Contribution of Artificial Intelligence to Predictive Maintenance of Wind Turbines: A Hybrid Framework Combining Multiphysics Modelling and Explainable Deep Learning
Sara SGHIOURI, Hamza SABIR, Mohamed BEZZA, Soukayna TANTANI
Abstract. Wind energy is a pillar of the energy transition. However, WT subassemblies are exposed to mechanical and electrical failures, resulting in high costs and reduced availability. This paper presents a hybrid framework combining Multiphysics modelling using COMSOL Multiphysics, frequency-domain signal analysis, and a comprehensive CNN-LSTM architecture. First, we produce consistent vibrational and electromagnetic torque signatures across varying conditions. Second, we train deep learning models on transformed signals from FFT and STFT. Finally, we use explainable AI tools, such as Grad-CAM and SHAP, to clarify the model’s decision-making process. The suggested architecture achieves an average classification accuracy of 95.6%, which exceeds traditional ML techniques (SVM and Random Forests). These results show that physics-based modelling and XAI work well together for fault detection in WT, establishing a robust baseline for sustainable maintenance strategies aligned with Net Zero 2050 goals.
Keywords
COMSOL Multiphysics, Explainable Artificial Intelligence (XAI), Fast Fourier Transform (FFT), Gradient-Weighted Class Activation Mapping (Grad-CAM), Long-Short Term Memory (LSTM), Machine Learning (ML), Multiphysics Modelling, Predictive Maintenance (PdM), SHapley Additive exPlanations (SHAP), Wind Turbine (WT)
Published online 4/25/2026, 8 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Sara SGHIOURI, Hamza SABIR, Mohamed BEZZA, Soukayna TANTANI, Contribution of Artificial Intelligence to Predictive Maintenance of Wind Turbines: A Hybrid Framework Combining Multiphysics Modelling and Explainable Deep Learning, Materials Research Proceedings, Vol. 64, pp 52-59, 2026
DOI: https://doi.org/10.21741/9781644904091-7
The article was published as article 7 of the book Energy Futures
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] E. Kandemir, A. Hasan, T. Kvamsdal, and S. Abdel-Afou Alaliyat, ‘Predictive digital twin for wind energy systems: a literature review’, Energy Inform., vol. 7, no. 1, p. 68, Aug. 2024. https://doi.org/10.1186/s42162-024-00373-9
[2] K. Yemets, I. Izonin, and I. Dronyuk, ‘Time Series Forecasting Model Based on the Adapted Transformer Neural Network and FFT-Based Features Extraction’, Sensors, vol. 25, no. 3, p. 652, Jan. 2025. https://doi.org/10.3390/s25030652
[3] H. Dhungana, ‘A machine learning approach for wind turbine power forecasting for maintenance planning’, Energy Inform., vol. 8, no. 1, p. 2, Jan. 2025. https://doi.org/10.1186/s42162-024-00459-4
[4] F. Jamil, C. Peeters, T. Verstraeten, and J. Helsen, ‘Leveraging Signal Processing and Machine Learning for Automated Fault Detection in Wind Turbine Drivetrains’, Nov. 25, 2024, Materials and operation/Operation and maintenance, condition monitoring, reliability. https://doi.org/10.5194/wes-2024-114
[5] L. Qi, Q. Zhang, Y. Xie, J. Zhang, and J. Ke, ‘Research on Wind Turbine Fault Detection Based on CNN-LSTM’, Energies, vol. 17, no. 17, p. 4497, Sep. 2024. https://doi.org/10.3390/en17174497
[6] K. Ullah et al., ‘Short-Term Load Forecasting: A Comprehensive Review and Simulation Study With CNN-LSTM Hybrids Approach’, IEEE Access, vol. 12, pp. 111858–111881, 2024. https://doi.org/10.1109/ACCESS.2024.3440631
[7] ‘Fault Diagnosis of Wind Turbine Based on CNN-LSTM Parallel Network Model’, Acad. J. Eng. Technol. Sci., vol. 6, no. 12, 2023. https://doi.org/10.25236/AJETS.2023.061217
[8] D. Astolfi, F. De Caro, and A. Vaccaro, ‘Condition Monitoring of Wind Turbine Systems by Explainable Artificial Intelligence Techniques’, Sensors, vol. 23, no. 12, p. 5376, Jun. 2023. https://doi.org/10.3390/s23125376
[9] H. Sabir, M. Ouassaid, and N. Ngote, ‘A New TSA-Fuzzy Logic Based Diagnosis of Rotor Winding Inter-turn Short Circuit Fault in Wind Turbine Based on DFIG Under Different Operating Wind Speeds’, in Innovation in Information Systems and Technologies to Support Learning Research, vol. 7, M. Serrhini, C. Silva, and S. Aljahdali, Eds, in Learning and Analytics in Intelligent Systems, vol. 7. , Cham: Springer International Publishing, 2020, pp. 583–592. https://doi.org/10.1007/978-3-030-36778-7_64
[10] H. Sabir, M. Ouassaid, and N. Ngote, ‘Detection of an Incipient Rotor Winding Inter-Turn Short Circuit Fault’, in 2021 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC), Ixtapa, Mexico: IEEE, Nov. 2021, pp. 1–7. https://doi.org/10.1109/ROPEC53248.2021.9668140
