Articles | Volume 10, issue 11
https://doi.org/10.5194/wes-10-2563-2025
© 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-10-2563-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
12 Nov 2025
Research article |
| 12 Nov 2025
| 12 Nov 2025
Simulating run-to-failure SCADA time series to enhance wind turbine fault detection and prognosis
Ali Eftekhari Milani
CORRESPONDING AUTHOR
TU Delft, Kluyverweg 1, Delft, 2629 HS, the Netherlands
Donatella Zappalá
TU Delft, Kluyverweg 1, Delft, 2629 HS, the Netherlands
Francesco Castellani
Department of Engineering, University of Perugia, Via Duranti, 06125, Perugia, Italy
Simon Watson
TU Delft, Kluyverweg 1, Delft, 2629 HS, the Netherlands
Related authors
Mario De Florio, Gabriel Appleby, Jonathan Keller, Ali Eftekhari Milani, Donatella Zappalá, and Shawn Sheng
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2025-157, https://doi.org/10.5194/wes-2025-157, 2025
Revised manuscript under review for WES
Short summary
Short summary
We developed a new method to predict when wind turbine parts are likely to fail, allowing maintenance to be planned before costly breakdowns occur. By combining real measurements from turbines with knowledge of how cracks grow in metal, our approach gives more reliable forecasts even when only limited data are available. We also measure how confident the predictions are, helping operators make better decisions. This can reduce downtime and lower the cost of wind energy.
Oriol Cayon, Simon Watson, and Roland Schmehl
Wind Energ. Sci., 10, 2161–2188, https://doi.org/10.5194/wes-10-2161-2025, https://doi.org/10.5194/wes-10-2161-2025, 2025
Short summary
Short summary
This study demonstrates how kites used to generate wind energy can act as sensors to measure wind conditions and system behaviour. By combining data from existing sensors, such as those measuring position, speed, and forces on the tether, a sensor fusion technique accurately estimates wind conditions and kite performance. This approach can be integrated into control systems to help optimize energy generation and enhance the reliability of these systems under changing wind conditions.
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.
Mario De Florio, Gabriel Appleby, Jonathan Keller, Ali Eftekhari Milani, Donatella Zappalá, and Shawn Sheng
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2025-157, https://doi.org/10.5194/wes-2025-157, 2025
Revised manuscript under review for WES
Short summary
Short summary
We developed a new method to predict when wind turbine parts are likely to fail, allowing maintenance to be planned before costly breakdowns occur. By combining real measurements from turbines with knowledge of how cracks grow in metal, our approach gives more reliable forecasts even when only limited data are available. We also measure how confident the predictions are, helping operators make better decisions. This can reduce downtime and lower the cost of wind energy.
Mehtab Ahmed Khan, Dries Allaerts, Simon J. Watson, and Matthew J. Churchfield
Wind Energ. Sci., 10, 1167–1185, https://doi.org/10.5194/wes-10-1167-2025, https://doi.org/10.5194/wes-10-1167-2025, 2025
Short summary
Short summary
To guide realistic atmospheric gravity wave simulations, we study flow over a two-dimensional hill and through a wind farm canopy, examining optimal domain size and damping layer setup. Wave properties based on non-dimensional numbers determine the optimal domain and damping parameters. Accurate solutions require the domain length to exceed the effective horizontal wavelength, height, and damping thickness to equal the vertical wavelength and non-dimensional damping strength between 1 and 10.
Dachuan Feng and Simon Watson
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2025-52, https://doi.org/10.5194/wes-2025-52, 2025
Revised manuscript under review for WES
Short summary
Short summary
Weather effects drive wind turbines loads and performance to be different from those under mean atmospheric conditions. However, the influence of unsteady atmospheric phenomena on wake behavior remains unclear. This paper explores how atmospheric gravity waves—large-scale wave-like patterns caused by topographical features—affect meandering motions and turbulence generation in the wake region. The outputs of this paper can be used to guide wake modeling in realistic atmospheric flows.
Branko Kosović, Sukanta Basu, Jacob Berg, Larry K. Berg, Sue E. Haupt, Xiaoli G. Larsén, Joachim Peinke, Richard J. A. M. Stevens, Paul Veers, and Simon Watson
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2025-42, https://doi.org/10.5194/wes-2025-42, 2025
Revised manuscript under review for WES
Short summary
Short summary
Most human activity happens in the layer of the atmosphere which extends a few hundred meters to a couple of kilometers above the surface of the Earth. The flow in this layer is turbulent. Turbulence impacts wind power production and turbine lifespan. Optimizing wind turbine performance requires understanding how turbulence affects both wind turbine efficiency and reliability. This paper points to gaps in our knowledge that need to be addressed to effectively utilize wind resources.
Majid Bastankhah, Marcus Becker, Matthew Churchfield, Caroline Draxl, Jay Prakash Goit, Mehtab Khan, Luis A. Martinez Tossas, Johan Meyers, Patrick Moriarty, Wim Munters, Asim Önder, Sara Porchetta, Eliot Quon, Ishaan Sood, Nicole van Lipzig, Jan-Willem van Wingerden, Paul Veers, and Simon Watson
Wind Energ. Sci., 9, 2171–2174, https://doi.org/10.5194/wes-9-2171-2024, https://doi.org/10.5194/wes-9-2171-2024, 2024
Short summary
Short summary
Dries Allaerts was born on 19 May 1989 and passed away at his home in Wezemaal, Belgium, on 10 October 2024 after battling cancer. Dries started his wind energy career in 2012 and had a profound impact afterward on the community, in terms of both his scientific realizations and his many friendships and collaborations in the field. His scientific acumen, open spirit of collaboration, positive attitude towards life, and playful and often cheeky sense of humor will be deeply missed by many.
Livia Brandetti, Sebastiaan Paul Mulders, Roberto Merino-Martinez, Simon Watson, and Jan-Willem van Wingerden
Wind Energ. Sci., 9, 471–493, https://doi.org/10.5194/wes-9-471-2024, https://doi.org/10.5194/wes-9-471-2024, 2024
Short summary
Short summary
This research presents a multi-objective optimisation approach to balance vertical-axis wind turbine (VAWT) performance and noise, comparing the combined wind speed estimator and tip-speed ratio (WSE–TSR) tracking controller with a baseline. Psychoacoustic annoyance is used as a novel metric for human perception of wind turbine noise. Results showcase the WSE–TSR tracking controller’s potential in trading off the considered objectives, thereby fostering the deployment of VAWTs in urban areas.
Livia Brandetti, Sebastiaan Paul Mulders, Yichao Liu, Simon Watson, and Jan-Willem van Wingerden
Wind Energ. Sci., 8, 1553–1573, https://doi.org/10.5194/wes-8-1553-2023, https://doi.org/10.5194/wes-8-1553-2023, 2023
Short summary
Short summary
This research presents the additional benefits of applying an advanced combined wind speed estimator and tip-speed ratio tracking (WSE–TSR) controller compared to the baseline Kω2. Using a frequency-domain framework and an optimal calibration procedure, the WSE–TSR tracking control scheme shows a more flexible trade-off between conflicting objectives: power maximisation and load minimisation. Therefore, implementing this controller on large-scale wind turbines will facilitate their operation.
Serkan Kartal, Sukanta Basu, and Simon J. Watson
Wind Energ. Sci., 8, 1533–1551, https://doi.org/10.5194/wes-8-1533-2023, https://doi.org/10.5194/wes-8-1533-2023, 2023
Short summary
Short summary
Peak wind gust is a crucial meteorological variable for wind farm planning and operations. Unfortunately, many wind farms do not have on-site measurements of it. In this paper, we propose a machine-learning approach (called INTRIGUE, decIsioN-TRee-based wInd GUst Estimation) that utilizes numerous inputs from a public-domain reanalysis dataset, generating long-term, site-specific peak wind gust series.
Sarah J. Ollier and Simon J. Watson
Wind Energ. Sci., 8, 1179–1200, https://doi.org/10.5194/wes-8-1179-2023, https://doi.org/10.5194/wes-8-1179-2023, 2023
Short summary
Short summary
This modelling study shows that topographic trapped lee waves (TLWs) modify flow behaviour and power output in offshore wind farms. We demonstrate that TLWs can substantially alter the wind speeds at individual wind turbines and effect the power output of the turbine and whole wind farm. The impact on wind speeds and power is dependent on which part of the TLW wave cycle interacts with the wind turbines and wind farm. Positive and negative impacts of TLWs on power output are observed.
Amir R. Nejad, Jonathan Keller, Yi Guo, Shawn Sheng, Henk Polinder, Simon Watson, Jianning Dong, Zian Qin, Amir Ebrahimi, Ralf Schelenz, Francisco Gutiérrez Guzmán, Daniel Cornel, Reza Golafshan, Georg Jacobs, Bart Blockmans, Jelle Bosmans, Bert Pluymers, James Carroll, Sofia Koukoura, Edward Hart, Alasdair McDonald, Anand Natarajan, Jone Torsvik, Farid K. Moghadam, Pieter-Jan Daems, Timothy Verstraeten, Cédric Peeters, and Jan Helsen
Wind Energ. Sci., 7, 387–411, https://doi.org/10.5194/wes-7-387-2022, https://doi.org/10.5194/wes-7-387-2022, 2022
Short summary
Short summary
This paper presents the state-of-the-art technologies and development trends of wind turbine drivetrains – the energy conversion systems transferring the kinetic energy of the wind to electrical energy – in different stages of their life cycle: design, manufacturing, installation, operation, lifetime extension, decommissioning and recycling. The main aim of this article is to review the drivetrain technology development as well as to identify future challenges and research gaps.
Bedassa R. Cheneka, Simon J. Watson, and Sukanta Basu
Wind Energ. Sci., 5, 1731–1741, https://doi.org/10.5194/wes-5-1731-2020, https://doi.org/10.5194/wes-5-1731-2020, 2020
Short summary
Short summary
Wind power ramps have important characteristics for the planning and integration of wind power production into electricity. We present a new and simple algorithm that detects wind power ramp characteristics. The algorithm classifies wind power production into ramp-ups, ramp-downs, and no-ramps; and it can detect wind power ramp characteristics that show a temporal increasing (decreasing) power capacity.
Cited articles
Antoniou, A., Storkey, A., and Edwards, H.: Data Augmentation Generative Adversarial Networks, arXiv, https://doi.org/10.48550/ARXIV.1711.04340, 2017. a
Chatterjee, J. and Dethlefs, N.: Scientometric review of artificial intelligence for operations & maintenance of wind turbines: The past, present and future, Renewable and Sustainable Energy Reviews, 144, https://doi.org/10.1016/j.rser.2021.111051, 2021. a
Chawla, N. V., Bowyer, K. W., Hall, L. O., and Kegelmeyer, W. P.: SMOTE: Synthetic Minority Over-sampling Technique, Journal of Artificial Intelligence Research, 16, 321–357, https://doi.org/10.1613/jair.953, 2002. a, b
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
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y.: Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation, arXiv [preprint], https://doi.org/10.48550/ARXIV.1406.1078, 2014. a
Chu, M., Xie, Y., Mayer, J., Leal-Taixé, L., and Thuerey, N.: Learning temporal coherence via self-supervision for GAN-based video generation, ACM Transactions on Graphics, 39, https://doi.org/10.1145/3386569.3392457, 2020. a
Chung, J., Gulcehre, C., Cho, K., and Bengio, Y.: Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling, arXiv [preprint], https://doi.org/10.48550/ARXIV.1412.3555, 2014. a
Cleveland, W. S. and Devlin, S. J.: Locally Weighted Regression: An Approach to Regression Analysis by Local Fitting, Journal of the American Statistical Association, 83, 596–610, https://doi.org/10.1080/01621459.1988.10478639, 1988. a
Colominas, M. A., Schlotthauer, G., and Torres, M. E.: Improved complete ensemble EMD: A suitable tool for biomedical signal processing, Biomedical Signal Processing and Control, 14, 19–29, https://doi.org/10.1016/j.bspc.2014.06.009, 2014. a
Eftekhari Milani, A., Zappalá, D., Castellani, F., and Watson, S.: Boosting field data using synthetic SCADA datasets for wind turbine condition monitoring, Journal of Physics: Conference Series, https://doi.org/10.1088/1742-6596/2767/3/032033, 2024a. a, b
Eftekhari Milani, A., Zappalá, D., and Watson, S.: A hybrid Convolutional Autoencoder training algorithm for unsupervised bearing health indicator construction, Engineering Applications of Artificial Intelligence, https://doi.org/10.1016/j.engappai.2024.109477, 2024b. a, b, c
Goodfellow, I., Bengio, Y., and Courville, A.: Deep Learning, MIT Press, http://www.deeplearningbook.org (last access: 6 November 2025), 2016. a
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y.: Generative adversarial networks, Communications of the ACM, 63, 139–144, https://doi.org/10.1145/3422622, 2020. a, b
Jonkman, B., Mudafort, R. M., Platt, A., Branlard, E., Sprague, M., jjonkman, HaymanConsulting, Vijayakumar, G., Buhl, M., Ross, H., Bortolotti, P., Masciola, M., Ananthan, S., Schmidt, M. J., Rood, J., rdamiani, nrmendoza, sinolonghai, Hall, M., ashesh2512, kshaler, Bendl, K., pschuenemann, psakievich, ewquon, mattrphillips, Kusuno, N., alvarogonzalezsalcedo, Martinez, T., and rcorniglion: OpenFAST/openfast: OpenFAST v3.1.0 (v3.1.0), Zenodo, https://doi.org/10.5281/zenodo.6324288, 2022. a
Kingma, D. P. and Ba, J.: Adam: A Method for Stochastic Optimization, arXiv, https://doi.org/10.48550/ARXIV.1412.6980, 2014. a
Li, S., Peng, Y., and Bin, G.: Prediction of Wind Turbine Blades Icing Based on CJBM With Imbalanced Data, IEEE Sensors Journal, 23, 19726–19736, https://doi.org/10.1109/jsen.2023.3296086, 2023. a
Li, Y., Pan, Q., Wang, S., Yang, T., and Cambria, E.: A Generative Model for category text generation, Information Sciences, 450, 301–315, https://doi.org/10.1016/j.ins.2018.03.050, 2018. a
Liu, J., Qu, F., Hong, X., and Zhang, H.: A Small-Sample Wind Turbine Fault Detection Method With Synthetic Fault Data Using Generative Adversarial Nets, IEEE Transactions on Industrial Informatics, 15, 3877–3888, https://doi.org/10.1109/tii.2018.2885365, 2019. a
Liu, J., Yang, G., Li, X., Wang, Q., He, Y., and Yang, X.: Wind turbine anomaly detection based on SCADA: A deep autoencoder enhanced by fault instances, ISA Transactions, 139, 586–605, https://doi.org/10.1016/j.isatra.2023.03.045, 2023. a
Liu, S., Li, S., and Cheng, H.: Towards an End-to-End Visual-to-Raw-Audio Generation With GAN, IEEE Transactions on Circuits and Systems for Video Technology, 32, 1299–1312, https://doi.org/10.1109/tcsvt.2021.3079897, 2022. a
Mello, E. d., Kampolis, G., Hart, E., Hickey, D., Dinwoodie, I., Carroll, J., Dwyer-Joyce, R., and Boateng, A.: Data driven case study of a wind turbine main-bearing failure, Journal of Physics: Conference Series, 2018, 012011, https://doi.org/10.1088/1742-6596/2018/1/012011, 2021. a
Mirza, M. and Osindero, S.: Conditional Generative Adversarial Nets, arXiv, https://doi.org/10.48550/ARXIV.1411.1784, 2014. a, b
Peng, C., Chen, Q., Zhang, L., Wan, L., and Yuan, X.: Research on fault diagnosis of wind power generator blade based on SC-SMOTE and kNN, Journal of Information Processing Systems, 16, 870–881, https://doi.org/10.3745/JIPS.04.0183, 2020. a
Peter, R., Zappalá, D., Schamboeck, V., and Watson, S. J.: Wind turbine generator prognostics using field SCADA data, Journal of Physics: Conference Series, 2265, 032111, https://doi.org/10.1088/1742-6596/2265/3/032111, 2022. a
Pohlert, T.: Non-Parametric Trend Tests and Change-Point Detection, https://doi.org/10.13140/RG.2.1.2633.4243, 2015. a
Pujana, A., Esteras, M., Perea, E., Maqueda, E., and Calvez, P.: Hybrid-Model-Based Digital Twin of the Drivetrain of a Wind Turbine and Its Application for Failure Synthetic Data Generation, Energies, 16, 861, https://doi.org/10.3390/en16020861, 2023. a
She, D. and Jia, M.: Wear indicator construction of rolling bearings based on multi-channel deep convolutional neural network with exponentially decaying learning rate, J. Measurement, 135, 368–375, https://doi.org/10.1016/j.measurement.2018.11.040, 2019. a
Shorten, C. and Khoshgoftaar, T. M.: A survey on Image Data Augmentation for Deep Learning, Journal of Big Data, 6, https://doi.org/10.1186/s40537-019-0197-0, 2019. a
Song, F., Han, Y., William Heath, A., and Hou, M.: Structural damage detection of floating offshore wind turbine blades based on Conv1d-GRU-MHA network, Engineering Failure Analysis, 166, 108896, https://doi.org/10.1016/j.engfailanal.2024.108896, 2024. a
Spinato, F., Tavner, P., van Bussel, G., and Koutoulakos, E.: Reliability of wind turbine subassemblies, IET Renewable Power Generation, 3, 387, https://doi.org/10.1049/iet-rpg.2008.0060, 2009. a
Tao, C., Tao, T., He, S., Bai, X., and Liu, Y.: Wind turbine blade icing diagnosis using B-SMOTE-Bi-GRU and RFE combined with icing mechanism, Renewable Energy, 221, 119741, https://doi.org/10.1016/j.renene.2023.119741, 2024. a
Tatsis, K., Dertimanis, V., Abdallah, I., and Chatzi, E.: A substructure approach for fatigue assessment on wind turbine support structures using output-only measurements, Procedia Engineering, 199, 1044–1049, https://doi.org/10.1016/j.proeng.2017.09.285, 2017. a
Tatsis, K., Ou, Y., Dertimanis, V. K., Spiridonakos, M. D., and Chatzi, E. N.: Vibration‐based monitoring of a small‐scale wind turbine blade under varying climate and operational conditions. Part II: A numerical benchmark, Structural Control and Health Monitoring, 28, https://doi.org/10.1002/stc.2734, 2021. 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, https://doi.org/10.1016/j.renene.2021.12.049, 2022. a
Yang, N., Liu, S., Liu, J., and Li, C.: Assessment of Equipment Operation State with Improved Random Forest, International Journal of Rotating Machinery, 2021, 1–10, https://doi.org/10.1155/2021/8813443, 2021. a
Yang, Z., Baraldi, P., and Zio, E.: A method for fault detection in multi-component systems based on sparse autoencoder-based deep neural networks, Reliability Engineering and System Safety, 220, 108278, https://doi.org/10.1016/j.ress.2021.108278, 2022. a
Yoon, J., Jarrett, D., and van der Schaar, M.: Time-series Generative Adversarial Networks, in: Advances in Neural Information Processing Systems, edited by Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., and Garnett, R., 5508–5518, https://proceedings.neurips.cc/paper/2019/file/c9efe5f26cd17ba6216bbe2a7d26d490-Paper.pdf (last access: 6 November 2025), 2019. a, b, c
Zhao, Y., Li, D., Dong, A., Kang, D., Lv, Q., and Shang, L.: Fault Prediction and Diagnosis of Wind Turbine Generators Using SCADA Data, Energies, 10, 1210, https://doi.org/10.3390/en10081210, 2017. a, b
Short summary
This paper proposes a data-driven approach to simulate wind turbine sensor time series, such as temperature and pressure signals, describing the behaviour of a wind turbine component as it degrades through time up to the failure point. It allows for the simulation of new failure events or the replication of a given failure under different conditions. The results show that the synthetic signals generated using this approach improve the performance of fault detection and prognosis methods.
This paper proposes a data-driven approach to simulate wind turbine sensor time series, such as...
Altmetrics
Final-revised paper
Preprint