Deep learning-based ensemble model for classification of photovoltaic module visual faults

References

• Aghaei, M., S. Leva, and F. Grimaccia. 2017. PV power plant inspection by image mosaicing techniques for IR real-time images. 2017 IEEE 44th Photovoltaic Specialist Conference, PVSC, Portland, OR, USA 2017: 1–6. doi:10.1109/PVSC.2017.8366734.
   Google Scholar
• Alawad, A. M., F. D. A. Rahman, O. O. Khalifa, and N. A. Malek. 2018. Fuzzy logic based edge detection method for image processing. International Journal of Electrical and Computer Engineering 8 (3):1863–69. doi:10.11591/ijece.v8i3.pp1863-1869.
   Google Scholar
• Chandel, S. S., M. Nagaraju Naik, V. Sharma, and R. Chandel. 2015. Degradation analysis of 28 year field exposed mono-c-Si photovoltaic modules of a direct coupled solar water pumping system in western Himalayan region of India. Renewable Energy 78:193–202. Elsevier Ltd: 193–202. doi:10.1016/j.renene.2015.01.015.
   Web of Science ®Google Scholar
• Chollet, F. 2017. Xception: Deep learning with depthwise separable convolutions. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 2017, 1800–07, January. doi:10.1109/CVPR.2017.195.
   Google Scholar
• Dolara, A., G. C. Lazaroiu, S. Leva, G. Manzolini, and L. Votta. 2016. Snail trails and cell microcrack impact on PV module maximum power and energy production. IEEE Journal of Photovoltaics 6 (5):1269–77. doi:10.1109/JPHOTOV.2016.2576682.
   Web of Science ®Google Scholar
• Gnetchejo, P. J., S. N. Essiane, P. Ele, A. Dadjé, and Z. Chen. 2021. Faults diagnosis in a photovoltaic system based on multivariate statistical analysis. Energy Sources, Part A: Recovery, Utilization and Environmental Effects Taylor & Francis, 1–22. doi:10.1080/15567036.2021.1919792.
   Web of Science ®Google Scholar
• Grimaccia, F., S. Leva, and A. Niccolai. 2017. PV plant digital mapping for modules’ defects detection by unmanned aerial vehicles. IET Renewable Power Generation 11 (10):1221–28. doi:10.1049/iet-rpg.2016.1041.
   Web of Science ®Google Scholar
• Grimaccia, F., S. Leva, A. Niccolai, and G. Cantoro. 2018. Assessment of PV plant monitoring system by means of unmanned aerial vehicles. Proceedings - 2018 IEEE International Conference on Environment and Electrical Engineering and 2018 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2018, Palermo, Italy. IEEE: 1–6. doi:10.1109/EEEIC.2018.8494532.
   Google Scholar
• Han, H., X. Dong, B. Li, H. Yan, P. J. Verlinden, J. Liu, J. Huang, Z. Liang, and H. Shen. 2018. Degradation analysis of crystalline silicon photovoltaic modules exposed over 30 years in hot-humid climate in China. Solar Energy 170 (December 2017):510–19. Elsevier. doi:10.1016/j.solener.2018.05.027.
   Web of Science ®Google Scholar
• He, K., X. Zhang, S. Ren, and J. Sun. 2016. Deep residual learning for image recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA. 2016Dec: 770–78. doi:10.1109/CVPR.2016.90.
   Google Scholar
• IEA-PVPS T13-10. 2018. Review on infrared (IR) and electroluminescence (EL) imaging for photovoltaic field applications.
   Google Scholar
• Joshuva, A., and V. Sugumaran. 2020. A lazy learning approach for condition monitoring of wind turbine blade using vibration signals and histogram features. Measurement: Journal of the International Measurement Confederation 152:107295. Elsevier Ltd: 107295. doi:10.1016/j.measurement.2019.107295.
   Web of Science ®Google Scholar
• Kim, K. W., H. G. Hong, G. P. Nam, and K. R. Park. 2017. A study of deep CNN-based classification of open and closed eyes using a visible light camera sensor. Sensors (Switzerland) 17 (7). doi:10.3390/s17071534.
   Google Scholar
• Köntges, M., S. Kurtz, C. Packard, U. Jahn, K. A. Berger, K. Kato, T. Friesen, H. Liu, and M. Van Iseghem 2014a. IEA-PVPST13-01 2014 review of failures of photovoltaic modules final.
   Google Scholar
• Köntges, M., S. Kurtz, C. E. Packard, U. Jahn, K. Berger, K. Kato, T. Friesen, H. Liu, and M. Van Iseghem. 2014b. Review of failures of photovoltaic modules. IEA-Photovoltaic Power Systems Programme 978-3-906042-16–9.
   Google Scholar
• Krizhevsky, A., I. Sutskever, and G. E. Hinton. 2017. ImageNet classification with deep convolutional neural networks. Communications of the ACM 60 (6):84–90. doi:10.1145/3065386.
   Web of Science ®Google Scholar
• Li, X., Q. Yang, Z. Chen, X. Luo, and W. Yan. 2017. Visible defects detection based on UAV-based inspection in large-scale photovoltaic systems. IET Renewable Power Generation 11 (10):1234–44. doi:10.1049/iet-rpg.2017.0001.
   Web of Science ®Google Scholar
• Li, X., Q. Yang, Z. Lou, and W. Yan. 2019. Deep learning based module defect analysis for large-scale photovoltaic farms. IEEE Transactions on Energy Conversion 34 (1):520–29. IEEE. doi:10.1109/TEC.2018.2873358.
   Web of Science ®Google Scholar
• Lu, X., P. Lin, S. Cheng, Y. Lin, Z. Chen, L. Wu, and Q. Zheng. 2019. Fault diagnosis for photovoltaic array based on convolutional neural network and electrical time series graph. Energy Conversion and Management 196 (June):950–65. Elsevier. doi:10.1016/j.enconman.2019.06.062.
   Web of Science ®Google Scholar
• Naveen Venkatesh, S, and V. Sugumaran. 2020. Fault diagnosis of visual faults in photovoltaic modules: A review. International Journal of Green Energy 18(1). Taylor & Francis 1–14. doi:10.1080/15435075.2020.1825443.
   Web of Science ®Google Scholar
• Naveen Venkatesh, S., and V. Sugumaran. 2021. Fault detection in aerial images of photovoltaic modules based on deep learning. IOP Conference Series: Materials Science and Engineering 1012 (1):012030. doi:10.1088/1757-899x/1012/1/012030.
   Google Scholar
• Naveen Venkatesh, S., and V. Sugumaran. 2022. Machine vision based fault diagnosis of photovoltaic modules using lazy learning approach. Measurement: Journal of the International Measurement Confederation 191 (October 2021):110786. Elsevier Ltd: 110786. doi:10.1016/j.measurement.2022.110786.
   Web of Science ®Google Scholar
• Niccolai, A., A. Gandelli, F. Grimaccia, R. Zich, and S. Leva. 2019. Overview on photovoltaic inspections procedure by means of unmanned aerial vehicles. 2019 IEEE Milan PowerTech, Milan, Italy. IEEE: 1–6. doi:10.1109/ptc.2019.8810987.
   Google Scholar
• Ozbek, A., A. Yildirim, and M. Bilgili. 2021. Deep learning approach for one-hour ahead forecasting of energy production in a solar-PV plant. Energy Sources, Part A: Recovery, Utilization and Environmental Effects Taylor & Francis, 1–16. doi:10.1080/15567036.2021.1924316.
   Web of Science ®Google Scholar
• Pierdicca, R., E. S. Malinverni, F. Piccinini, M. Paolanti, A. Felicetti, and P. Zingaretti. 2018. Deep convolutional neural network for automatic detection of damaged photovoltaic cells. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives 42 (2):893–900. doi:10.5194/isprs-archives-XLII-2-893-2018.
   Google Scholar
• Sánchez-Friera, P., M. Piliougine, J. Peláez, J. Carretero, and M. S. De Cardona. 2011. Analysis of degradation mechanisms of crystalline silicon PV modules after 12 years of operation in Southern Europe. Progress in Photovoltaics: Research and Applications 19 (6):658–66. doi:10.1002/pip.1083.
   Web of Science ®Google Scholar
• Simon, M., and E. L. Meyer. 2010. Detection and analysis of hot-spot formation in solar cells. Solar Energy Materials and Solar Cells 94 (2):106–13. Elsevier. doi:10.1016/j.solmat.2009.09.016.
   Web of Science ®Google Scholar
• Simonyan, K., and A. Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, San Diego, CA, USA, 1–14.
   Google Scholar
• Sridharan, N. V., and V. Sugumaran. 2021a. Convolutional neural network based automatic detection of visible faults in a photovoltaic module. Energy Sources, Part A: Recovery, Utilization and Environmental Effects Taylor & Francis, 1–16. doi:10.1080/15567036.2021.1905753.
   Web of Science ®Google Scholar
• Sridharan, N. V., and V. Sugumaran. 2021b. Visual fault detection in photovoltaic modules using decision tree algorithms with deep learning features. Energy Sources, Part A: Recovery, Utilization and Environmental Effects Taylor & Francis, 1–17. doi:10.1080/15567036.2021.2020379.
   Google Scholar
• Srivastava, I., S. Bhat, and A. R. Singh. 2020. Fault diagnosis, service restoration, and data loss mitigation through multi-agent system in a smart power distribution grid. Energy Sources, Part A: Recovery, Utilization and Environmental Effects Taylor & Francis, 1–26. doi:10.1080/15567036.2020.1817190.
   Web of Science ®Google Scholar
• Szegedy, C., W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. 2015. Going deeper with convolutions. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Boston, MA, 7-12 June:1–9. doi:10.1109/CVPR.2015.7298594.
   Google Scholar
• Szegedy, C., V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna. 2016. Rethinking the inception architecture for computer vision. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA. 2016 Dec: 2818–26. doi:10.1109/CVPR.2016.308.
   Google Scholar
• Tsanakas, J. A., and P. N. Botsaris. 2012. An infrared thermographic approach as a hot-spot detection tool for photovoltaic modules using image histogram and line profile analysis. International Journal of Condition Monitoring 2 (1):22–30. doi:10.1784/204764212800028842.
   Google Scholar
• Tsanakas, J. A., L. D. Ha, and F. Al Shakarchi. 2017. Advanced inspection of photovoltaic installations by aerial triangulation and terrestrial georeferencing of thermal/visual imagery. Renewable Energy 102:224–33. Elsevier Ltd. doi:10.1016/j.renene.2016.10.046.
   Web of Science ®Google Scholar
• Venkatesh, S. N., and V. Sugumaran. 2022. A combined approach of convolutional neural networks and machine learning for visual fault classification in photovoltaic modules. Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability 236 (1):148–59. doi:10.1177/1748006X211020305.
   Web of Science ®Google Scholar
• Wen, L., X. Li, and L. Gao. 2019. A transfer convolutional neural network for fault diagnosis based on ResNet-50. In Neural computing and applications, 0123456789. Springer:London. doi:10.1007/s00521-019-04097-w.
   Google Scholar
• Zhang, D., F. Wu, X. Li, X. Luo, J. Wang, W. Yan, Z. Chen, and Q. Yang. 2017. Aerial image analysis based on improved adaptive clustering for photovoltaic module inspection. 2017 International Smart Cities Conference, ISC2, Wuxi, China. 2017. doi: 10.1109/ISC2.2017.8090798.
   Google Scholar