Diagnosis of External Faults in Photovoltaic Systems based on a Deep Learning approach
Main Article Content
Abstract
Due to the growing global demand for electricity energy, photovoltaic systems are becoming increasingly important as a continuous and environmentally friendly alternative. They ensure the continuity of electrical production in a healthy and sustainable manner. To ensure the efficiency and optimal performance of these systems, an effective diagnostic model is urgently needed to classify faulty and working solar cells. In recent years, deep learning methods have been used to analyse and process images, providing new insights and guidance in the field of fault diagnosis in PV systems. This research proposes a comparative study of the deep learning models ResNet50, VGG-19, and AlexNet to test their effectiveness in analysing and classifying defective solar cells from non-defective cells using EL images.
Article Details
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
-
Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
-
ShareAlike — If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
References
Bedrich, K. G., Bliss, M., Betts, T. R. & Gottschalg, R, (2017). Electroluminescence imaging of PV devices: Camera calibration and image correction. 2017 IEEE 44th Photovolt. Spec. Conf. PVSC 2017 3254-3255 doi:10.1109/PVSC.2017.8366325.
Berghout, T. et al. (2021). Machine learning-based condition monitoring for PV systems: State of the art and future prospects. Energies 14, 1-24
Demirci, M. Y., Besli, N. & Gumuscu, A, (2021). Efficient deep feature extraction and classification for identifying defective photovoltaic module cells in Electroluminescence images. Expert Syst. Appl. 175,.
Fuyuki, T., Kondo, H., Yamazaki, T., Takahashi, Y. & Uraoka, Y, (2005). Photographic surveying of minority carrier diffusion length in polycrystalline silicon solar cells by electroluminescence. Appl. Phys. Lett. 86, 1-3.
Gonzalez, T. F. Handbook of approximation algorithms and metaheuristics. Handb. Approx. Algorithms Metaheuristics 1-1432 doi:10.1201/9781420010749.
Kang, D. & Cha, Y. J, (2021). Autonomous UAVs for Structural Health Monitoring Using Deep Learning and an Ultrasonic Beacon System with Geo-Tagging. Comput. Civ. Infrastruct. Eng. 33, 885-902 (2018).
Mantel, C. et al. (2018). Correcting for Perspective Distortion in Electroluminescence Images of Photovoltaic Panels. IEEE 7th World Conf. Photovolt. Energy Conversion, WCPEC 2018 - A Jt. Conf. 45th IEEE PVSC, 28th PVSEC 34th EU PVSEC 433-437 doi:10.1109/PVSC.2018.8547724.
Masci, J., Meier, U., Ciresan, D., Schmidhuber, J. & Fricout, G. (2012). Steel defect classification with Max-Pooling Convolutional Neural Networks. Proc. Int. Jt. Conf. Neural Networks 10-15 doi:10.1109/IJCNN.2012.6252468.
Mehta, S., Azad, A. P, (2018) Chemmengath, S. A., Raykar, V. & Kalyanaraman, S. (2018). DeepSolarEye: Power Loss Prediction and Weakly Supervised Soiling Localization via Fully Convolutional Networks for Solar Panels. Proc. -IEEE Winter Conf. Appl. Comput. Vision, WACV 2018 2018-Janua, 333-342.
Owen-Bellini, M. et al. (2020). Methods for in Situ Electroluminescence Imaging of Photovoltaic Modules under Varying Environmental Conditions. IEEE J. Photovoltaics 10, 1254-1261.
Rahmouni, D., Benbouzid, M., Mouss, M.D. & Mouss, L.H. (2023). Efficient Diagnosis of Photovoltaic Cell Degradation Based on Deep Learning Using Drone Thermal Imagery. Int. J. Energy Convers. 11, 153-169.
Rahmouni, D., Mouss, M.D., Mouss, L.H., Benbouzid, M. (2023). Enhancing Photovoltaic Module Reliability: A Comparative study of Deep Learning Models for Failure Diagnosis Using Electroluminescence Images. first Int. Conf. Electr. Eng. Adv. Technol. ICEEAT23 979-8-3503.
Tsai, D. M., Wu, S. C. & Li, W. C, (2012). Defect detection of solar cells in electroluminescence images using Fourier image reconstruction. Sol. Energy Mater. Sol. Cells 99, 250-262.
Victor, A. (2007). ResNet-50 vs VGG-19 vs training from scratch: a comparative analysis of pneumonia segmentation and classification from chest X-ray images. Proc. Glob. Transitions Proceeding.