journal article·2026-03Open access

Intelligent fault detection in photovoltaic modules using attention-based deep learning network

Naveen Venkatesh Sridharan, Divya Sripada, Sugumaran Vaithiyanathan, Mohammadreza Aghaei

Cell Reports Physical Science· Volume 7· Issue 3

Abstract

Photovoltaic (PV) systems experience various faults due to environmental conditions, human errors, and equipment failure during their service life. To necessitate maximum power generation and ensure ideal operating conditions, the development of intelligent fault diagnosis models is essential. In the present study, an attention-based deep learning network, namely, vision transformer (ViT), is adopted to automatically detect the visual faults, such as glass breakage, discoloration, burn marks, snail trail, good panel, and delamination on PV modules. An image dataset has been developed with the true color images of various faulty PV modules. The ViT model was fine-tuned and trained over the custom dataset created. The trained ViT model demonstrates a superior classification accuracy of 99.84% for fault detection and classification in PV modules. The obtained classification results of the model are compared with several other classification results reported in the literature. The ViT model could potentially be integrated into existing inspection systems for autonomous, real-time, efficient, and robust condition monitoring of PV modules.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Photovoltaic System Optimization Techniques · Photovoltaic Systems and Sustainability · Solar Radiation and Photovoltaics

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (46)

Show source-provided references
1. “Towards a fuller assessment of benefits to children’s health of reducing air pollution and mitigating climate change due to fossil fuel combustion,”10.1016/j.envres.2018.12.016 ↗
2. “Addressing the challenges of climate change risks and adaptation in coastal areas: A review,”10.1016/j.coastaleng.2019.103611 ↗
3. “Higher frequency of Central Pacific El Niño events in recent decades relative to past centuries,”10.1038/s41561-019-0353-3 ↗
4. “Challenges and solution technologies for the integration of variable renewable energy sources—a review,”10.1016/j.renene.2019.06.147 ↗
5. “New tendencies in wind energy operation and maintenance,”10.3390/app11041386 ↗
6. “Material consumption and environmental impact of wind turbines in the USA and globally,”10.1016/j.resconrec.2021.105938 ↗
7. “Hydropower dams, river drought and health effects: A detection and attribution study in the lower Mekong Delta Region,”
8. “A multi-perspective assessment approach of renewable energy production: policy perspective analysis,”10.1007/s10668-021-01524-8 ↗
9. IRENA, World Energy Transitions Outlook: 1.5°C Pathway. 2022.
10. “Modeling of PV system based on experimental data for fault detection using kNN method,”10.1016/j.solener.2018.07.038 ↗
11. “A comprehensive review of automatic cleaning systems of solar panels,”
12. “Inspection and condition monitoring of large-scale photovoltaic power plants: A review of imaging technologies,”10.1016/j.rser.2022.112353 ↗
13. “Robust scheduling and routing for collaborative human/Unmanned aerial vehicle surveillance missions,”
14. “Unmanned aerial vehicle integrated real time kinematic in infrared inspection of photovoltaic panels,”10.1016/j.measurement.2021.110536 ↗
15. “Aerial infrared thermography for low-cost and fast fault detection in utility-scale PV power plants,”10.1016/j.solener.2020.09.066 ↗
16. “Survey on PV Modules’ Common Faults after an O&M Flight Extensive Campaign over Different Plants in Italy,”10.1109/JPHOTOV.2017.2674977 ↗
17. “Faults and infrared thermographic diagnosis in operating c-Si photovoltaic modules: A review of research and future challenges,”10.1016/j.rser.2016.04.079 ↗
18. “Visible defects detection based on UAV-based inspection in large-scale photovoltaic systems,”10.1049/iet-rpg.2017.0001 ↗
19. “Fault diagnosis of photovoltaic modules through image processing and Canny edge detection on field thermographic measurements,”10.1080/14786451.2013.826223 ↗
20. “PV power plant inspection by UAS: Correlation between altitude and detection of defects on PV modules,”
21. “Opportunities and Challenges of Machinery Intelligent Fault Diagnosis in Big Data Era,”10.3901/JME.2018.05.094 ↗
22. “Enhancing photovoltaic module fault diagnosis: Leveraging unmanned aerial vehicles and autoencoders in machine learning,”
23. “A fault diagnosis method for cracks of photovoltaic modules based on calculation of equivalent circuit model parameters,”10.1016/j.solener.2024.112970 ↗
24. “Online Fault Diagnosis, Classification, and Localization in Photovoltaic Systems,”10.1109/TIM.2024.3379087 ↗
25. “Fault diagnosis of photovoltaic strings by using machine learning-based stacking classifier,”10.1049/rpg2.12755 ↗
26. A novel few-shot detector for rare defect localization in photovoltaic cells using electroluminescence images10.1016/j.solener.2025.113546 ↗
27. An efficient CNN-based detector for photovoltaic module cells defect detection in electroluminescence images10.1016/j.solener.2023.112245 ↗
28. “An innovative transformer neural network for fault detection and classification for photovoltaic modules,”10.1016/j.enconman.2024.118718 ↗
29. “Diagnosis of photovoltaic faults using digital twin and PSO-optimized shifted window transformer,”10.1016/j.asoc.2023.111092 ↗
30. “Backpropagation Applied to Handwritten Zip Code Recognition,”10.1162/neco.1989.1.4.541 ↗
31. “Attention is all you need,”
32. X. Zhai, “An IMage Is Worth 16 X 16 Words” International Conference on Learning Representations, 2021.
33. “Research on Fault Diagnosis of Photovoltaic Array Based on Random Forest Algorithm,”
34. C. Zhang, Zhang, M., Zhang, S., Jin, D., Zhou, Q., Cai, Z., Zhao, H., Liu, X., and Liu, Z. (2022). Delving Deep into the Generalization of Vision Transformers under Distribution Shifts Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol, pp. 7267–7276, https://doi.org/10.1109/CVPR52688.2022.00713.10.1109/CVPR52688.2022.00713 ↗
35. “DeepSolarEye: Power Loss Prediction and Weakly Supervised Soiling Localization via Fully Convolutional Networks for Solar Panels”10.1109/WACV.2018.00043 ↗
36. “PV Abnormal Shading Detection Based on Convolutional Neural Network”
37. “Intelligent fault pattern recognition of aerial photovoltaic module images based on deep learning technique”
38. “Solar cell surface defect inspection based on multispectral convolutional neural network”10.1007/s10845-018-1458-z ↗
39. “Deep Learning Based Module Defect Analysis for Large-Scale Photovoltaic Farms,”10.1109/TEC.2018.2873358 ↗
40. “Convolutional Neural Network based Automatic Detection of Visible Faults in a Photovoltaic Module,”
41. “Visual fault detection in photovoltaic modules using decision tree algorithms with deep learning features,”
42. “Machine vision based fault diagnosis of photovoltaic modules using lazy learning approach,”10.1016/j.measurement.2022.110786 ↗
43. “Deep learning-based ensemble model for classification of photovoltaic module visual faults,”
44. A. Dosovitskiy, “An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale” 2020.
45. A.H. Zim, A. Ashraf, A. Iqbal, A. Malik, and M. Kuribayashi. (2022) “A Vision Transformer-Based Approach to Bearing Fault Classification via Vibration Signals Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022”, no, pp. 1321–1326. https://doi.org/10.23919/APSIPAASC55919.2022.9980013.10.23919/APSIPAASC55919.2022.9980013 ↗
46. “Adaptive input representations for neural language modeling”