Document Type : Review Paper
Authors
1 Mathematics, Informatics and Applications Team, National School of Applied Sciences of Tangier, Abdelmalek Essaâdi University, Tetouan, Morocco
2 Intelligent Systems and Applications Laboratory, Moroccan School of Engineering Sciences, Tangier, Morocco.
10.22044/rera.2026.17973.1558
Abstract
The growing emphasis on renewable energy has led to a notable rise in photovoltaic (PV) installations, highlighting the need for advanced diagnostic methods to enable efficient maintenance and performance optimisation. This paper offers a comprehensive overview of recent developments in the use of artificial intelligence (AI) for image-based fault detection and diagnosis in PV systems with a particular focus on the influence of modality and task design on the performance and real-world deployability. First, a bibliometric analysis was performed to trace the field’s evolution and structural trends, followed by an in-depth technical synthesis organized by fault type, learning paradigm, and application goal. The bibliometric data were sourced from Scopus and Web of Science (WoS). Using Bibliometrix/Biblioshiny, we observe rapid growth in publication activity, increasing collaboration, and a thematic evolution from early classification-oriented studies toward more deployment-relevant pipelines. Consequently, this review highlights persistent technical challenges as well as emerging research directions providing a structured reference for both researchers and practitioners and outlines actionable priorities for advancing reliable field-deployable inspection systems.
Keywords
Main Subjects
[1] R. Herbazi et al., « Performance evaluation and experimental validation of different empirical models for predicting photovoltaic output power », International Journal of Ambient Energy, vol. 43, no 1, p. 7437‑7453, déc. 2022, doi: 10.1080/01430750.2022.2068069.
[2] J.-M. Huang, R.-J. Wai, et W. Gao, « Newly-Designed Fault Diagnostic Method for Solar Photovoltaic Generation System Based on IV-Curve Measurement », IEEE Access, vol. 7, p. 70919‑70932, 2019, doi: 10.1109/ACCESS.2019.2919337.
[3] M. Dhimish, V. Holmes, B. Mehrdadi, M. Dales, et P. Mather, « Photovoltaic fault detection algorithm based on theoretical curves modelling and fuzzy classification system », Energy, vol. 140, no 1, p. 276‑290, août 2017.
[4] E. Garoudja, F. Harrou, Y. Sun, K. Kara, A. Chouder, et S. Silvestre, « Statistical fault detection in photovoltaic systems », Solar Energy, vol. 150, p. 485‑499, juill. 2017, doi: 10.1016/j.solener.2017.04.043.
[5] Q. Navid, A. Hassan, A. A. Fardoun, R. Ramzan, et A. Alraeesi, « Fault Diagnostic Methodologies for Utility-Scale Photovoltaic Power Plants: A State of the Art Review », Sustainability, vol. 13, no 4, p. 1629, janv. 2021, doi: 10.3390/su13041629.
[6] S. Boubaker, S. Kamel, N. Ghazouani, et A. Mellit, « Assessment of Machine and Deep Learning Approaches for Fault Diagnosis in Photovoltaic Systems Using Infrared Thermography », Remote Sens., vol. 15, no 6, 2023, doi: 10.3390/rs15061686.
[7] M. Islam, M. R. Rashel, M. T. Ahmed, A. K. M. K. Islam, et M. Tlemçani, « Artificial Intelligence in Photovoltaic Fault Identification and Diagnosis: A Systematic Review », Energies, vol. 16, no 21, nov. 2023, doi: 10.3390/en16217417.
[8] A. Thakfan et Y. B. Salamah, « Artificial-Intelligence-Based Detection of Defects and Faults in Photovoltaic Systems: A Survey », Energies, vol. 17, no 19, sept. 2024, doi: 10.3390/en17194807.
[9] S. R. Mohanty, M. U. Maruf, V. Singh, et Z. Ahmad, « Machine learning approaches for automatic defect detection in photovoltaic systems », Solar Energy, vol. 298, p. 113672, sept. 2025, doi: 10.1016/j.solener.2025.113672.
[10] E. H. Sepúlveda-Oviedo, L. Travé-Massuyès, A. Subias, M. Pavlov, et C. Alonso, « Fault diagnosis of photovoltaic systems using artificial intelligence: A bibliometric approach », Heliyon, vol. 9, no 11, p. e21491, nov. 2023, doi: 10.1016/j.heliyon.2023.e21491.
[11] I. Passas, « Bibliometric Analysis: The Main Steps », Encyclopedia, vol. 4, no 2, p. 1014‑1025, juin 2024, doi: 10.3390/encyclopedia4020065.
[12] N. van Eck et L. Waltman, « Software survey: VOSviewer, a computer program for bibliometric mapping », Scientometrics, vol. 84, no 2, p. 523‑538, déc. 2009, doi: 10.1007/s11192-009-0146-3.
[13] M. Aria et C. Cuccurullo, « bibliometrix: An R-tool for comprehensive science mapping analysis », Journal of Informetrics, vol. 11, no 4, p. 959‑975, nov. 2017, doi: 10.1016/j.joi.2017.08.007.
[14] B. Thomas, J. Joseph, et J. Jose, « Explorative Bibliometric Study of Medical Image Analysis: Unveiling Trends and Advancements », Scientific Visualization, vol. 15, no 5, 2023, doi: 10.26583/sv.15.5.04.
[15] M. Akram et al., « CNN based automatic detection of photovoltaic cell defects in electroluminescence images », ENERGY, vol. 189, déc. 2019, doi: 10.1016/j.energy.2019.116319.
[16] W. Tang, Q. Yang, K. Xiong, et W. Yan, « Deep learning based automatic defect identification of photovoltaic module using electroluminescence images », SOLAR ENERGY, vol. 201, p. 453‑460, mai 2020, doi: 10.1016/j.solener.2020.03.049.
[17] X. Yang, Q. Zhang, S. Wang, et Y. Zhao, « Detection of solar panel defects based on separable convolution and convolutional block attention module », Energy Sources Recovery Util. Environ. Eff., vol. 45, no 3, p. 7136‑7149, 2023, doi: 10.1080/15567036.2023.2218301.
[18] C. Haitao, L. Caijia, W. Xin, et S. Qiang, « An automatic defects detection system for PV plants with data augmentation », in 2021 International Conference on Power System Technology (POWERCON), déc. 2021, p. 980‑984. doi: 10.1109/POWERCON53785.2021.9697898.
[19] Y. Zhang, X. Zhang, et D. Tu, « Solar photovoltaic module defect detection based on deep learning », Meas. Sci. Technol., vol. 35, no 12, p. 125404, sept. 2024, doi: 10.1088/1361-6501/ad7d28.
[20] H. P.-C. Hwang, C. C.-Y. Ku, et J. C.-C. Chan, « Detection of malfunctioning photovoltaic modules based on machine learning algorithms », IEEE Access, vol. 9, p. 37210‑37219, 2021, doi: 10.1109/ACCESS.2021.3063461.
[21] Z. Barraz, I. Sebari, K. Ait El Kadi, et I. Ait Abdelmoula, « Towards a Holistic Approach for UAV-Based Large-Scale Photovoltaic Inspection: A Review on Deep Learning and Image Processing Techniques », Technologies, vol. 13, no 3, p. 117, mars 2025, doi: 10.3390/technologies13030117.
[22] J. Jerome Vasanth, N. V. S, S. Sugumaran, et V. S. Mahamuni, « Enhancing Photovoltaic Module Fault Diagnosis with Unmanned Aerial Vehicles and Deep Learning-Based Image Analysis », Int. J. Photoenergy, vol. 2023, 2023, doi: 10.1155/2023/8665729.
[23] S. Prabhakaran, R. Uthra, et J. Preetha Roselyn, « Feature Extraction and Classification of Photovoltaic Panels Based on Convolutional Neural Network », Comput. Mater. Continua, vol. 74, no 1, p. 1437‑1455, 2023, doi: 10.32604/cmc.2023.032300.
[24] S. Naveen Venkatesh, B. Rebecca Jeyavadhanam, A. M. Moradi Sizkouhi, S. M. Esmailifar, M. Aghaei, et V. Sugumaran, « Automatic detection of visual faults on photovoltaic modules using deep ensemble learning network », Energy Reports, vol. 8, p. 14382‑14395, nov. 2022, doi: 10.1016/j.egyr.2022.10.427.
[25] R. Pierdicca, M. Paolanti, A. Felicetti, F. Piccinini, et P. Zingaretti, « Automatic faults detection of photovoltaic farms: Solair, a deep learning-based system for thermal images », Energies, vol. 13, no 24, 2020, doi: 10.3390/en13246496.
[26] C.-F. Jeffrey Kuo, S.-H. Chen, et C.-Y. Huang, « Automatic detection, classification and localization of defects in large photovoltaic plants using unmanned aerial vehicles (UAV) based infrared (IR) and RGB imaging », Energy Conversion and Management, vol. 276, p. 116495, janv. 2023, doi: 10.1016/j.enconman.2022.116495.
[27] A. Rico Espinosa, M. Bressan, et L. F. Giraldo, « Failure signature classification in solar photovoltaic plants using RGB images and convolutional neural networks », Renewable Energy, vol. 162, p. 249‑256, déc. 2020, doi: 10.1016/j.renene.2020.07.154.
[28] D. Matusz-Kalász, I. Bodnár, et M. Jobbágy, « An Overview of CNN-Based Image Analysis in Solar Cells, Photovoltaic Modules, and Power Plants », Applied Sciences, vol. 15, no 10, p. 5511, janv. 2025, doi: 10.3390/app15105511.
[29] S. Apak et M. Farsadi, « Multi-branch spatial pyramid dynamic graph convolutional neural networks for solar defect detection », Comput Electr Eng, vol. 121, 2025, doi: 10.1016/j.compeleceng.2024.109872.
[30] M. A. Gupta, M. B. Shah, et M. M. Z. Katlariwala, « Enhanced Detection of Solar Panel Defects Using VGG16-Based Convolutional Neural Networks », International Journal of Scientific Research in Science and Technology, vol. 12, no 3, p. 1255‑1262, juin 2025, doi: 10.32628/IJSRST25123136.
[31] H. Gasparyan, S. Agaian, et S. Wu, « Efficient Lightweight Networks for Solar Panel Fault Classification Using EL and RGB Imagery », IEEE Trans. Instrum. Meas., vol. 74, 2025, doi: 10.1109/TIM.2025.3548249.
[32] A. A. Raorane, D. B. Magare, et Y. D. Mistry, « Performance of fault classification on Photovoltaic modules using Thermographic images », ITM Web of Conferences, 2022, doi: 10.1051/itmconf/20224403065.
[33] A. Raorane, D. Magare, et Y. Mistry, « Thermal image-driven CNN for predicting solar photovoltaic module lifespan from hotspots », Solar Energy, vol. 302, p. 113965, déc. 2025, doi: 10.1016/j.solener.2025.113965.
[34] E. Ozturk, E. Ogliari, M. Sakwa, A. Dolara, N. Blasuttigh, et A. M. Massi Pavan, « Photovoltaic modules fault detection, power output, and parameter estimation: A deep learning approach based on electroluminescence images », Energy Convers. Manage., vol. 319, 2024, doi: 10.1016/j.enconman.2024.118866.
[35] V. E. Puranik et R. Gupta, « Analysis and insight of electroluminescence imaging in the assessment of potential-induced degradation in crystalline silicon photovoltaic module », Engineering Failure Analysis, vol. 134, p. 106027, avr. 2022, doi: 10.1016/j.engfailanal.2022.106027.
[36] B. Wang et al., « PVF-10: A high-resolution unmanned aerial vehicle thermal infrared image dataset for fine-grained photovoltaic fault classification », Appl. Energy, vol. 376, 2024, doi: 10.1016/j.apenergy.2024.124187.
[37] A. S. Al‐Waisy et al., « Identifying defective solar cells in electroluminescence images using deep feature representations », PeerJ Comput. Sci., vol. 8, p. e992, mai 2022, doi: 10.7717/peerj-cs.992.
[38] D. Manno, G. Cipriani, G. Ciulla, V. Di Dio, S. Guarino, et V. Lo Brano, « Deep learning strategies for automatic fault diagnosis in photovoltaic systems by thermographic images », Energy Convers. Manage., vol. 241, 2021, doi: 10.1016/j.enconman.2021.114315.
[39] W. M. Shaban, « Detection and classification of photovoltaic module defects based on artificial intelligence », Neural Comput. Appl., vol. 36, no 27, p. 16769‑16796, 2024, doi: 10.1007/s00521-024-10000-z.
[40] H. Chen, A. Zhang, C. Gong, W. Liang, et Z. Wang, « Fault Diagnosis Method for Photovoltaic Panels Based on Improved ShuffleNet V2 and Infrared Images », in 2022 7th International Conference on Power and Renewable Energy (ICPRE), sept. 2022, p. 447‑451. doi: 10.1109/ICPRE55555.2022.9960396.
[41] N. L. Bin Zulkifli et al., « Optimizing Thermal Image Segmentation Using K-Means Clustering and Morphological Operations for Photovoltaic », in IEEE Int. Conf. Control Syst., Comput. Eng., ICCSCE - Conf. Proc., Institute of Electrical and Electronics Engineers Inc., 2025, p. 169‑174. doi: 10.1109/ICCSCE65566.2025.11182688.
[42] X. Xu, M. Liu, Y. Nie, K. Wang, et W. Xu, « Photovoltaic Module Fault Detection Technology Based on Remote Sensing Technology and Deeplabv3+ Model », IEEE Access, vol. 12, p. 195472‑195482, 2024, doi: 10.1109/ACCESS.2024.3515165.
[43] S. P. Pathak, S. A. Patil, et D. Mishra, « Enhancing Solar Panel Fault Detection: An Efficient Multidomain Feature Analysis Model with Entropy-Guided Saliency Map Segmentation », Int. J. Intelligent Eng. Syst., vol. 17, no 4, p. 328‑339, 2024, doi: 10.22266/IJIES2024.0831.25.
[44] V. Carletti, A. Greco, A. Saggese, et M. Vento, « An intelligent flying system for automatic detection of faults in photovoltaic plants », J Ambient Intell Human Comput, vol. 11, no 5, p. 2027‑2040, mai 2020, doi: 10.1007/s12652-019-01212-6.
[45] L. Bommes, T. Pickel, C. Buerhop, J. Hauch, C. Brabec, et I. Marius Peters, « Computer vision tool for detection, mapping, and fault classification of photovoltaics modules in aerial IR videos », Prog Photovoltaics Res Appl, vol. 29, no 12, p. 1236‑1251, 2021, doi: 10.1002/pip.3448.
[46] W.-H. Chiang, H.-S. Wu, J.-S. Wu, et S.-J. Lin, « A Method for Estimating On-Field Photovoltaics System Efficiency Using Thermal Imaging and Weather Instrument Data and an Unmanned Aerial Vehicle », Energies, vol. 15, no 16, p. 5835, janv. 2022, doi: 10.3390/en15165835.
[47] Ö. Baltacı, Z. Kiral, K. Dalkılınç, et O. Karaman, « Thermal Image and Inverter Data Analysis for Fault Detection and Diagnosis of PV Systems », Appl. Sci., vol. 14, no 9, 2024, doi: 10.3390/app14093671.
[48] A. Sohail, M. S. Rusdi, M. Z. Abdullah, et S. M. Sultan, « Numerical investigation of the thermal performance of PV system under variable wind speeds and ambient temperatures in the tropical climate of Malaysia », Green Technologies and Sustainability, vol. 3, no 3, p. 100210, juill. 2025, doi: 10.1016/j.grets.2025.100210.
[49] « (PDF) Influence of irradiance and drone altitude in infrared thermography inspections of photovoltaic plants », ResearchGate, avr. 2026, doi: 10.1051/epjpv/2025020.
[50] W. Zhang, Y. Zhou, J. Wang, et Z. Li, « PHOTOVOLTAIC MODULES FAULT DETECTION MODEL BASED ON YOLOv7 », Taiyangneng Xuebao, vol. 46, no 8, p. 333‑340, 2025, doi: 10.19912/j.0254-0096.tynxb.2024-0540.
[51] C. R. da Silveira, C. E. R. Sousa, et R. H. Fonseca Alves, « Automatic Fault Classification in Photovoltaic Modules Using Denoising Diffusion Probabilistic Model, Generative Adversarial Networks, and Convolutional Neural Networks », Energies, vol. 18, no 4, 2025, doi: 10.3390/en18040776.
[52] M. A. Ebied, A. Munshi, S. A. Alhuzali, M. M. El-Sotouhy, A. I. Shehta, et M. S. Elborlsy, « Advanced deep learning modeling to enhance detection of defective photovoltaic cells in electroluminescence images », Sci. Rep., vol. 15, no 1, 2025, doi: 10.1038/s41598-025-14478-y.
[53] H. F. M. Romero et al., « Synthetic Dataset of Electroluminescence Images of Photovoltaic Cells by Deep Convolutional Generative Adversarial Networks », Sustainability, vol. 15, no 9, p. 7175, janv. 2023, doi: 10.3390/su15097175.
[54] J. Lekavičius et V. Gružauskas, « Data Augmentation with Generative Adversarial Network for Solar Panel Segmentation from Remote Sensing Images », Energies, vol. 17, no 13, p. 3204, janv. 2024, doi: 10.3390/en17133204.
[55] Y. Jia, G. Chen, et L. Zhao, « Defect detection of photovoltaic modules based on improved VarifocalNet », Sci Rep, vol. 14, no 1, p. 15170, juill. 2024, doi: 10.1038/s41598-024-66234-3.
[56] A. Jha, Y. Rawat, et S. Vyas, « Advancing automatic photovoltaic defect detection using semi-supervised semantic segmentation of electroluminescence images », Eng Appl Artif Intell, vol. 160, 2025, doi: 10.1016/j.engappai.2025.111790.
[57] A.-K. Hamid, M. Alrahhal, K. Obaideen, T. Bonny, Y. C. Tan, et M. I. Hussein, « Artificial intelligence for smart solar energy monitoring: Genetic attention-based hybrid deep–handcrafted fusion for faulty solar panel image classification », Result. Eng., vol. 28, 2025, doi: 10.1016/j.rineng.2025.107900.
[58] T. S. Babu, G. Sruthi, A. A. Goud, V. S. Manikanta, M. Paramasivan, et B. K. Chaitanya, « Fault Identification and Classification of Solar PV System », in Int. Conf. Circuit, Power Comput. Technol., ICCPCT, Institute of Electrical and Electronics Engineers Inc., 2025, p. 1376‑1382. doi: 10.1109/ICCPCT65132.2025.11176670.
[59] L. E. Montanez, J. Reyes-Luévano, L. M. Valentín, D. Moctezuma-Ochoa, F. Lezama, et Z. Vale, « HotSD-Net: Convolutional Neural Network for Estimation of Hot Spots in Photovoltaic Modules via Infrared Imaging », in IEEE Symp. Comput. Intell. Energy, Transp. Environ. Sustain., CIETES, Institute of Electrical and Electronics Engineers Inc., 2025. doi: 10.1109/CIETES63869.2025.10995018.
[60] R. D. Amar Raj, R. M. R. Yanamala, A. Pallakonda, et A. N. Kanasottu, « AAPN-Tiny: A Compact Edge-Deployable Adaptive Attention Pyramid Architecture for Multi-Class Fault Diagnosis in Solar Photovoltaic Modules », IEEE. Lat. Am. Trans., vol. 23, no 12, p. 1284‑1296, 2025, doi: 10.1109/TLA.2025.11231229.
[61] D. Rocha et al., « Multidefect Detection Tool for Large-Scale PV Plants: Segmentation and Classification », IEEE Journal of Photovoltaics, vol. 13, no 2, p. 291‑295, mars 2023, doi: 10.1109/JPHOTOV.2023.3236188.
[62] F. Hong, J. Song, H. Meng, W. Rui, F. Fang, et Z. Zhang, « A novel framework on intelligent detection for module defects of PV plant combining the visible and infrared images », Sol. Energy, vol. 236, p. 406‑416, 2022, doi: 10.1016/j.solener.2022.03.018.
[63] Z. Ksira, N. Blasuttigh, A. Mellit, et A. M. Massi Pavan, « TinyML Model for Fault Classification of Photovoltaic Modules Based on Visible Images », in Lect. Notes Networks Syst., M. Hatti, Éd., Springer Science and Business Media Deutschland GmbH, 2024, p. 373‑380. doi: 10.1007/978-3-031-60629-8_37.
[64] K. Himavarshini et al., « TinyTripleNet: A lightweight architecture for solar photo voltaic fault detection optimized for edge tensor processing unit hardware deployment », Electr Power Syst Res, vol. 252, 2026, doi: 10.1016/j.epsr.2025.112451.
[65] A. Mellit, N. Blasuttigh, et A. M. Massi Pavan, « TinyML for fault diagnosis of Photovoltaic Modules using Edge Impulse Platform », in Int. Conf. Smart Grid, icSmartGrid, Institute of Electrical and Electronics Engineers Inc., 2023. doi: 10.1109/icSmartGrid58556.2023.10171088.
[66] M. F. Bekciogullari, H. Acikgoz, et S. Ozbay, « Detection of Hot Spots in PV Modules with the CBAM-Enhanced Yolo Model », in ISAS - Int. Symp. Innov. Approaches Smart Technol., Proc., Institute of Electrical and Electronics Engineers Inc., 2025. doi: 10.1109/ISAS66241.2025.11101735.
[67] A. Karakan, « Detection of Defective Solar Panel Cells in Electroluminescence Images with Deep Learning », Sustainability, vol. 17, no 3, 2025, doi: 10.3390/su17031141.
[68] N. Drir, F. Chekired, A. Mellit, et N. Blasuttigh, « Hybrid CNN-EML model for fault diagnosis in electroluminescence images of photovoltaic cells », Renew. Energy, vol. 250, 2025, doi: 10.1016/j.renene.2025.123343.
[69] S. Boubaker, C. Moussaoui, A. Mellit, et M. Benghanem, « TinyML Model for Solar Cell Defect Classification Based on Electroluminescence Images », in Lect. Notes Electr. Eng., B. Hajji, A. Gagliano, A. Mellit, A. Rabhi, et M. Calì, Éd., Springer Science and Business Media Deutschland GmbH, 2025, p. 511‑519. doi: 10.1007/978-981-96-0644-3_46.
[70] D. Lang et Z. Lv, « A PV cell defect detector combined with transformer and attention mechanism », Sci. Rep., vol. 14, no 1, 2024, doi: 10.1038/s41598-024-72019-5.
[71] N. V. S, J. V. Joseph, S. Sugumaran, et M. Aghaei, « Weightless Neural Network-Based Detection and Diagnosis of Visual Faults in Photovoltaic Modules », Energies, vol. 16, no 15, 2023, doi: 10.3390/en16155824.
[72] M. Alanazi et Y. A. Alamri, « SolarFaultAttentionNet: Dual-Attention Framework for Enhanced Photovoltaic Fault Classification », Inventions, vol. 10, no 5, 2025, doi: 10.3390/inventions10050091.
[73] P. A. Vyas, S. Bhandari, et P. Sonowane, « Vision Transformer-Based Fault Diagnosis for Solar Panels Using Visible Image Dataset », in Int. Conf. Energy, Power Environ., ICEPE, Institute of Electrical and Electronics Engineers Inc., 2025. doi: 10.1109/ICEPE65965.2025.11139664.
[74] K. Chahine, « Tree-Based Algorithms and Incremental Feature Optimization for Fault Detection and Diagnosis in Photovoltaic Systems », Eng, vol. 6, no 1, p. 20, janv. 2025, doi: 10.3390/eng6010020.
[75] S. Goyal et J. C. Rajapakse, « Self-supervised learning for hotspot detection and isolation from thermal images », Expert Systems with Applications, vol. 237, p. 121566, mars 2024, doi: 10.1016/j.eswa.2023.121566.
[76] F. Z. Kardaş et A. Atmaca, « A REVIEW OF ARTIFICIAL INTELLIGENCE BASED STUDIES ABOUT FAULT-DETECTION AND PERFORMANCE ASSESSMENT IN SOLAR POWER PLANTS », IJEES, no Advanced Online Publication, p. 16‑39.
[77] A. Oulefki et al., « Unveiling the Invisible: Enhanced Detection and Analysis of Deteriorated Areas in Solar PV Modules Using Unsupervised Sensing Algorithms and 3D Augmented Reality », 12 juillet 2023, arXiv: arXiv:2307.05136. doi: 10.48550/arXiv.2307.05136.
[78] A. Esteban, A. Cano, S. Ventura, et A. Zafra, « Simultaneous fault prediction in evolving industrial environments with ensembles of Hoeffding adaptive trees », Appl Intell, vol. 55, no 13, p. 930, août 2025, doi: 10.1007/s10489-025-06786-7.
[79] N. Sergin, J. Huang, T.-S. Chang, et H. Yan, « Image-based Novel Fault Detection with Deep Learning Classifiers using Hierarchical Labels », 26 mars 2024, arXiv: arXiv:2403.17891. doi: 10.48550/arXiv.2403.17891.
[80] E. K. Ukiwe, S. A. Adeshina, T. Jacob, et B. B. Adetokun, « Deep learning model for detection of hotspots using infrared thermographic images of electrical installations », Journal of Electrical Systems and Inf Technol, vol. 11, no 1, p. 24, juin 2024, doi: 10.1186/s43067-024-00148-y.
[81] D. Rocha, M. Lopes, J. P. Teixeira, P. A. Fernandes, M. Morais, et P. M. P. Salomé, « A Deep Learning Approach for PV Failure Mode Detection in Infrared Images: First Insights », in Conf Rec IEEE Photovoltaic Spec Conf, Institute of Electrical and Electronics Engineers Inc., 2022, p. 630‑632. doi: 10.1109/PVSC48317.2022.9938524.
[82] Y. Tao, Z. Xu, Q. Liu, L. Li, et Y. Zhang, « Improved faster R-CNN algorithm for defect detection of electromagnetic luminescence », in Proc SPIE Int Soc Opt Eng, H. Xia, L. X. Yang, et L. Yu, Éd., SPIE, 2021. doi: 10.1117/12.2617320.
[83] N. S. Maddileti, R. Namburi, R. D. A. David Amar Raj, R. M. R. Yanamala, et A. Pallakonda, « DCGAN-Driven Minority Class Augmentation for Lightweight YOLO-Based Photovoltaic Defect Localization Suitable for Edge Deployment », IEEE Trans. Device Mater. Reliab., vol. 25, no 3, p. 742‑751, 2025, doi: 10.1109/TDMR.2025.3592416.
[84] P. R. Sonawane et S. Bhandari, « Deep Learning-Based Fault Diagnosis System for Solar Photovoltaic Panels Using EL Images », in Lect. Notes Electr. Eng., H. Mohamad, M. H. Hasan, S. J. Abdulkadir, et N. Shafiq, Éd., Springer Science and Business Media Deutschland GmbH, 2025, p. 279‑294. doi: 10.1007/978-981-96-5848-0_24.
[85] A. Mellit, « An embedded solution for fault detection and diagnosis of photovoltaic modules using thermographic images and deep convolutional neural networks », Eng Appl Artif Intell, vol. 116, 2022, doi: 10.1016/j.engappai.2022.105459.
[86] A. Mellit, C. Moussaoui, S. Pastore, et A. M. Pavan, « Fault Diagnosis of Photovoltaic Modules Using Infrared Images and Hybrid DCNNs: A Comparative Study », in 2024 IEEE International Conference on Environment and Electrical Engineering and 2024 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe), juin 2024, p. 1‑6. doi: 10.1109/EEEIC/ICPSEurope61470.2024.10751391.
[87] P. Malik, V. Saxena, S. Raj, S. Singh, S. Kumar, et P. S. Ganaraj, « Fault Detection of the Solar Photovoltaic Modules Using YOLO Models », in IEEE Reg. 10 Symp., TENSYMP, Institute of Electrical and Electronics Engineers Inc., 2024. doi: 10.1109/TENSYMP61132.2024.10752194.
[88] B. Li, X. Chen, et A. Jain, « Exploring Capability of Multimodal Foundation Model for Image-based Fault Detection of Photovoltaic Modules », in Conf Rec IEEE Photovoltaic Spec Conf, Institute of Electrical and Electronics Engineers Inc., 2025, p. 988‑991. doi: 10.1109/PVSC59419.2025.11133222.
[89] Q. Hong, T. Huang, W. Yan, C. Ji, X. Li, et Z. Du, « Deep Learning Based Multi-Stage Defect Diagnosis Method of Photovoltaic Modules Using Aerial Images from UAV », in Chinese Control Conf., CCC, J. Sun et H. Yin, Éd., IEEE Computer Society, 2025, p. 7520‑7525. doi: 10.23919/CCC64809.2025.11179561.
[90] W.-Q. Lu, C. Delpha, D. Diallo, et A. Migan-Dubois, « Spatial Attention Mechanism Derived from Diffusion Model for Photovoltaic Cell Fault Diagnosis », in Proc. - EUROCON: Int. Conf. Smart Technol., I. Czarnowski et M. Jasinski, Éd., Institute of Electrical and Electronics Engineers Inc., 2025. doi: 10.1109/EUROCON64445.2025.11073476.
[91] L. Bommes et al., « Anomaly detection in IR images of PV modules using supervised contrastive learning », Prog Photovoltaics Res Appl, vol. 30, no 6, p. 597‑614, 2022, doi: 10.1002/pip.3518.
[92] U. Naeem, K. Chadda, S. Vahaji, J. Ahmad, X. Li, et E. Asadi, « Aerial Imaging-Based Soiling Detection System for Solar Photovoltaic Panel Cleanliness Inspection », Sensors, vol. 25, no 3, 2025, doi: 10.3390/s25030738.
[93] Q. Wang, K. Paynabar, et M. Pacella, « Online automatic anomaly detection for photovoltaic systems using thermography imaging and low rank matrix decomposition », J Qual Technol, vol. 54, no 5, p. 503‑516, 2022, doi: 10.1080/00224065.2021.1948372.
[94] S. Gallmetzer, M. Sondoqah, E. Turri, L. Koester, A. Louwen, et D. Moser, « Redefining failure detection in PV Systems: a comparative study of GPT-4o and ResNet’s computer vision in aerial infrared imagery analysis », EPJ Photovolt., vol. 16, 2025, doi: 10.1051/epjpv/2025010.
[95] X. Li, W. Li, Q. Yang, W. Yan, et A. Y. Zomaya, « Edge-Computing-Enabled Unmanned Module Defect Detection and Diagnosis System for Large-Scale Photovoltaic Plants », IEEE Internet Things J., vol. 7, no 10, p. 9651‑9663, 2020, doi: 10.1109/JIOT.2020.2983723.
[96] J. I. A. Tsanakas et P. Marechal, « Decoding pixels: A modular software prototype for cognitive image-based diagnostics of PV plants », EPJ Photovolt., vol. 16, 2025, doi: 10.1051/epjpv/2025013.
[97] M. Kolahi, S. M. Esmailifar, A. M. Moradi Sizkouhi, et M. Aghaei, « Digital-PV: A digital twin-based platform for autonomous aerial monitoring of large-scale photovoltaic power plants », Energy Convers. Manage., vol. 321, 2024, doi: 10.1016/j.enconman.2024.118963.
[98] S. Rao et al., « A cyber-physical system approach for photovoltaic array monitoring and control », in Int. Conf. Inf., Intell., Syst. Appl., IISA, Institute of Electrical and Electronics Engineers Inc., 2017, p. 1‑6. doi: 10.1109/IISA.2017.8316458.
)