Articles | Volume 10, issue 12
https://doi.org/10.5194/wes-10-2841-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/wes-10-2841-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
01 Dec 2025
Research article |
| 01 Dec 2025
| 01 Dec 2025
Fault detection in wind turbines using health index monitoring with variational autoencoders
Shun Wang
Control, Data and Artificial Intelligence (CoDAlab), Department of Mathematics, Escola d'Enginyeria de Barcelona Est (EEBE), Universitat Politècnica de Catalunya (UPC), Campus Diagonal-Besòs (CDB), Eduard Maristany, 16, Barcelona, 08019, Spain
Control, Data and Artificial Intelligence (CoDAlab), Department of Mathematics, Escola d'Enginyeria de Barcelona Est (EEBE), Universitat Politècnica de Catalunya (UPC), Campus Diagonal-Besòs (CDB), Eduard Maristany, 16, Barcelona, 08019, Spain
Institute of Mathematics (IMTech), Universitat Politècnica de Catalunya (UPC), Barcelona, 08028, Spain
Francesc Pozo
Control, Data and Artificial Intelligence (CoDAlab), Department of Mathematics, Escola d'Enginyeria de Barcelona Est (EEBE), Universitat Politècnica de Catalunya (UPC), Campus Diagonal-Besòs (CDB), Eduard Maristany, 16, Barcelona, 08019, Spain
Institute of Mathematics (IMTech), Universitat Politècnica de Catalunya (UPC), Barcelona, 08028, Spain
Related authors
Sarah Barber, Shun Wang, Francesc Pozo, Yolanda Vidal, Marcela Rodrigues Machado, Amanda Aryda Silva Rodrigues de Sousa, Jefferson da Silva Coelho, Xukai Zhang, Yao-Teng Hu, Arash Noshadravan, Theodoros Varouxis, Mahmoud Abdelhak, Ramin Ghiasi, and Abdollah Malekjafarian
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2025-122, https://doi.org/10.5194/wes-2025-122, 2025
Preprint under review for WES
Short summary
Short summary
Open innovation digital platforms can boost data sharing and maturity in wind energy. This study applies a two-phase Design Thinking approach to evolve the WeDoWind project into an open innovation ecosystem. A feasibility study using a fault detection challenge showed medium feasibility: strong governance and scalability, but improvements are needed in funding, adoption, and community engagement for sustainable growth.
Sarah Barber, Shun Wang, Francesc Pozo, Yolanda Vidal, Marcela Rodrigues Machado, Amanda Aryda Silva Rodrigues de Sousa, Jefferson da Silva Coelho, Xukai Zhang, Yao-Teng Hu, Arash Noshadravan, Theodoros Varouxis, Mahmoud Abdelhak, Ramin Ghiasi, and Abdollah Malekjafarian
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2025-122, https://doi.org/10.5194/wes-2025-122, 2025
Preprint under review for WES
Short summary
Short summary
Open innovation digital platforms can boost data sharing and maturity in wind energy. This study applies a two-phase Design Thinking approach to evolve the WeDoWind project into an open innovation ecosystem. A feasibility study using a fault detection challenge showed medium feasibility: strong governance and scalability, but improvements are needed in funding, adoption, and community engagement for sustainable growth.
Kayacan Kestel, Xavier Chesterman, Donatella Zappalá, Simon Watson, Mingxin Li, Edward Hart, James Carroll, Yolanda Vidal, Amir R. Nejad, Shawn Sheng, Yi Guo, Matthias Stammler, Florian Wirsing, Ahmed Saleh, Nico Gregarek, Thao Baszenski, Thomas Decker, Martin Knops, Georg Jacobs, Benjamin Lehmann, Florian König, Ines Pereira, Pieter-Jan Daems, Cédric Peeters, and Jan Helsen
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2025-168, https://doi.org/10.5194/wes-2025-168, 2025
Preprint under review for WES
Short summary
Short summary
Wind energy use has been rapidly expanding worldwide in recent years. Driven by global decarbonization goals and energy security concerns, this growth is expected to continue. To achieve these targets, production costs must decrease, with operation and maintenance being major contributors. This paper reviews current and emerging technologies for monitoring wind turbine drivetrains and highlights key academic and industrial challenges that may hinder progress.
Lorena Campoverde-Vilela, María del Cisne Feijóo, Yolanda Vidal, José Sampietro, and Christian Tutivén
Wind Energ. Sci., 8, 557–574, https://doi.org/10.5194/wes-8-557-2023, https://doi.org/10.5194/wes-8-557-2023, 2023
Short summary
Short summary
In order to provide early warnings of faults in the main bearing, a fault detection system is developed by applying an anomaly detector based on principal component analysis. Without the need to obtain the fault history or install additional equipment or sensors that would require a larger investment, this model is constructed using only healthy supervisory control and data acquisition (SCADA) data. The results obtained enable failure detection even months before the fatal breakdown takes place.
Cited articles
Abid, A., Khan, M. T., and Iqbal, J.: A review on fault detection and diagnosis techniques: basics and beyond, Artificial Intelligence Review, 54, 3639–3664, 2021. a
Ashkarkalaei, M., Ghiasi, R., Pakrashi, V., and Malekjafarian, A.: Feature selection for unsupervised defect detection of a wind turbine blade considering operational and environmental conditions, Mechanical Systems and Signal Processing, 230, 112568, https://doi.org/10.1016/j.ymssp.2025.112568, 2025. a, b
Badihi, H., Zhang, Y., Jiang, B., Pillay, P., and Rakheja, S.: A comprehensive review on signal-based and model-based condition monitoring of wind turbines: Fault diagnosis and lifetime prognosis, Proceedings of the IEEE, 110, 754–806, 2022. a
Bertelè, M., Bottasso, C. L., and Cacciola, S.: Automatic detection and correction of pitch misalignment in wind turbine rotors, Wind Energ. Sci., 3, 791–803, https://doi.org/10.5194/wes-3-791-2018, 2018. a
Bilendo, F., Lu, N., Badihi, H., Meyer, A., Cali, Ü., and Cambron, P.: Multitarget normal behavior model based on heterogeneous stacked regressions and change-point detection for wind turbine condition monitoring, IEEE Transactions on Industrial Informatics, 20, 5171–5181, 2023. a
Cacciola, S., Agud, I. M., and Bottasso, C. L.: Detection of rotor imbalance, including root cause, severity and location, Journal of Physics: Conference Series, 753, 072003, https://doi.org/10.1088/1742-6596/753/7/072003, 2016. a
Castellani, F., Natili, F., Astolfi, D., and Vidal, Y.: Wind turbine gearbox condition monitoring through the sequential analysis of industrial SCADA and vibration data, Energy Reports, 12, 750–761, 2024. a
Chatzi, E., Abdallah, I., Hofsäß, M., Bischoff, O., Barber, S., and Marykovskiy, Y.: Aventa AV-7 ETH Zurich Research Wind Turbine SCADA and high frequency Structural Health Monitoring (SHM) data, Zenodo [Data set], https://doi.org/10.5281/zenodo.8229750, 2023. a
Chatzi, E., Abdallah, I., Hofsäß, M., Bischoff, O., Barber, S., and Marykovskiy, Y.: Aventa AV-7 ETH Zurich Research Wind Turbine SCADA and High-Frequency Structural Health Monitoring (SHM) Data, Zenodo, https://doi.org/10.5281/zenodo.8229750, 2023. a, b, c, d
Chen, W., Zhou, H., Cheng, L., and Xia, M.: Condition Monitoring and Anomaly Detection of Wind Turbines using Temporal Convolutional Informer and Robust Dynamic Mahalanobis Mahalanobis Distance, IEEE Transactions on Instrumentation and Measurement, 72, https://doi.org/10.1109/TIM.2023.3329105, 2023. a
Chen, Y. and Griffith, D. T.: Blade mass imbalance identification and estimation for three-bladed wind turbine rotor based on modal analysis, Mechanical Systems and Signal Processing, 197, 110341, https://doi.org/10.1016/j.ymssp.2023.110341 2023. a
Chesterman, X., Verstraeten, T., Daems, P.-J., Nowé, A., and Helsen, J.: Overview of normal behavior modeling approaches for SCADA-based wind turbine condition monitoring demonstrated on data from operational wind farms, Wind Energ. Sci., 8, 893–924, https://doi.org/10.5194/wes-8-893-2023, 2023. a, b
Council, G. W. E.: Global Wind Report 2025, https://www.gwec.net/reports/globalwindreport/ (last access: 27 November 2025), 2025. a
Cuesta, J., Leturiondo, U., Vidal, Y., and Pozo, F.: A review of prognostics and health management techniques in wind energy, Reliability Engineering & System Safety, 260, 111004, https://doi.org/10.1016/j.ress.2025.111004, 2025. a, b
Dey, S., Pisu, P., and Ayalew, B.: A comparative study of three fault diagnosis schemes for wind turbines, IEEE Transactions on Control Systems Technology, 23, 1853–1868, 2015. a
Dibaj, A., Gao, Z., and Nejad, A. R.: Fault detection of offshore wind turbine drivetrains in different environmental conditions through optimal selection of vibration measurements, Renewable Energy, 203, 161–176, 2023. a
Ding, P., Jia, M., and Yan, X.: Stationary subspaces-vector autoregressive with exogenous terms methodology for degradation trend estimation of rolling and slewing bearings, Mechanical Systems and Signal Processing, 150, 107293, https://doi.org/10.1016/j.ymssp.2020.107293, 2021. a
Ghiasi, R., Khan, M. A., Sorrentino, D., Diaine, C., and Malekjafarian, A.: An unsupervised anomaly detection framework for onboard monitoring of railway track geometrical defects using one-class support vector machine, Engineering Applications of Artificial Intelligence, 133, 108167, https://doi.org/10.1016/j.engappai.2024.108167, 2024. a
Habibi, H., Howard, I., and Simani, S.: Reliability improvement of wind turbine power generation using model-based fault detection and fault tolerant control: A review, Renewable Energy, 135, 877–896, 2019. a
Irena, I.: Renewable power generation costs in 2017, Report, International Renewable Energy Agency, Abu Dhabi, https://www.irena.org/publications/2018/Jan/Renewable-power-generation-costs-in-2017 (last access: 27 November 2025), 2018. a
Jiang, G., He, H., Yan, J., and Xie, P.: Multiscale convolutional neural networks for fault diagnosis of wind turbine gearbox, IEEE Transactions on Industrial Electronics, 66, 3196–3207, 2018. a
Jiang, Y., Tang, B., Qin, Y., and Liu, W.: Feature extraction method of wind turbine based on adaptive Morlet wavelet and SVD, Renewable Energy, 36, 2146–2153, 2011. a
Jin, X., Lv, S., Kong, Z., Yang, H., Zhang, Y., Guo, Y., and Xu, Z.: Graph Spatio-Temporal Networks for Condition Monitoring of Wind Turbine, IEEE Transactions on Sustainable Energy, 15, https://doi.org/10.1109/TSTE.2024.3411884, 2024. a
Kingma, D. P. and Welling, M.: Auto-encoding variational bayes, in: Proceedings of the 2nd International Conference on Learning Representations (ICLR), Banff, AB, Canada, https://doi.org/10.48550/arXiv.1312.6114, 2014. a
Li, X., Cheng, C., and Peng, Z.: Unsupervised construction of health indicator for rotating machinery via multi-criterion feature selection and attentive variational autoencoder, Science China Technological Sciences, 67, 1524–1537, 2024. a
Liu, J., Yang, G., Li, X., Hao, S., Guan, Y., and Li, Y.: A deep generative model based on CNN-CVAE for wind turbine condition monitoring, Measurement Science and Technology, 34, 035902, https://doi.org/10.1088/1361-6501/aca496, 2022. a
Liu, X., Teng, W., Wu, S., Wu, X., Liu, Y., and Ma, Z.: Sparse dictionary learning based adversarial variational auto-encoders for fault identification of wind turbines, Measurement, 183, 109810, https://doi.org/10.1016/j.measurement.2021.109810, 2021. a
Mylonas, C., Abdallah, I., and Chatzi, E.: Conditional variational autoencoders for probabilistic wind turbine blade fatigue estimation using Supervisory, Control, and Data Acquisition data, Wind Energy, 24, 1122–1139, 2021. a
Pandit, R. and Wang, J.: A comprehensive review on enhancing wind turbine applications with advanced SCADA data analytics and practical insights, IET Renewable Power Generation, 18, 722–742, 2024. a
Peng, D., Desmet, W., and Gryllias, K.: Reconstruction-based deep unsupervised adaptive threshold support vector data description for wind turbine anomaly detection, Reliability Engineering & System Safety, 260, 110995, https://doi.org/10.1016/j.ress.2025.110995, 2025. a
Ren, Z., Verma, A. S., Li, Y., Teuwen, J. J., and Jiang, Z.: Offshore wind turbine operations and maintenance: A state-of-the-art review, Renewable and Sustainable Energy Reviews, 144, 110886, https://doi.org/10.1016/j.rser.2021.110886, 2021. a
Riva, R., Cacciola, S., and Bottasso, C. L.: Periodic stability analysis of wind turbines operating in turbulent wind conditions, Wind Energ. Sci., 1, 177–203, https://doi.org/10.5194/wes-1-177-2016, 2016. a
Rolinek, M., Zietlow, D., and Martius, G.: Variational autoencoders pursue pca directions (by accident), in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12406–12415, https://doi.org/10.1109/CVPR.2019.01269, 2019. a
Sandoval, D., Leturiondo, U., Vidal, Y., and Pozo, F.: Entropy indicators: An approach for low-speed bearing diagnosis, Sensors, 21, 849, https://doi.org/10.3390/s21030849, 2021. a
Singh, D., Dwight, R., and Viré, A.: Probabilistic surrogate modeling of damage equivalent loads on onshore and offshore wind turbines using mixture density networks, Wind Energ. Sci., 9, 1885–1904, https://doi.org/10.5194/wes-9-1885-2024, 2024. a
Singh, D., Haugen, E., Laugesen, K., P. Dwight, R., and Viré, A.: Data-driven probabilistic surrogate model for floating wind turbine lifetime damage equivalent load prediction, Wind Energ. Sci. Discuss. [preprint], https://doi.org/10.5194/wes-2025-24, in review, 2025. a
Su, X., Shan, Y., Li, C., Mi, Y., Fu, Y., and Dong, Z.: Spatial-temporal attention and GRU based interpretable condition monitoring of offshore wind turbine gearboxes, IET Renewable Power Generation, 16, 402–415, 2022. a
Sun, S., Li, Q., Hu, W., Liang, Z., Wang, T., and Chu, F.: Wind turbine blade breakage detection based on environment-adapted contrastive learning, Renewable Energy, 219, 119487, https://doi.org/10.1016/j.renene.2023.119487, 2023. a
Tutivén, C., Vidal, Y., Insuasty, A., Campoverde-Vilela, L., and Achicanoy, W.: Early fault diagnosis strategy for WT main bearings based on SCADA data and one-class SVM, Energies, 15, 4381, https://doi.org/10.3390/en15124381, 2022. a
Visbech, J., Göçmen, T., Özçakmak, Ö. S., Meyer Forsting, A., Hannesdóttir, Á., and Réthoré, P.-E.: Aerodynamic effects of leading-edge erosion in wind farm flow modeling, Wind Energ. Sci., 9, 1811–1826, https://doi.org/10.5194/wes-9-1811-2024, 2024. a
Wang, A., Qian, Z., Pei, Y., and Jing, B.: A de-ambiguous condition monitoring scheme for wind turbines using least squares generative adversarial networks, Renewable Energy, 185, 267–279, 2022. a
Wang, S., Vidal, Y., and Pozo, F.: An unsupervised approach to early fault detection and performance degradation assessment in bearings, Advanced Engineering Informatics, 68, 103620, https://doi.org/10.1016/j.aei.2025.103620, 2025a. a
Wang, Z., Zhang, M., Chen, H., Li, J., Li, G., Zhao, J., Yao, L., Zhang, J., and Chu, F.: A generalized fault diagnosis framework for rotating machinery based on phase entropy, Reliability Engineering & System Safety, 256, 110745, https://doi.org/10.1016/j.ress.2024.110745, 2025b. a
WeDoWind: The RTDT Research Affiliate Programme Space, https://www.wedowind.ch/spaces/the-rtdt-research-affiliate-programme-space (last access: 27 November 2025), 2025. a
Wu, P., Wang, Y., Zhang, X., Gao, J., Wang, L., and Liu, Y.: Wind Turbine Blade Breakage Monitoring with Mogrifier LSTM Autoencoder, IEEE Transactions on Instrumentation and Measurement, 72, https://doi.org/10.1109/TIM.2023.3323967, 2023. a
Xu, H., Pang, G., Wang, Y., and Wang, Y.: Deep isolation forest for anomaly detection, IEEE Transactions on Knowledge and Data Engineering, 35, 12591–12604, 2023. a
Xu, X., Huang, X., Bian, H., Wu, J., Liang, C., and Cong, F.: Total process of fault diagnosis for wind turbine gearbox, from the perspective of combination with feature extraction and machine learning: A review, Energy and AI, 15, 100318, https://doi.org/10.1016/j.egyai.2023.100318, 2024. a
Yan, X., Xu, Y., She, D., and Zhang, W.: Reliable fault diagnosis of bearings using an optimized stacked variational denoising auto-encoder, Entropy, 24, 36, 2021. a
Yang, T., Jiang, L., Guo, Y., Han, Q., and Li, X.: LTFM-net framework: Advanced intelligent diagnostics and interpretability of insulated bearing faults in offshore wind turbines under complex operational conditions, Ocean Engineering, 309, 118533, https://doi.org/10.1016/j.oceaneng.2024.118533, 2024. a
Ying, W., Li, Y., Noman, K., Zheng, J., Wang, D., Feng, K., and Li, Z.: Stockwell transform spectral amplitude modulation method for rotating machinery fault diagnosis, Mechanical Systems and Signal Processing, 223, 111884, https://doi.org/10.1016/j.ymssp.2024.111884, 2025. a
Yu, W., Kim, I. Y., and Mechefske, C.: An improved similarity-based prognostic algorithm for RUL estimation using an RNN autoencoder scheme, Reliability Engineering & System Safety, 199, 106926, https://doi.org/10.1016/j.ress.2020.106926, 2020. a
Zhang, C., Hu, D., and Yang, T.: Anomaly detection and diagnosis for wind turbines using long short-term memory-based stacked denoising autoencoders and XGBoost, Reliability Engineering & System Safety, 222, 108445, https://doi.org/10.1016/j.ress.2022.108445, 2022. a
Zhou, H., Huang, X., Wen, G., Lei, Z., Dong, S., Zhang, P., and Chen, X.: Construction of health indicators for condition monitoring of rotating machinery: A review of the research, Expert Systems with Applications, 203, 117297, https://doi.org/10.1016/j.eswa.2022.117297, 2022. a
Short summary
This research aims to improve wind turbine maintenance by detecting faults early using only data from normal operation. The method analyzes vibration signals in both time and frequency domains and uses a variational autoencoder, a type of deep learning model, to learn normal behavior. It then detects anomalies by measuring how much new data deviate from this learned model. Tests on real turbine data show early and accurate detection of faults such as pitch issues and icing.
This research aims to improve wind turbine maintenance by detecting faults early using only data...
Altmetrics
Final-revised paper
Preprint