Detection and Identification of Degradation Root Causes in a Photovoltaic Cell Based on Physical Modeling and Deep Learning
Source abstract
Abstract
Photovoltaic (PV) systems are key renewable energy sources due to their ease of implementation, scalability, and global solar availability. Enhancing their lifespan and performance is vital for wider adoption. Identifying degradation root causes is essential for improving PV design and maintenance, thus extending lifespan. This paper proposes a hybrid fault diagnosis method combining a bond graph-based PV cell model with empirical degradation models to simulate faults, and a deep learning approach for root-cause detection. The experimentally validated model simulates degradation effects on measurable variables (voltage, current, ambient, and cell temperatures). The resulting dataset trains an Optimized Feed-Forward Neural Network (OFFNN), achieving 75.43% accuracy in multi-class classification, which effectively identifies degradation processes.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Photovoltaic System Optimization Techniques · Industrial Vision Systems and Defect Detection · Fault Detection and Control Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Aix-Marseille University, Université de Toulon, CNRS, IM2NP, 13397 Marseille, France
Electrical Electronics Engineering Department, Ankara Medipol University, 06800 Ankara, Türkiye
Faculty of Engineering, City University, Tripoli 1300, Lebanon
LaRGES-CRSI, Faculty of Engineering, Lebanese University, Tripoli 1300, Lebanon
References (35)
Show source-provided references
1. Fault diagnosis of photovoltaic panels using full I–V characteristics and machine learning techniques10.1016/j.enconman.2021.114785 ↗
2. Fault diagnosis model for photovoltaic array using a dual-channels convolutional neural network with a feature selection structure10.1016/j.enconman.2021.114777 ↗
3. Methods of photovoltaic fault detection and classification: A review10.1016/j.egyr.2022.04.043 ↗
4. Application of Artificial Neural Networks to photovoltaic fault detection and diagnosis: A review10.1016/j.rser.2020.110512 ↗
5. Multivariate feature extraction based supervised machine learning for fault detection and diagnosis in photovoltaic systems10.1016/j.ejcon.2020.03.004 ↗
6. Sopori, B., Basnyat, P., Devayajanam, S., Shet, S., Mehta, V., Binns, J., and Appel, J. (2012, January 3–8). Understanding light-induced degradation of c-Si solar cells. Proceedings of the 38th IEEE Photovoltaic Specialists Conference, Austin, TX, USA.10.1109/PVSC.2012.6317798 ↗
7. Damiani, B., Nakayashiki, K., Kim, D.S., Yelundur, V., Ostapenko, S., Tarasov, I., and Rohatgi, A. (2003, January 11–18). Light induced degradation in promising multi-crystalline silicon materials for solar cell fabrication. Proceedings of the 3rd World Conference on Photovoltaic Energy Conversion, Osaka, Japan.
8. Control algorithms applied to active solar tracking systems: A review10.1016/j.solener.2020.10.071 ↗
9. Logerais, P.-O., Riou, O., Doumane, R., Balistrou, M., and Durastanti, J.-F. (2013, January 13–15). Étude par simulation de l’influence du vieillissement et des conditions climatiques sur la production électrique d’un module photovoltaïque. Proceedings of the JiTH 2013, Marrakesh, Morocco.
10. Factors that affect the EVA encapsulant discoloration rate upon accelerated exposure10.1016/0927-0248(95)00128-X ↗
11. Braisaz, B., Duchayne, C., Van Iseghem, M., and Khalid, R. (2014, January 22–26). PV aging model applied to several meteorological conditions. Proceedings of the 29th European Photovoltaic Solar Energy Conference and Exhibition (EU PVSEC 2014), Amsterdam, The Netherlands.
12. Effect of materials and design on PV cracking under mechanical loading10.1016/j.renene.2022.09.009 ↗
13. Karnopp, D., Margolis, D., and Rosenberg, R. (2012). System Dynamics: Modeling, Simulation, and Control of Mechatronic Systems, John Wiley and Sons. [5th ed.].10.1002/9781118152812 ↗
14. Kononenko, I. (1994). Estimating attributes: Analysis and extensions of RELIEF. Lecture Notes in Computer Science, Springer.10.1007/3-540-57868-4_57 ↗
15. Deep learning in neural networks: An overview10.1016/j.neunet.2014.09.003 ↗
16. A comparison of different one-diode models for the representation of I–V characteristic of a PV cell10.1016/j.rser.2014.01.027 ↗
17. Case study of a grid connected with a battery photovoltaic system: V-trough concentration vs. single-axis tracking10.1016/j.enconman.2012.05.029 ↗
18. Submerged photovoltaic solar panel: SP210.1016/j.renene.2009.10.023 ↗
19. Comparative analysis of monofacial and bifacial photovoltaic modules for floating power plants10.1016/j.apenergy.2020.116084 ↗
20. Le, P.-T., Tsai, H.-L., and Le, P.-L. (2023). Development and Performance Evaluation of Photovoltaic (PV) Evaluation and Fault Detection System Using Hardware-in-the-Loop Simulation for PV Applications. Micromachines, 14.10.3390/mi14030674 ↗
21. A multi-physics and multi-scale numerical approach to microcracking and power-loss in photovoltaic modules10.1016/j.compstruct.2012.08.014 ↗
22. Degradation and fault diagnosis of photovoltaic cells using impedance spectroscopy10.1016/j.solmat.2019.01.040 ↗
23. A Review of Photovoltaic Module Failure and Degradation Mechanisms: Causes and Detection Techniques10.3390/solar4010003 ↗
24. A systematic study of the class imbalance problem in convolutional neural networks10.1016/j.neunet.2018.07.011 ↗
25. A temporal-based SVM approach for the detection and identification of pollutant gases in a gas mixture10.1007/s10489-021-02761-0 ↗
26. Ioffe, S., and Szegedy, C. (2015, January 6–11). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. Proceedings of the 32nd International Conference on Machine Learning (ICML’15), Lille, France.
27. Benchmarking relief-based feature selection methods for bioinformatics data mining10.1016/j.jbi.2018.07.015 ↗
28. Regularized Evolution for Image Classifier Architecture Search
29. Montavon, G., Orr, G.B., and Müller, K.-R. (2012). Early Stopping—But When?. Neural Networks: Tricks of the Trade, Springer. [2nd ed.].10.1007/978-3-642-35289-8 ↗
30. Lundberg, S.M., and Lee, S.-I. (2017, January 4–9). A unified approach to interpreting model predictions. Proceedings of the 31st International Conference on Neural Information Processing Systems (NeurIPS), Long Beach, CA, USA.
31. Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13–17). “Why should I trust you?”: Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939778 ↗
32. A survey of methods for explaining black box models
33. Amiri, A.F., Kichou, S., Oudira, H., Chouder, A., and Silvestre, S. (2024). Fault Detection and Diagnosis of a Photovoltaic System Based on Deep Learning Using the Combination of a Convolutional Neural Network (CNN) and Bidirectional Gated Recurrent Unit (Bi-GRU). Sustainability, 16.10.3390/su16031012 ↗
34. Lodhi, E., Wang, F.-Y., Xiong, G., Zhu, L., Tamir, T.S., Rehman, W.U., and Khan, M.A. (2023). A Novel Deep Stack-Based Ensemble Learning Approach for Fault Detection and Classification in Photovoltaic Arrays. Remote Sens., 15.10.3390/rs15051277 ↗
35. Boubaker, S., Kamel, S., Ghazouani, N., and Mellit, A. (2023). Assessment of Machine and Deep Learning Approaches for Fault Diagnosis in Photovoltaic Systems Using Infrared Thermography. Remote Sens., 15.10.3390/rs15061686 ↗