Abstract

The expansion of installed capacity in photovoltaic (PV) generation systems requires automated methods for detecting faults in their constituent cells. This paper proposes a hybrid convolutional neural network (HCNN) model for fault detection in electroluminescence (EL) images of PV panels. The model utilizes the ResNet50 and VGG16 topologies for feature extraction and the support vector machine (SVM) for detecting defective cells. Fine-tuning the model’s hyperparameters through a genetic algorithm resulted in accuracies of 98.17% and 99.67% in classification experiments conducted with two public datasets. The challenges posed by the heterogeneity of these datasets in model training were addressed through data augmentation techniques and contrast enhancement. The results highlight the effectiveness of the HCNN, demonstrating its potential as a robust solution for the automated detection of defects in PV cells, which is essential for maintaining optimal energy conversion efficiency and extending the operational lifespan of these systems.

References

• A. K. Acharya, P. K. Sahu, and S. R. Jena. Deep neural network based approach for detection of defective solar cell. Materials Today: Proceedings, 39:2009–2014, 2021.
• M. W. Akram, G. Li, Y. Jin, X. Chen, C. Zhu, and A. Ahmad. Automatic detection of photovoltaic module defects in infrared images with isolated and develop-model transfer deep learning. Solar Energy, 198:175–186, 2020.
• G. Balasubramani, V. Thangavelu, M. Chinnusamy, L. Mihet- Popa, U. Subramaniam, and S. Padmanaban. Infrared thermography based defects testing of solar photovoltaic panel with fuzzy rule-based evaluation. Energies, 13(6):1343, 2020.
• C. Buerhop-Lutz, S. Deitsch, A. Maier, F. Gallwitz, S. Berger, B. Dol, J. Hauch, C. Camus, and C. J. Brabec. A benchmark for visual identification of defective solar cells in electroluminescence imagery. In European PV Solar Energy Conference and Exhibition (EU PVSEC), 2018.
• Y. Chaibi, M. Malvoni, A. Chouder, M. Boussetta, and M. Salhi. Simple and efficient approach to detect and diagnose electrical faults and partial shading in photovoltaic systems. Energy Conversion and Management, 196:330–343, 2019.
• A. Singh Chaudhary and D. K. Chaturvedi. Analyzing defects of solar panels under natural atmospheric conditions with thermal image processing. International Journal of Image, Graphics and Signal Processing, 10(6):10–21, 2018.
• J. Cohen. Nominal scale agreement with provision for scaled disagreement or partial credit. Psychol. Bull., 70:213, Oct 1968.
• C. Cortes and V. Vapnik. Support-vector networks. Machine Learning,, 20(3):273–297, 1995.
• T. Homem de Mello and G. Bayraksan. Monte carlo sampling-based methods for stochastic optimization. Surveys in Operations Research and Management Science, 19(1):56– 85, 2014.
• S. Deitsch, C. Buerhop-Lutz, E. Sovetkin, A. Steland, A. Maier, F. Gallwitz, and C. Riess. Segmentation of photovoltaic module cells in uncalibrated electroluminescence images. Machine Vision and Applications, 32(4):84, May 2021.
• S. Deitsch, V. Christlein, S. Berger, C. Buerhop-Lutz, A. Maier, F. Gallwitz, and C. Riess. Automatic classification of defective photovoltaic module cells in electroluminescence images. Solar Energy, 185:455–468, jun 2019.
• M. Y. Demirci, N. Bes¸li, and A. G¨um¨us¸c¸ ¨u. Efficient deep feature extraction and classification for identifying defective photovoltaic module cells in electroluminescence images. Expert Systems with Applications, 175:114810, 2021.
• Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei. Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 248–255, 2009.
• A. E. Eiben and J. E. Smith. Introduction to Evolutionary Computing. Springer Publishing Company, 2 edition, 2015.
• A. Et-taleby, Y. Chaibi, M. Boussetta, A. Allouhi, and M. Benslimane. A novel fault detection technique for pv systems based on the k-means algorithm, coded wireless orthogonal frequency division multiplexing and thermal image processing techniques. Solar Energy, 237:365–376, 2022.
• T. Fan, S. Tao, X. Xiangying, L. Hu, and Z. Na. Automatic micro-crack detection of polycrystalline solar cells in industrial scene. IEEE Access, 10:16269–16282, 2022.
• J. L. Fleiss. The equivalence of weighted kappa and the intraclass correlation coefficient as measures of reliability. Educational and Psychological Measurement, 33(3):613–619, 1973.
• M. A. Islam, M. Hasanuzzaman, and N. A. Rahim. A comparative investigation on in-situ and laboratory standard test of the potential induced degradation of crystalline silicon photovoltaic modules. Renewable Energy, 127:102–113, 2018.
• Z. A. Jaffery, A. K. Dubey, Irshad, and A. Haque. Scheme for predictive fault diagnosis in photo-voltaic modules using thermal imaging. Infrared Physics & Technology, 83:182–187, 2017.
• U. Jahn, M. Herz, D. Parlevliet, M. Paggi, I. Tsanakas, J. Stein, K. Berger, S. Ranta, R. French, M. Richter, and et al. Review on infrared and electroluminescence imaging for pv field applications. techreport, International Energy Agency, Institute for Solar Energy Research Hamelin, Emmerthal (ISFH), Germany, March 2018. ISBN 978-3-906042- 53-4.
• G. Koch, R. Zemel, and R. Salakhutdinov. Siamese neural networks for one-shot image recognition. In Proceedings of the 32nd International Conference on Machine Learning, volume 37. Journal of Machine Learning Research, 2015.
• R. Koha. A study of cross-validation and bootstrap for accuracy estimation and model selection. In International Joint Conference on Artificial Intelligence IJCAI, 1995.
• S. R. Madeti and S.N. Singh. A comprehensive study on different types of faults and detection techniques for solar photovoltaic system. Solar Energy, 158:161–185, 2017.
• S. R. Madeti and S.N. Singh. Monitoring system for photovoltaic plants: A review. Renewable and Sustainable Energy Reviews, 67:1180–1207, 2017.
• M. L. McHugh. Interrater reliability: the kappa statistic. Biochem. Med. (Zagreb), 22(3):276–282, 2012.
• Z. Meng, S. Xu, L. Wang, Y. Gong, X. Zhang, and Y. Zhao. Defect object detection algorithm for electroluminescence image defects of photovoltaic modules based on deep learning. Energy Science and Engineering, 10(3):800–813, 2022.
• K. A. K. Niazi,W. Akhtar, H. A. Khan, Y. Yang, and S. Athar. Hotspot diagnosis for solar photovoltaic modules using a naive bayes classifier. Solar Energy, 190(34-43), 2019.
• G. Sombrio, P. L. Franzen, R. L. Maltez, L. G. Matos, M. B. Pereira, and H. Boudinov. Photoluminescence from sinxoy films deposited by reactive sputtering. Journal of Physics D: Applied Physics, 46(23):235106, May 2013.
• W. Tang, Q. Yang, X. Hu, and W. Yan. Convolution neural network based polycrystalline silicon photovoltaic cell linear defect diagnosis using electroluminescence images. Expert Systems with Applications, 202:117087, 2022.
• A. Tsanakas, L. Ha, and C. Buerhop. Faults and infrared thermographic diagnosis in operating c-si photovoltaic modules: A review of research and future challenges. Renewable and Sustainable Energy Reviews, 62:695–709, 2016.
• S. van der Walt, J. L. Sch¨onberger, J. Nunez-Iglesias, F. Boulogne, J. D. Warner, N. Yager, E. Gouillart, T. Yu, and scikit-image contributors. scikit-image: image processing in python. PeerJ, 2014.
• P. Vieira, O. Sousa, D. Magalh˜aes, R. Rabˆelo, and R. Silva. Detecting pulmonary diseases using deep features in x-ray images. Pattern Recognition, 119:108081, 2021.
• P. A. Vieira, D. M. V. Magalh˜aes, A. O. Carvalho-Filho, R. M. S. Veras, R. A. L. Rabˆelo, and R. R. V. Silva. Classification of covid-19 in x-ray images with genetic fine-tuning. Computers and Electrical Engineering, 96:107467, 2021.