Automated Fault Classification in Solar Panels Using Transfer Learning with EfficientNet and ResNet Models

Abstract

Classifying and detecting faults in solar panels using deep learning methods is crucial to ensuring their efficiency and longevity. In this study, we propose a model that concatenates ResNet and EfficientNet to classify faults in solar panel images. ResNet's advantage lies in its residual connections, which help mitigate the vanishing gradient problem and improve training of deep networks. EfficientNet is known for its scalability and efficiency, providing a balanced trade-off between accuracy and computational cost by optimizing network depth, width, and resolution. Together, these models enhance fault classification accuracy while maintaining efficiency. To evaluate the performance of the proposed model, experimental studies were conducted using a solar panel dataset with six classes: bird-drops, covered snow, dusty, clean, electrical and physical damage on the surfaces of solar panels. The results demonstrated that the ResNet101 + EfficientNetB1 concatenation achieved superior performance, with an accuracy of 87.55%, F1-score of 88.13%, recall of 88.75%, and precision of 87.92%. This concatenation provided significant improvements in fault classification metrics compared to individual models.

Keywords

• Solar panel
• Transfer learning
• EfficientNet
• ResNet
• Fault classification

References

1. [1] D. Korkmaz and H. Acikgoz, “An efficient fault classification method in solar photovoltaic modules using transfer learning and multi-scale convolutional neural network,” Eng. Appl. Artif. Intell., vol. 113, no. April, p. 104959, 2022.
2. [2] H. Acikgoz, “A novel approach based on integration of convolutional neural networks and deep feature selection for short-term solar radiation forecasting,” Appl. Energy, vol. 305, no. June 2021, p. 117912, 2022.
3. [3] T. Z. Ang, M. Salem, M. Kamarol, H. S. Das, M. A. Nazari, and N. Prabaharan, “A comprehensive study of renewable energy sources: Classifications, challenges and suggestions,” Energy Strateg. Rev., vol. 43, no. November 2021, p. 100939, 2022.
4. [4] B. Li, C. Delpha, D. Diallo, and A. Migan-Dubois, “Application of Artificial Neural Networks to photovoltaic fault detection and diagnosis: A review,” Renew. Sustain. Energy Rev., vol. 138, no. October 2020, 2021.
5. [5] A. Rico Espinosa, M. Bressan, and L. F. Giraldo, “Failure signature classification in solar photovoltaic plants using RGB images and convolutional neural networks,” Renew. Energy, vol. 162, pp. 249–256, 2020.
6. [6] M. Le, L. Van Su, N. Dang Khoa, V. D. Dao, V. Ngoc Hung, and V. Hong Ha Thi, “Remote anomaly detection and classification of solar photovoltaic modules based on deep neural network,” Sustain. Energy Technol. Assessments, vol. 48, no. June, p. 101545, 2021.
7. [7] C. Haydaroğlu, H. Kılıç, and B. Gümüş, “Performance Analysis and Comparison of Performance Ratio of Solar Power Plant,” Turkish J. Electr. Power Energy Syst., vol. 4, pp. 190–199, 2024.
8. [8] H. KILIC, M. YILMAZ, and B. GUMUS, “Fault Detection in Photovoltaic Arrays: a Robust Regularized Machine Learning Approach,” Dyna, vol. 95, no. 1, pp. 622–628, 2020.

9. [9] K. Osmani, A. Haddad, T. Lemenand, B. Castanier, M. Alkhedher, and M. Ramadan, “A critical review of PV systems’ faults with the relevant detection methods,” Energy Nexus, vol. 12, no. September, p. 100257, 2023.
10. [10] G. R. Venkatakrishnan et al., “Detection, location, and diagnosis of different faults in large solar PV system—a review,” Int. J. Low-Carbon Technol., vol. 18, no. 1, pp. 659–674, 2023.
11. [11] Z. B. Duranay, “Fault Detection in Solar Energy Systems: A Deep Learning Approach,” Electron., vol. 12, no. 21, 2023.
12. [12] A. Mahmud, M. S. R. Shishir, R. Hasan, and M. Rahman, “A comprehensive study for solar panel fault detection using VGG16 and VGG19 convolutional neural networks,” 2023 26th Int. Conf. Comput. Inf. Technol. ICCIT 2023, pp. 1–6, 2023.
13. [13] M. M. Taye, “Understanding of Machine Learning with Deep Learning: Architectures, Workflow, Applications and Future Directions,” Computers, vol. 12, no. 5, 2023.
14. [14] S. H. Han, T. Rahim, and S. Y. Shin, “Detection of faults in solar panels using deep learning,” 2021 Int. Conf. Electron. Information, Commun. ICEIC 2021, pp. 2–5, 2021.
15. [15] W. Tang, Q. Yang, K. Xiong, and W. Yan, “Deep learning based automatic defect identification of photovoltaic module using electroluminescence images,” Sol. Energy, vol. 201, no. November 2019, pp. 453–460, 2020.
16. [16] S. Naveen Venkatesh and V. Sugumaran, “Fault Detection in aerial images of photovoltaic modules based on Deep learning,” IOP Conf. Ser. Mater. Sci. Eng., vol. 1012, no. 1, p. 012030, 2021.
17. [17] G. S. Eldeghady, H. A. Kamal, and M. A. M. Hassan, “Fault diagnosis for PV system using a deep learning optimized via PSO heuristic combination technique,” Electr. Eng., vol. 105, no. 4, pp. 2287–2301, 2023.
18. [18] R. H. Fonseca Alves, G. A. de Deus Júnior, E. G. Marra, and R. P. Lemos, “Automatic fault classification in photovoltaic modules using Convolutional Neural Networks,” Renew. Energy, vol. 179, pp. 502–516, 2021.
19. [19] S. H. Lee, L. C. Yan, and C. S. Yang, “LIRNet: A Lightweight Inception Residual Convolutional Network for Solar Panel Defect Classification,” Energies, vol. 16, no. 5, pp. 1–12, 2023.
20. [20] Afroz, “Solar Panel Images Clean and Faulty Images,” Kaggle, 2023. [Online]. Available: https://www.kaggle.com/datasets/pythonafroz/solar-panel-images. [Accessed: 10-May-2024].
21. [21] A. W. Salehi et al., “A Study of CNN and Transfer Learning in Medical Imaging: Advantages, Challenges, Future Scope,” Sustainability, vol. 15, no. 7, 2023.
22. [22] N. Raza, A. Naseer, M. Tamoor, and K. Zafar, “Alzheimer Disease Classification through Transfer Learning Approach,” Diagnostics, vol. 13, no. 4, 2023.
23. [23] J. Deng, W. Dong, R. Socher, L.-J. Li, Kai Li, and Li Fei-Fei, “ImageNet: A large-scale hierarchical image database,” 2009 IEEE Conf. Comput. Vis. Pattern Recognit., pp. 248–255, 2010.
24. [24] M. Tan and Q. V. Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” 36th Int. Conf. Mach. Learn. ICML 2019, vol. 2019-June, pp. 10691–10700, 2019.
25. [25] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016, vol. 2016-Decem, pp. 770–778.
26. [26] B. Baheti, S. Innani, S. Gajre, and S. Talbar, “Eff-UNet: A novel architecture for semantic segmentation in unstructured environment,” IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. Work., vol. 2020-June, no. September 2021, pp. 1473–1481, 2020.
27. [27] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L. C. Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 4510–4520, 2018.
28. [28] F. Chollet, “Xception: Deep learning with depthwise separable convolutions,” Proc. - 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR 2017, vol. 2017-Janua, pp. 1800–1807, 2017.
29. [29] H. Fırat, “Classification of White Blood Cells using the Squeeze-Excitation Residual Network,” Bilişim Teknol. Derg., vol. 16, no. 3, pp. 189–205, 2023.
30. [30] B. N. Chaithanya, T. J. Swasthika Jain, A. Usha Ruby, and A. Parveen, “An approach to categorize chest X-ray images using sparse categorical cross entropy,” Indones. J. Electr. Eng. Comput. Sci., vol. 24, no. 3, pp. 1700–1710, 2021.
31. [31] P. Naveen, “Phish: A novel hyper-optimizable activation function,” techrxiv.orgP NaveenAuthorea Prepr. 2023•techrxiv.org, pp. 1–8, 2023.
32. [32] A. Bhat, A. V. Krishna, and S. Acharya, “Analytical Comparison of Classification Models for Raga Identification in Carnatic Classical Instrumental Polyphonic Audio,” SN Comput. Sci., vol. 1, no. 6, pp. 1–9, 2020.
33. [33] H. Dalianis, “Evaluation Metrics and Evaluation,” Clin. Text Min., no. 1967, pp. 45–53, 2018.
34. [34] S. A. Hicks et al., “On evaluation metrics for medical applications of artificial intelligence,” Sci. Rep., vol. 12, no. 1, pp. 1–9, 2022.
35. [35] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” in 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, 2015.
36. [36] A. G. Howard et al., “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications,” 2017.
37. [37] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” Proc. - 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR 2017, vol. 2017-Janua, pp. 2261–2269, 2017.
38. [38] R. Akınca, H. Fırat, and M. E. Asker, “Transfer Öğrenme Tabanlı ResNet Modeli Kullanılarak Güneş Panellerindeki Hataların Tespiti,” Dicle Üniversitesi 2.Uluslararası Fen Bilim. Lisansüstü Araştırmalar Sempozyumu, pp. 27–30, 2024.