Development of an Integrated DBN-ELM, CNN-SVM and CNN-BiGRU Photovoltaic Array Fault Diagnosis Model Based on Weighted Probability Averaging
DOI:
https://doi.org/10.65582/ec.2026.006Keywords:
PV array, Fault diagnosis methods, Weighted probability average integration modelAbstract
Photovoltaic arrays are continuously exposed to complex environmental conditions over long periods, making them susceptible to seven types of single and multiple failures such as shadow blocking and module aging. Fault diagnosis of photovoltaic arrays is essential to prevent failures that may lead to reduced power generation efficiency and potential safety hazards. This paper proposes a photovoltaic array fault diagnosis model based on weighted probability averaging, integrating DBN-ELM, CNN-SVM, and CNN-BiGRU methods. The model is calculated and experimentally verified. The results demonstrate that the integrated model achieves an overall accuracy, recall, precision, and F1-score of 99.0% across the four evaluation metrics, indicating a highly effective fault recognition capability.
References
Aljafari, B., Satpathy, P.R., 2024. Supervised classification and fault detection in grid-connected PV systems using 1D-CNN: Simulation and real-time validation. Energy Reports, 12: 2156–2178. DOI: https://doi.org/10.1016/j.egyr.2024.08.008. DOI: https://doi.org/10.1016/j.egyr.2024.08.008
Ali, Y.M., Ding, L. and Qin, S., 2025. An efficient approach for diagnosing faults in photovoltaic array using 1D-CNN and feature selection techniques. International Journal of Electrical Power & Energy Systems, 166: 110526. DOI: doi.org/10.1016/j.ijepes.2025.110526. DOI: https://doi.org/10.1016/j.ijepes.2025.110526
Aziz, F., Haq, A.U., Ahmad, S., Mahmoud, Y., Jalal, M. and Ali, U., 2020. A novel convolutional neural network-based approach for fault classification in photovoltaic arrays. IEEE Access, 8: 41889–41904. DOI: doi.org/10.1109/ACCESS.2020.2977116. DOI: https://doi.org/10.1109/ACCESS.2020.2977116
Fu, H., Liu, H., Xie, S., 2025. Multi-coupling fault detection and diagnosis of photovoltaic arrays with improved slime mould algorithm and PolyCatBoost. Process Safety and Environmental Protection, 194: 523–541. DOI: doi.org/10.1016/j.psep.2024.11.135. DOI: https://doi.org/10.1016/j.psep.2024.11.135
Gao, X. and Qian, Y., 2024. Fault diagnosis of photovoltaic arrays based on VMD-SABO-KELM. Information Technology and Informatization, (7): 112–115.
Hajji, M., Harkat, M.F., Kouadri, A., 2021. Multivariate feature extraction based supervised machine learning for fault detection and diagnosis in photovoltaic systems. European Journal of Control, 59: 313–321. DOI: doi.org/10.1016/j.ejcon.2020.03.004. DOI: https://doi.org/10.1016/j.ejcon.2020.03.004
Karmacharya, I.M. and Gokaraju, R., 2018. Fault location in ungrounded photovoltaic system using wavelets and ANN. IEEE Transactions on Power Delivery, 33(2): 549–559. DOI: doi.org/10.1109/PESGM40551.2019.8973821. DOI: https://doi.org/10.1109/TPWRD.2017.2721903
Lin, P., Guo, F., Lu, X., 2024. A compound fault diagnosis model for photovoltaic array based on 1D VoVNet-SVDD by considering unknown faults. Solar Energy, 267: 112155. DOI: doi.org/10.1016/j.solener.2023.112155. DOI: https://doi.org/10.1016/j.solener.2023.112155
Liu, Y., Ding, K., Zhang, J., 2021. Fault diagnosis approach for photovoltaic array based on the stacked auto-encoder and clustering with I–V curves. Energy Conversion and Management, 245: 114603. DOI: https://doi.org/10.1016/j.enconman.2021.114603. DOI: https://doi.org/10.1016/j.enconman.2021.114603
Lu, S.D., Liu, H.D., Wang, M.H., 2024. A novel strategy for multitype fault diagnosis in photovoltaic systems using multiple regression analysis and support vector machines. Energy Reports, 12: 2824–2844. DOI: doi.org/10.1016/j.egyr.2024.08.074. DOI: https://doi.org/10.1016/j.egyr.2024.08.074
Lu, X., Lin, Y., Lin, P., 2023. Efficient fault diagnosis approach for solar photovoltaic array using a convolutional neural network in combination of generative adversarial network under small dataset. Solar Energy, 253: 360–374. DOI: https://doi.org/10.1016/j.solener.2022.12.037
Mustafa, Z., Awad, A.S.A., Azzouz, M., 2023. Fault identification for photovoltaic systems using a multi-output deep learning approach. Expert Systems with Applications, 211: 118551. DOI: doi.org/0.1016/j.eswa.2022.118551. DOI: https://doi.org/10.1016/j.eswa.2022.118551
Patthi, S., Murali Krishna, V.B., Reddy, L., 2024. Photovoltaic string fault optimization using multi-layer neural network technique. Results in Engineering, 22: 102299. DOI: https://doi.org/10.1016/j.rineng.2024.102299. DOI: https://doi.org/10.1016/j.rineng.2024.102299
Turhal, U.C., Onal, Y. and Turhal, K., 2025. Enhanced fault detection and diagnosis in photovoltaic arrays using a hybrid NCA-CNN model. Computer Modeling in Engineering & Sciences, 143(2). DOI: doi.org/10.32604/cmes.2025.064269. DOI: https://doi.org/10.32604/cmes.2025.064269
Voutsinas, S., Karolidis, D., Voyiatzis, I., 2022. Development of a multi-output feed-forward neural network for fault detection in photovoltaic systems. Energy Reports, 8: 33–42. DOI: doi.org/https://doi.org/10.1016/j.egyr.2022.06.107. DOI: https://doi.org/10.1016/j.egyr.2022.06.107
Wang, X.X., Dong, L., Liu, S.Y., 2019. A fault classification method of photovoltaic array based on probabilistic neural network. In: Proceedings of the 2019 Chinese Control and Decision Conference (CCDC), pp. 5260–5265. DOI: doi.org/10.1109/CCDC.2019.8832338. DOI: https://doi.org/10.1109/CCDC.2019.8832338
Yahyaoui, Z., Hajji, M., Mansouri, M., 2024. Enhancing fault diagnosis of uncertain grid-connected photovoltaic systems using deep GRU-based Bayesian optimization. IFAC-PapersOnLine, 58(4): 449–454. DOI: https://doi.org/10.1016/j.ifacol.2024.07.259. DOI: https://doi.org/10.1016/j.ifacol.2024.07.259
Zhong, S., Chen, Z., Wu, L., 2024. Fault diagnosis of photovoltaic arrays based on an improved SqueezeNet. Power Electronics Technology, 58(7): 76–79.
