AAPN-Tiny: A Compact Edge-Deployable Adaptive Attention Pyramid Architecture for Multi-Class Fault Diagnosis in Solar Photovoltaic Modules
Keywords:
Adaptive attention pyramid network, batch normalization, CNN, detection, Fault classification, infraredAbstract
Solar PV arrays are susceptible to various faults, such as hotspots, cracks, and Potential Induced Degradation, which can impair efficiency and longevity. Traditional fault detection methods are time-intensive and limited in accuracy, especially for large-scale installations. This paper proposes an Adaptive Attention Pyramid Network (AAPN) for accurate and efficient fault detection in PV modules. AAPN integrates depthwise separable convolutions, squeeze-and-excitation blocks, and adaptive attention mechanisms to achieve high accuracy in identifying fault types across different classification complexities. Extensive experimentation on a comprehensive dataset of infrared PV images, organized into 12 fault classes, demonstrated AAPN’s high classification accuracy of up to 96% in binary and 92% in 12-class classification scenarios. The proposed model is tested using an infrared solar module dataset for 2-class, 8- class, 11-class, and 12-class fault categories. Its effectiveness is compared with 69 existing deep-learning models for various fault classes. An ablation study was conducted to evaluate the impact of different architectural components, such as depthwise separable convolutions and squeeze-and-excitation blocks, on the model’s performance, showing an optimal trade-off between accuracy and computational efficiency. The proposed architecture model is very lightweight, utilizing only 0.8 million parameters. Its effective balance between high accuracies and low parameter utilization makes it highly suitable for deployment on dronebased edge devices, facilitating on-site real-time PV fault monitoring, maintenance, and detection. Additionally, the model has been successfully implemented on the Google Coral Edge TPU, achieving 40.2 ms inference time per image, confirming its efficiency and suitability for real-time applications in resourceconstrained environments.
Downloads
References
B. Sezen, C. C. Cerasi et al., “Solar cell busbars surface defect detection based on deep convolutional neural network,” IEEE Latin America Transactions, vol. 21, no. 2, pp. 242–250, 2023, doi: 10.1109/TLA.2023.10015216.
A. E. Nieto, F. Ruiz, D. Patino, and O. Ramirez, “Classification of electric faults in photovoltaic systems based on voltage-power curves,” IEEE Latin america transactions, vol. 19, no. 12, pp. 2071–2078, 2021, doi: 10.1109/TLA.2021.9480149.
A. Guis´andez Hern´andez and S. P. Santos, “Modelling and experimental validation of aging factors of photovoltaic solar cells,” IEEE Latin America Transactions, vol. 19, no. 8, pp. 1270–1277, 2021, doi: 10.1109/TLA.2021.9475857.
M. Le, D. K. Nguyen, V.-D. Dao, N. H. Vu, H. H. T. Vu et al., “Remote anomaly detection and classification of solar photovoltaic modules based on deep neural network,” Sustainable Energy Technologies and Assessments, vol. 48, p. 101545, 2021. https://doi.org/10.1016/j.seta.2021.101545.
M. Le, D. Le, and H. H. T. Vu, “Thermal inspection of photovoltaic modules with deep convolutional neural networks on edge devices in auv,” Measurement, vol. 218, p. 113135, 2023. https://doi.org/10.1016/j.measurement.2023.113135.
Z. B. Duranay, “Fault detection in solar energy systems: A deep learning approach,” Electronics, vol. 12, no. 21, p. 4397, 2023. https://doi.org/10.3390/electronics12214397
R. F. Pamungkas, I. B. K. Y. Utama, and Y. M. Jang, “A novel approach for efficient solar panel fault classification using coupled udensenet,” Sensors, vol. 23, no. 10, p. 4918, 2023. https://doi.org/10.3390/s23104918
C. Tang, H. Ren, J. Xia, F. Wang, and J. Lu, “Automatic defect identification of pv panels with ir images through unmanned aircraft,” IET Renewable Power Generation, vol. 17, no. 12, pp. 3108-3119, 2023. https://doi.org/10.1049/rpg2.12831
X. Zhao, C. Song, H. Zhang, X. Sun, and J. Zhao, “Hrnet-based automatic identification of photovoltaic module defects using electroluminescence images,” Energy, vol. 267, p. 126605, 2023. https://doi.org/10.1016/j.energy.2022.126605
X. Chen, T. Karin, and A. Jain, “Automated defect identification in electroluminescence images of solar modules,” Solar Energy, vol. 242, pp. 20-29, 2022. https://doi.org/10.1016/j.solener.2022.06.031
Á. H. Herraiz, A. P. Marugán, and F. P. G. Márquez, “Photovoltaic plant condition monitoring using thermal images analysis by convolutional neural network-based structure,” Renewable Energy, vol. 153, pp. 334–348, 2020. https://doi.org/10.1016/j.renene.2020.01.148
W. Gao and R.-J. Wai, “A novel fault identification method for photovoltaic array via convolutional neural network and residual gated recurrent unit,” IEEE Access, vol. 8, pp. 159493–159510, 2020. DOI: 10.1109/ACCESS.2020.3020296
B. Su, H. Chen, P. Chen, G. Bian, K. Liu, and W. Liu, “Deep learning-based solar-cell manufacturing defect detection with complementary attention network,” IEEE Transactions on Industrial Informatics, vol. 17, no. 6, pp. 4084–4095, 2020. DOI: 10.1109/TII.2020.3008021
L. Li, Z. Wang, and T. Zhang, “Gbh-yolov5: Ghost convolution with bottleneckcsp and tiny target prediction head incorporating yolov5 for pv panel defect detection,” Electronics, vol. 12, no. 3, p. 561, 2023. https://doi.org/10.3390/electronics12030561
J. Fioresi, D. J. Colvin, R. Frota, R. Gupta, M. Li, H. P. Seigneur, S. Vyas, S. Oliveira, M. Shah, and K. O. Davis, “Automated defect detection and localization in photovoltaic cells using semantic segmentation of electroluminescence images,” IEEE Journal of Photovoltaics, vol. 12, no. 1, pp. 53–61, 2021. DOI: 10.1109/JPHOTOV.2021.3131059
X. Qian, J. Li, J. Cao, Y. Wu, and W. Wang, “Micro-cracks detection of solar cells surface via combining short-term and long-term deep features,” Neural Networks, vol. 127, pp. 132–140, 2020. https://doi.org/10.1016/j.neunet.2020.04.012
Q. Liu, M. Liu, C. Wang, and Q. J. Wu, “An efficient cnn-based detector for photovoltaic module cells defect detection in electroluminescence images,” Solar Energy, vol. 267, p. 112245, 2024. https://doi.org/10.1016/j.solener.2023.112245.
Y. Jia, G. Chen, and L. Zhao, “Defect detection of photovoltaic modules based on improved varifocalnet,” Scientific Reports, vol. 14, no. 1, p. 15170, 2024. https://doi.org/10.1038/s41598-024-66234-3
X. Li, Q. Yang, Z. Lou, and W. Yan, “Deep learning based module defect analysis for large-scale photovoltaic farms,” IEEE Transactions on Energy Conversion, vol. 34, no. 1, pp. 520–529, 2018. DOI: 10.1109/TEC.2018.2873358
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, vol. 198, pp. 175–186, 2020. https://doi.org/10.1016/j.solener.2020.01.055.
N. Kellil, A. Aissat, and A. Mellit, “Fault diagnosis of photovoltaic modules using deep neural networks and infrared images under algerian climatic conditions,” Energy, vol. 263, p. 125902, 2023. https://doi.org/10.1016/j.energy.2022.125902
R. Tang, Z. Ren, S. Ning, and Y. Zhang, “Fault classification of photovoltaic module infrared images based on transfer learning and interpretable convolutional neural network,” Solar Energy, vol. 276, p. 112703, 2024. https://doi.org/10.1016/j.solener.2024.112703
X. Xie, G. Lai, M. You, J. Liang, and B. Leng, “Effective transfer learning of defect detection for photovoltaic module cells in electroluminescence images,” Solar Energy, vol. 250, pp. 312–323, 2023. https://doi.org/10.1016/j.solener.2022.10.055
W. Tang, Q. Yang, K. Xiong, and W. Yan, “Deep learning based automatic defect identification of photovoltaic module using electroluminescence images,” Solar Energy, vol. 201, pp. 453–460, 2020. https://doi.org/10.1016/j.solener.2020.03.049.
M. U. Ali, H. F. Khan, M. Masud, K. D. Kallu, and A. Zafar, “A machine learning framework to identify the hotspot in photovoltaic module using infrared thermography,” Solar Energy, vol. 208, pp. 643–651, 2020. https://doi.org/10.1016/j.solener.2020.08.027
A. M. Karimi, J. S. Fada, M. A. Hossain, S. Yang, T. J. Peshek, J. L. Braid, and R. H. French, “Automated pipeline for photovoltaic module electroluminescence image processing and degradation feature classification,” IEEE Journal of Photovoltaics, vol. 9, no. 5, pp. 1324–1335, 2019. DOI: 10.1109/JPHOTOV.2019.2920732
M. Zhang and L. Yin, “Solar cell surface defect detection based on improved yolo v5,” IEEE Access, vol. 10, pp. 80804–80815, 2022. DOI: 10.1109/ACCESS.2022.3195901
S. Lu, K. Wu, and J. Chen, “Solar cell surface defect detection based on optimized yolov5,” IEEE Access, 2023. DOI: 10.1109/ACCESS.2023.3294344
Y. Cao, D. Pang, Q. Zhao, Y. Yan, Y. Jiang, C. Tian, F. Wang, and J. Li, “Improved yolov8-gd deep learning model for defect detection in electroluminescence images of solar photovoltaic modules,” Engineering Applications of Artificial Intelligence, vol. 131, p. 107866, 2024. https://doi.org/10.1016/j.engappai.2024.107866
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, vol. 202, p. 117087, 2022. https://doi.org/10.1016/j.eswa.2022.117087
Y.-Y. Hong and R. A. Pula, “Detection and classification of faults in photovoltaic arrays using a 3d convolutional neural network,” Energy, vol. 246, p. 123391, 2022. https://doi.org/10.1016/j.energy.2022.123391
H. Wang, H. Chen, B. Wang, Y. Jin, G. Li, and Y. Kan, “High-efficiency low-power microdefect detection in photovoltaic cells via a field programmable gate array-accelerated dual-flow network,” Applied Energy, vol. 318, p. 119203, 2022. https://doi.org/10.1016/j.apenergy.2022.119203
W. Tang, Q. Yang, X. Hu, and W. Yan, “Deep learning-based linear defects detection system for large-scale photovoltaic plants based on an edge-cloud computing infrastructure,” Solar Energy, vol. 231, pp. 527–535, 2022. https://doi.org/10.1016/j.solener.2021.11.016
A. Korovin, A. Vasilev, F. Egorov, D. Saykin, E. Terukov, I. Shakhray, L. Zhukov, and S. Budennyy, “Anomaly detection in electroluminescence images of heterojunction solar cells,” Solar Energy, vol. 259, pp. 130–136, 2023. https://doi.org/10.1016/j.solener.2023.04.059
E. A. Mejia, H. L. Correa, É. Mejía, R. Girón, A. David, N. Rodriguez, and S. Esperanza, “Photovoltaic system thermal images,” Mendeley Data: Amsterdam, The Netherlands, 2019. DOI:10.17632/82vzccxb6y.2
L. Li, Z. Wang, and T. Zhang, “Gbh-yolov5: Ghost convolution with bottleneckcsp and tiny target prediction head incorporating yolov5 for pv panel defect detection,” Electronics, vol. 12, no. 3, p. 561, 2023. https://doi.org/10.3390/electronics12030561
Q. Yang, T. Ku, and K. Hu, “Efficient attention pyramid network for semantic segmentation,” IEEE Access, vol. 9, pp. 18867–18875, 2021. DOI: 10.1109/ACCESS.2021.3053316
E. Ramadan, N. M. Moawad, B. A. Abouzalam, A. A. Sakr, W. F. Abouzaid, and G. M. El-Banby, “An innovative transformer neural network for fault detection and classification for photovoltaic modules,” Energy Conversion and Management, vol. 314, p. 118718, 2024. https://doi.org/10.1016/j.enconman.2024.118718.
D. Korkmaz and H. Acikgoz, “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, p. 104959, 2022. https://doi.org/10.1016/j.engappai.2022.104959
D. Sriraman and R. Ramaprabha, “Application of machine learning and convolutional neural networks for the fault detection and classification monitoring system in pv plants,” in 2023 9th International Conference on Electrical Energy Systems (ICEES). IEEE, 2023, pp. 694–699. DOI: 10.1109/ICEES57979.2023.10110284
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, p. 2112, 2023. https://doi.org/10.3390/en16052112
H. Chen, A. Zhang, C. Gong, W. Liang, and Z. Wang, “Fault diagnosis method for photovoltaic panels based on improved shufflenet v2 and infrared images,” in 2022 7th International Conference on Power and Renewable Energy (ICPRE). IEEE, 2022, pp. 447–451. DOI: 10.1109/ICPRE55555.2022.9960396
S. Wu, Y. Kong, R. Xu, Y. Guo, Z. Chen, and X. Zheng, “A feature space class balancing strategy-based fault classification method in solar photovoltaic modules,” Engineering Applications of Artificial Intelligence, vol. 136, p. 108991, 2024. https://doi.org/10.1016/j.engappai.2024.108991
