy Mater. Sol. Cells, vol. 148, pp. 73–86, Apr. 2016, doi: 10.1016/j.solmat.2015.09.004. A. Mohammad Bagher, “Types of Solar Cells and Application,” Am. J. Opt. Photonics, vol. 3, no. 5, p. 94, 2015, doi: 10.11648/j.ajop.20150305.17. M. Zhang and L. Yin, “Solar Cell Surface Defect Detection Based on Improved YOLO v5,” IEEE Access, vol. 10, pp. 80804–80815, 2022, doi: 10.1109/ACCESS.2022.3195901. A. N. Wilson, K. A. Gupta, B. H. Koduru, A. Kumar, A. Jha, and L. R. Cenkeramaddi, “Recent Advances in Thermal Imaging and its Applications Using Machine Learning: A Review,” IEEE Sens. J., vol. 23, no. 4, pp. 3395–3407, Feb. 2023, doi: 10.1109/JSEN.2023.3234335. L. Alzubaidi et al., “Review of deep learning: concepts, CNN architectures, challenges, applications, future directions,” J. Big Data, vol. 8, no. 1, p. 53, Mar. 2021, doi: 10.1186/s40537-021-00444-8. Li, X., Wang, Y., Monday, H.N. and Nneji, G.U., 2025. A novel residual learning of multi-scale feature extraction model for the classification of rice grain varieties. Computers and Electronics in Agriculture, 237, p.110491. Monday, H.N., Nneji, G.U., Hossin, M.A., Mark, K.D., Umana, E.S., Mgbejime, G.T. and Li, J., 2025. Enhancing ECG Classification in Cardiac Diagnostics: A Novel Approach Using Adaptive Focal Cross-Entropy Loss Function. IEEE Journal of Biomedical and Health Informatics. Nneji, G. U., Monday, H. N., Pathapati, V. S. R., Nahar, S., Mgbejime, G. T., Umana, E. S., & Hossin, M. A. (2025). FFS-IML: fusion-based statistical feature selection for machine learning-driven interpretability of chronic kidney disease. International Journal of Machine Learning and Cybernetics, 1-34. Happy. N. M, J. Li, G. U. Nneji, C. C. Ukwuoma, J. Cai, I. Chikwendu, and A. Oluwasanmi, “A wavelet convolutional capsule network with modified super resolution generative adversarial network for fault diagnosis and classification”, Complex & Intelligent Systems, vol. 8, no. 1, pp. 1–15, Apr. 2022. doi: 10.1007/s40747-022-00733-6. Grace. U. N, J. Cai, H. N. Monday, M. A. Hossin, S. Nahar, J. Jackson, and J. Deng, “Fine-tuned Siamese Network with Modified Enhanced Super-Resolution GAN Plus Based on Low Quality Chest X-Ray Images for COVID-19 Identification”, Diagnostics, vol. 12, no. 3, Mar. 2022, https://doi.org/10.3390/diagnostics12030717. N. U. Ugochi, J. Deng, H. N. Monday, J. Cai, M. A. Hossin, S. Nahar, and J. Jackson, “COVID- 19 Identification from Low-Quality Computed Tomography Using a Modified Enhanced Super-Resolution Generative Adversarial Network Plus and Siamese Capsule Network”, Healthcare, vol. 10, no. 2, p. 403, Feb. 2022, https://doi.org/10.3390/healthcare10020403. S. Indolia, A. K. Goswami, S. P. Mishra, and P. Asopa, “Conceptual Understanding of E- ISSN 2489-009X , Convolutional Neural Network- A Deep Learning Approach,” Procedia Comput. Sci., vol. 132, pp. 679–688, 2018, doi: 10.1016/j.procs.2018.05.069. A. Ghosh, A. Sufian, F. Sultana, A. Chakrabarti, and D. De, “Fundamental Concepts of Convolutional Neural Network,” in Recent Trends and Advances in Artificial Intelligence and Internet of Things, vol. 172, V. E. Balas, R. Kumar, and R. Srivastava, Eds., in Intelligent Systems Reference Library, vol. 172. , Cham: Springer International Publishing, 2020, pp. 519–567. doi: 10.1007/978-3-030-32644-9_36. A. Younesi, M. Ansari, M. Fazli, A. Ejlali, M. Shafique, and J. Henkel, “A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends,” IEEE Access, vol. 12, pp. 41180–41218, 2024, doi: 10.1109/ACCESS.2024.3376441. L. Koshy, M. V. Vaishnav, S. Sunil, S. V. Abraham, and S. Vidhyadharan, “A Thermal Image- based Fault Detection System for Solar Panels,” in 2024 International Conference on Cybernation and Computation (CYBERCOM), Dehradun, India: IEEE, Nov. 2024, pp. 246–250. doi: 10.1109/CYBERCOM63683.2024.10803145. F. Wang, Z. Wang, Z. Chen, D. Zhu, X. Gong, and W. Cong, “An Edge-Guided Deep Learning Solar Panel Hotspot Thermal Image Segmentation Algorithm,” Appl. Sci., vol. 13, no. 19, p. 11031, Oct. 2023, doi: 10.3390/app131911031. P. Haidari, A. Hajiahmad, A. Jafari, and A. Nasiri, “Deep learning-based model for fault classification in solar modules using infrared images,” Sustain. Energy Technol. Assess., vol. 52, p. 102110, Aug. 2022, doi: 10.1016/j.seta.2022.102110. C. Dunderdale, W. Brettenny, C. Clohessy, and E. E. Van Dyk, “Photovoltaic defect classification through thermal infrared imaging using a machine learning approach,” Prog. Photovolt. Res. Appl., vol. 28, no. 3, pp. 177–188, Mar. 2020, doi: 10.1002/pip.3191. H. Yousif and Z. Al-Milaji, “Fault detection from PV images using hybrid deep learning model,” Sol. Energy, vol. 267, p. 112207, Jan. 2024, doi: 10.1016/j.solener.2023.112207. S. Jaybhaye, O. Thakur, R. Yardi, V. Raut, and A. Raut, “Solar Panel Damage Detection and Localization of Thermal Images,” J. Fail. Anal. Prev., vol. 23, no. 5, pp. 1980–1990, Oct. 2023, doi: 10.1007/s11668-023-01747-z. T. Barakbayeva and F. M. Demirci, “Fully automatic CNN design with inception and ResNet blocks,” Neural Comput. Appl., vol. 35, no. 2, pp. 1569–1580, Jan. 2023, doi: 10.1007/s00521-022-07700-9. G. Brauwers and F. Frasincar, “A General Survey on Attention Mechanisms in Deep Learning,” IEEE Trans. Knowl. Data Eng., vol. 35, no. 4, pp. 3279–3298, Apr. 2023, doi: 10.1109/TKDE.2021.3126456. M. Kerkhof, L. Wu, G. Perin, and S. Picek, “Focus is Key to Success: A Focal Loss Function for Deep Learning-Based Side-Channel Analysis,” in Constructive Side-Channel Analysis and Secure Design, vol. 13211, J. Balasch and C. O’Flynn, Eds., in Lecture Notes in Computer Science, vol. 13211. , Cham: Springer International Publishing, 2022, pp. 29– 48. doi: 10.1007/978-3-030-99766-3_2. S. Ali et al., “Explainable Artificial Intelligence : What we know and what is left to attain Trustworthy Artificial Intelligence,” Inf. Fusion, vol. 99, p. 101805, Nov. 2023, doi: 10.1016/j.inffus.2023.101805.
More Articles from INTERNATIONAL JOURNAL OF APPLIED SCIENCES AND MATHEMATICAL THEORY
5-Point Block Backward Differentiation Formulae for Solving Stiff Chemical Reaction Problems of Ordinary Differential Equations
Author: Samson Yunusa, Imande Terdon Terlumun,, Etuk Emmanuel Dan, and Micah Michael
Analytical–Numerical Solution of a Temperature-Dependent Volterra Integro-Differential Model for Avian Influenza Transmission with Saturated Incidence and Environmental Feedback Via an Enhanced Adomian Decomposition Method
Author: Ejes, Valentine, Liberty Ebiwareme
Modelling Dengue Transmission Dynamics using a Two-Time Delay Differential Equation
Author: Uwakwe, J. I., Anyanwu, E., Inalegwu, N.
Intelligent Diagnosis and Dynamic Differentiated Instruction for High-School Mathematics Concepts Based on APOS Theory - Model Development, Implementation Pathway, And Validation Plan
Author: Xi Yang, Wenzhuo Zhang
Distribution-Free Error Control for Fraud Alert Triage: Conformal Anomaly P-Values Under Class Imbalance, Concept Drift, and Calibration Contamination
Author: Olamiji Onafowokan1, Olawale Fadugba2, Deborah Okunola1, Alex Mendy1