A Study on the Optimization of Fine-tuning and Dataset for Defect Detection Models in Photovoltaic Modules Images

Taeyun Kim; Byung Chul Yeo

doi:10.7836/kses.2025.45.4.067

All Issue

2025 Vol.45, Issue 4 Preview Page Next Page

Research Article

A Study on the Optimization of Fine-tuning and Dataset for Defect Detection Models in Photovoltaic Modules Images 태양광 모듈 이미지 결함 검출 모델의 미세 조정 및 데이터셋 최적화에 관한 연구

30 August 2025. pp. 67-79

PDF XML

Abstract

Fault diagnosis of photovoltaic (PV) modules is essential for reliable solar energy generation. Previously, defects in solar modules were identified through manual inspection of PV module images; however, these methods are inefficient and prone to errors. To address this issue, deep-learning-based approaches have been explored to automate defect diagnosis in solar modules. Nevertheless, there remains a lack of systematic analysis on how model structure optimization and dataset composition affect classification performance. This study investigates the effectiveness of layer-wise fine-tuning and dataset integration using image classification models retrained on infrared (IR) and electroluminescence (EL) images. Specifically, we compared three AlexNet-based training strategies: (1) retraining AlexNet from scratch using only IR images, (2) fine-tuning a model pretrained on general image datasets with IR images, and (3) fine-tuning a model pretrained on general image datasets using both IR and EL images. The results indicated that the best performance was achieved by freezing the first three convolutional layers during fine-tuning, with the AlexNet model fine-tuned on the IR dataset achieving the highest classification accuracy. These findings suggest that combining fine-tuned models with selective layer freezing and tailored datasets can effectively enhance the design of defect detection systems for photovoltaic module diagnostics.

Keywords

Photovoltaic module

Fault diagnosis

Fine-tuning

Thermal image

Electroluminescence image

키워드

태양광 모듈

결함 진단

미세 조정

열화상 이미지

전계발광 이미지

References

IEA, Snapshot of Global PV Markets, 2025. https://iea-pvps.org/wp-content/uploads/2025/04/Snapshot-of-Global-PV-Markets_2025.pdf. last accessed on the 8^th July 2025.

Tsanakas, J. A., Ha, L., and 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, Vol. 62, pp. 695-709, 2016.

10.1016/j.rser.2016.04.079

Kaplani, E., Detection of Degradation Effects in Field-Aged c-Si Solar Cells through IR Thermography and Digital Image Processing, International Journal of Photoenergy, Vol. 2012, pp. 1-11, 2012.

10.1155/2012/396792

Hong, Y. Y. and Pula, R. A., Methods of Photovoltaic Fault Detection and Classification: A Review, Energy Reports, Vol. 8, pp. 5898-5929, 2022.

10.1016/j.egyr.2022.04.043

Akram, M. W., Li, G., Jin, Y., Chen, X., Zhu, C., Zhao, X., and Ahmad, A., CNN based Automatic Detection of Photovoltaic Cell Defects in Electroluminescence Images, Energy, Vol. 189, 116319, 2019.

10.1016/j.energy.2019.116319

Chine, W., Mellit, A., Lughi, V., Malek, A., Sulligoi, G., and Pavan, A. M., A Novel Fault Diagnosis Technique for Photovoltaic Systems Based on Artificial Neural Networks, Renewable Energy, Vol. 90, pp. 501-512, 2016.

10.1016/j.renene.2016.01.036

Herraiz, Á. H., Marugán, A. P., and Márquez, F. P. G., Photovoltaic Plant Condition Monitoring Using Thermal Images Analysis by Convolutional Neural Network-Based Structure, Renewable Energy, Vol. 153, pp. 334-348, 2020.

10.1016/j.renene.2020.01.148

Kellil, N., Aissat, A., and Mellit, A., Fault Diagnosis of Photovoltaic Modules Using Deep Neural Networks and Infrared Images under Algerian Climatic Conditions, Energy, Vol. 263, 125902, 2023.

10.1016/j.energy.2022.125902

Ebrahim, M., Al-Ayyoub, M., and Alsmirat, M. A., Will Transfer Learning Enhance ImageNet Classification Accuracy Using ImageNet Pretrained Models?, International Conference on Information and Communication Systems (ICICS), 211-216, June 2019, Irbid, Jordan, 2019.

10.1109/IACS.2019.8809114

Korkmaz, D. and Acikgoz, H., An Efficient Fault Classification Method in Solar Photovoltaic Modules Using Transfer Learning and Multi-Scale Convolutional Neural Network, Engineering Applications of Artificial Intelligence, Vol. 113, 104959, 2022.

10.1016/j.engappai.2022.104959

Xie, X., Lai, G., You, M., Liang, J., and Leng, B., Effective Transfer Learning of Defect Detection for Photovoltaic Module Cells in Electroluminescence Images, Solar Energy, Vol. 250, pp. 312-323, 2023.

10.1016/j.solener.2022.10.055

Shou, C., Hong, L., Ding, W., Shen, Q., Zhou, W., Jiang, Y., and Zhao, C., Defect Detection with Generative Adversarial Networks for Electroluminescence Images of Solar Cells, In Proceedings of the 2020 35th Youth Academic Annual Conference of Chinese Association of Automation (YAC), pp. 312-317, October 2020, Zhanjiang, China, 2020.

10.1109/YAC51587.2020.9337676

Song, X. and Liu, Y., Defect Detection of Solar Panel Based on DenseNet Network, Industrial Engineering and Applications, Vol. 35, pp. 661-669, 2022.

10.3233/ATDE230093

He, K., Zhang, X., Ren, S., and Sun, J., Deep Residual Learning for Image Recognition, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770-778, June 2016, Las Vegas, USA, 2016.

10.1109/CVPR.2016.90

Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A., Going Deeper with Convolutions, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1-9, June 2015, Boston, USA, 2015.

10.1109/CVPR.2015.7298594

Iandola, F. N., Han, S., Moskewicz, M. W., Ashraf, K., Dally, W. J., and Keutzer, K., SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size, arXiv preprint, arXiv:1602.07360, 2016.

Millendorf, M., Obropta, E., and Vadhavkar, N., Infrared Solar Module Dataset for Anomaly Detection, International Conference on Learning Representations (ICLR), 2020. https://github.com/RaptorMaps/InfraredSolarModules. last accessed on the the 8^th July 2025

Buerhop-Lutz, C. J. C., Deitsch, S., Maier, A., Gallwitz, F., Berger, S., Doll, B., Hauch, J., Camus, C., and Brabec, C. J., A Benchmark for Visual Identification of Defective Solar Cells in Electroluminescence Imagery, 35th European PV Solar Energy Conference and Exhibition, pp. 1287-1289, August 2018, Brussels, Belgium, 2018.

Bharath, V. S. Kurukuru, Haque, A., and Khan, M. A., Fault Classification for Photovoltaic Modules Using Thermography and Image Processing, Proceedings of the 2019 IEEE Industry Applications Society Annual Meeting, pp. 1-6, November 2019, Baltimore, USA, 2019.

10.1109/IAS.2019.8912356

Information

Publisher :Korean Solar Energy Society
Publisher(Ko) :한국태양에너지학회
Journal Title :Journal of the Korean Solar Energy Society
Journal Title(Ko) :한국태양에너지학회 논문집
Volume : 45
No :4
Pages :67-79
Received Date : 2025-07-14
Revised Date : 2025-07-31
Accepted Date : 2025-08-07
DOI :https://doi.org/10.7836/kses.2025.45.4.067

Journal of the Korean Solar Energy Society ISSN:1598-6411(Print) 2508-3562(Online) 한국태양에너지학회 논문집

All Issue