Hybrid Convolutional Neural Network on Fault Detection in Electroluminescence Images of Photovoltaic Cells

Alan Marques da Rocha; Marcelo Marques Simões de Souza; Carlos Alexandre Rolim Fernandes

doi:10.22456/2175-2745.145838

Authors

Alan Marques da Rocha Federal University of Ceará (UFC) https://orcid.org/0000-0002-6446-0263
Marcelo Marques Simões de Souza Federal University of Ceará (UFC) https://orcid.org/0000-0002-7590-9898
Carlos Alexandre Rolim Fernandes Federal University of Ceará (UFC)

DOI:

https://doi.org/10.22456/2175-2745.145838

Keywords:

electroluminescence, hybrid convolutional neural network, evolutionary genetic algorithms, fault detection

Abstract

The expansion of installed capacity in photovoltaic generation systems demands automated methods for fault detection in its constituent cells. This paper proposes a hybrid convolutional neural network model for fault detection in electroluminescence images of photovoltaic panels. The model leverages the convolutional neural networks ResNet50 and VGG16 for feature extraction and the support vector machine classifier to detect faulty cells. Adjusting the model's settings using a genetic algorithm achieved accuracy rates of 98.2% and 99.7% in tests with two public datasets. The challenges that this dataset's heterogeneity imposed on training the model were addressed by data augmentation and contrast enhancement techniques. These results support hybrid convolutional neural networks as a promising solution for automatically detecting defects in photovoltaic cells, which is important for keeping energy conversion efficiency high and extending the lifespan of photovoltaic systems.

Downloads

Download data is not yet available.

References

[1] CHAIBI, Y. et al. Simple and efficient approach to detect and diagnose electrical faults and partial shading in photovoltaic systems. Energy Conversion and Management, v. 196, p. 330–343, 2019.

[2] MADETI, S. R.; SINGH, S. A comprehensive study on different types of faults and detection techniques for solar photovoltaic system. Solar Energy, v. 158, p. 161–185, 2017.

[3] CHAUDHARY, A. S.; CHATURVEDI, D. K. Analyzing defects of solar panels under natural atmospheric conditions with thermal image processing. International Journal of Image, Graphics and Signal Processing, v. 10, n. 6, p. 10–21, 2018.

[4] AKRAM, M. W. et al. Automatic detection of photovoltaic module defects in infrared images with isolated and develop-model transfer deep learning. Solar Energy, v. 198, p. 175–186, 2020.

[5] RIVAI, A. et al. Analysis of photovoltaic string failure and health monitoring with module fault identification. Energies, v. 13, n. 1, 2020. ISSN 1996-1073. Disponível em: ⟨https://www.mdpi.com/1996-1073/13/1/100⟩.

[6] BASNET, B.; CHUN, H.; BANG, J. An intelligent fault detection model for fault detection in photovoltaic systems. Journal of Sensors, Hindawi Limited, v. 2020, 2020. ISSN 1687-7268. Disponível em: ⟨http://dx.doi.org/10.1155/2020/6960328⟩.

[7] TSANAKAS, A.; HA, L.; BUERHOP, C. Faults and infrared thermographic diagnosis in operating c-si photovoltaic modules: A review of research and future challenges. Renewable and Sustainable Energy Reviews, v. 62, p. 695–709, 2016.

[8] JAFFERY, Z. A. et al. Scheme for predictive fault diagnosis in photo-voltaic modules using thermal imaging. Infrared Physics & Technology, v. 83, p. 182–187, 2017.

[9] NIAZI, K. A. K. et al. Hotspot diagnosis for solar photovoltaic modules using a naive bayes classifier. Solar Energy, v. 190, n. 34-43, 2019.

[10] ET-TALEBY, A. et al. 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, v. 237, p. 365–376, 2022.

[11] MADETI, S. R.; SINGH, S. Monitoring system for photovoltaic plants: A review. Renewable and Sustainable Energy Reviews, v. 67, p. 1180–1207, 2017.

[12] BALASUBRAMANI, G. et al. Infrared thermography based defects testing of solar photovoltaic panel with fuzzy rule-based evaluation. Energies, v. 13, n. 6, p. 1343, 2020.

[13] ISLAM, M. A.; HASANUZZAMAN, M.; RAHIM, N. A. A comparative investigation on in-situ and laboratory standard test of the potential induced degradation of crystalline silicon photovoltaic modules. Renewable Energy, v. 127, p. 102–113, 2018.

[14] MENG, Z. et al. Defect object detection algorithm for electroluminescence image defects of photovoltaic modules based on deep learning. Energy Science and Engineering, v. 10, n. 3, p. 800–813, 2022.

[15] JAHN, U. et al. Review on infrared and electroluminescence imaging for PV field applications. Institute for Solar Energy Research Hamelin, Emmerthal (ISFH), Germany, 2018. ISBN 978-3-906042-53-4.

[16] DEITSCH, S. et al. Automatic classification of defective photovoltaic module cells in electroluminescence images. Solar Energy, v. 185, p. 455–468, jun 2019.

[17] BUERHOP-LUTZ, C. et al. A benchmark for visual identification of defective solar cells in electroluminescence imagery. In: European PV Solar Energy Conference and Exhibition (EU PVSEC). [S.l.: s.n.], 2018.

[18] DEITSCH, S. et al. Segmentation of photovoltaic module cells in uncalibrated electroluminescence images. Machine Vision and Applications, v. 32, n. 4, p. 84, May 2021.

[19] HERRAIZ, A. H.; MARUGÁN, A. P.; MÁRQUEZ, F. P. G. Photovoltaic plant condition monitoring using thermal images analysis by convolutional neural network-based structure. Renewable Energy, v. 153, p. 334–348, 2020.

[20] FAN, T. et al. Automatic micro-crack detection of polycrystalline solar cells in industrial scene. IEEE Access, v. 10, p. 16269–16282, 2022.

[21] TANG, W. et al. Convolution neural network based polycrystalline silicon photovoltaic cell linear defect diagnosis using electroluminescence images. Expert Systems with Applications, v. 202, p. 117087, 2022.

[22] HE, K. et al. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). [s.n.], 2016. p. 770–778. Disponível em: ⟨https://arxiv.org/abs/1512.03385⟩.

[23] SIMONYAN, K.; ZISSERMAN, A. Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (ICLR). [s.n.], 2015. Disponível em: ⟨https://arxiv.org/abs/1409.1556⟩.

[24] DEMIRCI, M. Y.; BEŞLI, N.; GÜMÜŞÇÜ, A. Efficient deep feature extraction and classification for identifying defective photovoltaic module cells in electroluminescence images. Expert Systems with Applications, v. 175, p. 114810, 2021.

[25] ACHARYA, A. K.; SAHU, P. K.; JENA, S. R. Deep neural network based approach for detection of defective solar cell. Materials Today Proceedings, v. 39, p. 2009–2014, 2021.

[26] KOCH, G.; ZEMEL, R.; SALAKHUTDINOV, R. Siamese neural networks for one-shot image recognition. In: Proceedings of the 32nd International Conference on Machine Learning. [S.l.]: Journal of Machine Learning Research, 2015. v. 37.

[27] TANG, W. et al. Deep learning based automatic defect identification of photovoltaic module using electroluminescence images. Solar Energy, v. 201, p. 453–460, 2020.

[28] MATHIAS, N. et al. Detection of micro-cracks in electroluminescence images of photovoltaic modules. In: Proceedings of the 3rd International Conference on Advances in Science and Technology (ICAST). [S.l.: s.n.], 2020.

[29] DENG et al. Imagenet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition. [s.l.: s.n.], 2009. p. 248–255.

[30] AKRAM, M. W. et al. CNN based automatic detection of photovoltaic cell defects in electroluminescence images. Energy, v. 189, p. 116319, 2019.

[31] KARIMI, A. M. et al. Feature extraction, supervised and unsupervised machine learning classification of PV cell electroluminescence images. In: 2018 IEEE 7th World Conference on Photovoltaic Energy Conversion (WCPEC). [s.l.: s.n.], 2018. p. 0418–0424.

[32] HARALICK, R. M.; SHANMUGAM, K.; DINSTEIN, I. Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, SMC-3, n. 6, p. 610–621, 1973.

[33] EIBEN, A. E.; SMITH, J. E. Introduction to Evolutionary Computing. 2. ed. [S.l.]: Springer Publishing Company, 2015. ISBN 3662448734.

[34] VIEIRA, P. A. et al. Classification of covid-19 in x-ray images with genetic fine-tuning. Computers and Electrical Engineering, v. 96, p. 107467, 2021.

[35] VIEIRA, P. et al. Detecting pulmonary diseases using deep features in x-ray images. Pattern Recognition, v. 119, p. 108081, 2021.

[36] MELLO, T. H. de; BAYRAKSAN, G. Monte Carlo sampling-based methods for stochastic optimization. Surveys in Operations Research and Management Science, v. 19, n. 1, p. 56–85, 2014.

[37] COHEN, J. Nominal scale agreement with provision for scaled disagreement or partial credit. Psychol. Bull., v. 70, p. 213, Oct. 1968.

[38] CORTES, C.; VAPNIK, V. Support-vector networks. Machine Learning, v. 20, n. 3, p. 273–297, 1995.

[39] WALT, S. van der et al. scikit-image: image processing in python. PeerJ, 2014.

[40] KOHA, R. A study of cross-validation and bootstrap for accuracy estimation and model selection. In: International Joint Conference on Artificial Intelligence IJCAI. [S.l.: s.n.], 1995.

[41] FLEISS, J. L. The equivalence of weighted kappa and the intraclass correlation coefficient as measures of reliability. Educational and Psychological Measurement, v. 33, n. 3, p. 613–619, 1973.

[42] MCHUGH, M. L. Interrater reliability: the kappa statistic. Biochem. Med. (Zagreb), v. 22, n. 3, p. 276–282, 2012.