Abstract
The accumulation of dust on PV panels results in reduced energy efficiency and output power from the panels. This work proposes an effective dust detection system using the EfficientNet-B0 convolutional neural network (CNN) model. Channel normalization and data cleaninghave been incorporated to enhance accuracy. The proposed system categorizes panels into clean and dusty categories. The EfficientNet B0 architecture ensures high accuracy (88%) with minimal computational complexity. This method enables hands-on maintenance and reduces the need for manual inspection. The system also ensures enhanced solar energy production.
References
Madeti, Siva Ramakrishna, and S. N. Singh. "Monitoring system for photovoltaic plants: A review." Renewable and Sustainable Energy Reviews 67 (2017): 1180-1207.
Triki-Lahiani, Asma, Afef Bennani-Ben Abdelghani, and Ilhem Slama-Belkhodja. "Fault detection and monitoring systems for photovoltaic installations: A review." Renewable and Sustainable Energy Reviews 82 (2018): 2680-2692.
Dabou, Rachid, Farid Bouchafaa, Amar Hadj Arab, Ahmed Bouraiou, Mohammed Djamel Draou, Ammar Neçaibia, and Mohammed Mostefaoui. "Monitoring and performance analysis of grid connected photovoltaic under different climatic conditions in south Algeria." Energy Conversion and Management 130 (2016): 200-206.
Tchoketch Kebir, Selma, Nawal Cheggaga, Adrian Ilinca, and Sabri Boulouma. "An efficient neural network-based method for diagnosing faults of PV Array." Sustainability 13, no. 11 (2021): 6194.
Mantel, Claire, Frederik Villebro, Gisele Alves dos Reis Benatto, Harsh Rajesh Parikh, Stefan Wendlandt, Kabir Hossain, Peter Poulsen, Sergiu Spataru, Dezso Sera, and Søren Forchhammer. "Machine learning prediction of defect types for electroluminescence images of photovoltaic panels." In Applications of machine learning, vol. 11139, SPIE, 2019, 1113904.
Igathinathane, C., S. Melin, S. Sokhansanj, X. Bi, C. J. Lim, L. O. Pordesimo, and E. P. Columbus. "Machine vision based particle size and size distribution determination of airborne dust particles of wood and bark pellets." Powder Technology 196, no. 2 (2009): 202-212.
Maitre, Julien, Kévin Bouchard, and L. Paul Bédard. "Mineral grains recognition using computer vision and machine learning." Computers & Geosciences 130 (2019): 84-93.
Proietti, Andrea, Massimo Panella, Fabio Leccese, and Emiliano Svezia. "Dust detection and analysis in museum environment based on pattern recognition." Measurement 66 (2015): 62-72.
Saquib, Dania, Mohammed Nabeel Nasser, and Swaroop Ramaswamy. "Image Processing Based Dust Detection and prediction of Power using ANN in PV systems." In 2020 Third International Conference on Smart Systems and Inventive Technology (ICSSIT), IEEE, 2020, 1286-1292.
Mehta, Sachin, Amar P. Azad, Saneem A. Chemmengath, Vikas Raykar, and Shivkumar Kalyanaraman. "Deepsolareye: Power loss prediction and weakly supervised soiling localization via fully convolutional networks for solar panels." In 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE, 2018, 333-342.
Fan, Siyuan, Yu Wang, Shengxian Cao, Bo Zhao, Tianyi Sun, and Peng Liu. "A deep residual neural network identification method for uneven dust accumulation on photovoltaic (PV) panels." Energy 239 (2022): 122302.
Maity, Ritu, Md Shamaun Alam, and Asutosh Pati. "An approach for detection of dust on solar panels using CNN from RGB dust image to predict power loss." In Cognitive Computing in Human Cognition: Perspectives and Applications, Cham: Springer International Publishing, 2020, 41-48.
Zyout, Imad, and Abdulrohman Oatawneh. "Detection of PV solar panel surface defects using transfer learning of the deep convolutional neural networks." In 2020 Advances in Science and Engineering Technology International Conferences (ASET), IEEE, 2020, 1-4.
Khilar, Rashmita, G. Merlin Suba, T. Sathesh Kumar, J. Samson Isaac, Santaji Krishna Shinde, S. Ramya, V. Prabhu, and Kuma Gowwomsa Erko. "Improving the efficiency of photovoltaic panels using machine learning approach." International Journal of Photoenergy 2022, no. 1 (2022): 4921153.
Almalki, Faris A., Amani A. Albraikan, Ben Othman Soufiene, and Obaid Ali. "Utilizing artificial intelligence and lotus effect in an emerging intelligent drone for persevering solar panel efficiency." Wireless Communications and Mobile Computing 2022, no. 1 (2022): 7741535.
Ibrahim, Mariam, Ahmad Alsheikh, Feras M. Awaysheh, and Mohammad Dahman Alshehri. "Machine learning schemes for anomaly detection in solar power plants." Energies 15, no. 3 (2022): 1082.
Yousif, Jabar H., Hussein A. Kazem, Haitham Al-Balushi, Khaled Abuhmaidan, and Reem Al-Badi. "Artificial neural network modelling and experimental evaluation of dust and thermal energy impact on monocrystalline and polycrystalline photovoltaic modules." Energies 15, no. 11 (2022): 4138.