Articles | Volume 11, issue 6
https://doi.org/10.5194/wes-11-1963-2026
https://doi.org/10.5194/wes-11-1963-2026
Research article
 | 
04 Jun 2026
Research article |  | 04 Jun 2026

Remote diagnostics for power converter faults in wind turbines based on converter control system data

Timo Lichtenstein, Martin Hippenstiel, and Katharina Fischer

Related authors

Reliability and O&M key performance indicators of onshore and offshore wind turbines based on field-data analysis
Julia Walgern, Nils Stratmann, Martin Horn, Nathalene W. Y. Then, Moritz Menzel, Fraser Anderson, Athanasios Kolios, and Katharina Fischer
Wind Energ. Sci., 11, 1553–1568, https://doi.org/10.5194/wes-11-1553-2026,https://doi.org/10.5194/wes-11-1553-2026, 2026
Short summary

Cited articles

ABB: New ABB Ability Remote Services Help Boost Wind Parks' Performance | News Center, ABB Media Relations, https://new.abb.com/news/detail/2640/new-abb-ability-remote-services-help-boost-wind-parks-performance (last access: 27 May 2026), 2017. a
Anderson, F., Pelka, K., Walgern, J., Lichtenstein, T., and Fischer, K.: Trends and Influencing Factors in Power-Converter Reliability of Wind Turbines: A Deepened Analysis, IEEE T. Power Electr., 40, 7286–7297, https://doi.org/10.1109/TPEL.2025.3530163, 2025. a, b, c
Bette, H. M., Jungblut, E., and Guhr, T.: Nonstationarity in Correlation Matrices for Wind Turbine SCADA-data, Wind Energy, 26, 826–849, https://doi.org/10.1002/we.2843, 2023. a
Chen, H., Covert, I. C., Lundberg, S. M., and Lee, S.-I.: Algorithms to Estimate Shapley Value Feature Attributions, Nature Machine Intelligence, 5, 590–601, https://doi.org/10.1038/s42256-023-00657-x, 2023. a
Fischer, K., Pelka, K., Bartschat, A., Tegtmeier, B., Coronado, D., Broer, C., and Wenske, J.: Reliability of Power Converters in Wind Turbines: Exploratory Analysis of Failure and Operating Data From a Worldwide Turbine Fleet, IEEE T. Power Electr., 34, 6332–6344, https://doi.org/10.1109/TPEL.2018.2875005, 2019. a, b
Download
Short summary
Power converter faults in wind turbines often lead to costly downtime and repeated maintenance. We present a practical, explainable, and fully data-driven approach that utilizes high-resolution converter control system records, 1 min operating data, and event logs to predict whether a fault leads to a long or short standstill. By combining engineered features with interpretable feature reduction, we achieve 89 % accuracy and an F1 score of 0.86, providing support for remote decision-making.
Share
Altmetrics
Final-revised paper
Preprint