Articles | Volume 8, issue 2
https://doi.org/10.5194/wes-8-173-2023
© Author(s) 2023. 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-8-173-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
15 Feb 2023
Research article |
| 15 Feb 2023
| 15 Feb 2023
Introducing a data-driven approach to predict site-specific leading-edge erosion from mesoscale weather simulations
Department of Wind and Energy Systems, Technical University of Denmark (DTU), 4000 Roskilde, Denmark
Tuhfe Göçmen
Department of Wind and Energy Systems, Technical University of Denmark (DTU), 4000 Roskilde, Denmark
Charlotte Bay Hasager
Department of Wind and Energy Systems, Technical University of Denmark (DTU), 4000 Roskilde, Denmark
Hristo Shkalov
Wind Power LAB, 1150 Copenhagen, Denmark
Morten Handberg
Wind Power LAB, 1150 Copenhagen, Denmark
Kristian Pagh Nielsen
Danish Meteorological Institute (DMI), 2100 Copenhagen, Denmark
Related authors
Jens Visbech, Tuhfe Göçmen, Özge Sinem Özçakmak, Alexander Meyer Forsting, Ásta Hannesdóttir, and Pierre-Elouan Réthoré
Wind Energ. Sci., 9, 1811–1826, https://doi.org/10.5194/wes-9-1811-2024, https://doi.org/10.5194/wes-9-1811-2024, 2024
Short summary
Short summary
Leading-edge erosion (LEE) can impact wind turbine aerodynamics and wind farm efficiency. This study couples LEE prediction, aerodynamic loss modeling, and wind farm flow modeling to show that LEE's effects on wake dynamics can affect overall energy production. Without preventive initiatives, the effects of LEE increase over time, resulting in significant annual energy production (AEP) loss.
Hugo Rubio, Daniel Hatfield, Charlotte Bay Hasager, Martin Kühn, and Julia Gottschall
Atmos. Meas. Tech., 18, 4949–4968, https://doi.org/10.5194/amt-18-4949-2025, https://doi.org/10.5194/amt-18-4949-2025, 2025
Short summary
Short summary
Due to the scarcity of offshore in situ observations, alternative data sources are essential for a reliable understanding of offshore winds. Therefore, this study delves into the world of satellite remote sensing (ASCAT) and numerical models (ERA5), exploring their capabilities and limitations in characterising offshore winds. This investigation evaluates these two datasets against measurements from a floating ship-based lidar, collected during a novel measurement campaign in the Baltic Sea.
Charbel Assaad, Juan Pablo Murcia Leon, Julian Quick, Tuhfe Göçmen, Sami Ghazouani, and Kaushik Das
Wind Energ. Sci., 10, 559–578, https://doi.org/10.5194/wes-10-559-2025, https://doi.org/10.5194/wes-10-559-2025, 2025
Short summary
Short summary
This research develops a new method for assessing hybrid power plant (HPP) profitability, combining wind and battery systems. It addresses the need for an efficient, accurate, and comprehensive operational model by approximating a state-of-the-art energy management system (EMS) for spot market power bidding using machine learning. The approach significantly reduces computational demands while maintaining high accuracy. It thus opens new possibilities in terms of optimizing the design of HPPs.
Jens Visbech, Tuhfe Göçmen, Özge Sinem Özçakmak, Alexander Meyer Forsting, Ásta Hannesdóttir, and Pierre-Elouan Réthoré
Wind Energ. Sci., 9, 1811–1826, https://doi.org/10.5194/wes-9-1811-2024, https://doi.org/10.5194/wes-9-1811-2024, 2024
Short summary
Short summary
Leading-edge erosion (LEE) can impact wind turbine aerodynamics and wind farm efficiency. This study couples LEE prediction, aerodynamic loss modeling, and wind farm flow modeling to show that LEE's effects on wake dynamics can affect overall energy production. Without preventive initiatives, the effects of LEE increase over time, resulting in significant annual energy production (AEP) loss.
Jaime Liew, Tuhfe Göçmen, Alan W. H. Lio, and Gunner Chr. Larsen
Wind Energ. Sci., 8, 1387–1402, https://doi.org/10.5194/wes-8-1387-2023, https://doi.org/10.5194/wes-8-1387-2023, 2023
Short summary
Short summary
We present recent research on dynamically modelling wind farm wakes and integrating these enhancements into the wind farm simulator, HAWC2Farm. The simulation methodology is showcased by recreating dynamic scenarios observed in the Lillgrund offshore wind farm. We successfully recreate scenarios with turning winds, turbine shutdown events, and wake deflection events. The research provides opportunities to better identify wake interactions in wind farms, allowing for more reliable designs.
Haichen Zuo and Charlotte Bay Hasager
Atmos. Meas. Tech., 16, 3901–3913, https://doi.org/10.5194/amt-16-3901-2023, https://doi.org/10.5194/amt-16-3901-2023, 2023
Short summary
Short summary
Aeolus is a satellite equipped with a Doppler wind lidar to detect global wind profiles. This study evaluates the impact of Aeolus winds on surface wind forecasts over tropical oceans and high-latitude regions based on the ECMWF observing system experiments. We find that Aeolus can slightly improve surface wind forecasts for the region > 60° N, especially from day 5 onwards. For other study regions, the impact of Aeolus is nearly neutral or limited, which requires further investigation.
Daniel Hatfield, Charlotte Bay Hasager, and Ioanna Karagali
Wind Energ. Sci., 8, 621–637, https://doi.org/10.5194/wes-8-621-2023, https://doi.org/10.5194/wes-8-621-2023, 2023
Short summary
Short summary
Wind observations at heights relevant to the operation of modern offshore wind farms, i.e. 100 m and more, are required to optimize their positioning and layout. Satellite wind retrievals provide observations of the wind field over large spatial areas and extensive time periods, yet their temporal resolution is limited and they are only representative at 10 m height. Machine-learning models are applied to lift these satellite winds to higher heights, directly relevant to wind energy purposes.
Merete Badger, Haichen Zuo, Ásta Hannesdóttir, Abdalmenem Owda, and Charlotte Hasager
Wind Energ. Sci., 7, 2497–2512, https://doi.org/10.5194/wes-7-2497-2022, https://doi.org/10.5194/wes-7-2497-2022, 2022
Short summary
Short summary
When wind turbine blades are exposed to strong winds and heavy rainfall, they may be damaged and their efficiency reduced. The problem is most pronounced offshore where turbines are tall and the climate is harsh. Satellites provide global half-hourly rain observations. We use these rain data as input to a model for blade lifetime prediction and find that the satellite-based predictions agree well with predictions based on observations from weather stations on the ground.
Johan Meyers, Carlo Bottasso, Katherine Dykes, Paul Fleming, Pieter Gebraad, Gregor Giebel, Tuhfe Göçmen, and Jan-Willem van Wingerden
Wind Energ. Sci., 7, 2271–2306, https://doi.org/10.5194/wes-7-2271-2022, https://doi.org/10.5194/wes-7-2271-2022, 2022
Short summary
Short summary
We provide a comprehensive overview of the state of the art and the outstanding challenges in wind farm flow control, thus identifying the key research areas that could further enable commercial uptake and success. To this end, we have structured the discussion on challenges and opportunities into four main areas: (1) insight into control flow physics, (2) algorithms and AI, (3) validation and industry implementation, and (4) integrating control with system design
(co-design).
Konstanze Kölle, Tuhfe Göçmen, Irene Eguinoa, Leonardo Andrés Alcayaga Román, Maria Aparicio-Sanchez, Ju Feng, Johan Meyers, Vasilis Pettas, and Ishaan Sood
Wind Energ. Sci., 7, 2181–2200, https://doi.org/10.5194/wes-7-2181-2022, https://doi.org/10.5194/wes-7-2181-2022, 2022
Short summary
Short summary
The paper studies wind farm flow control (WFFC) in simulations with variable electricity prices. The results indicate that considering the electricity price in the operational strategy can be beneficial with respect to the gained income compared to focusing on the power gain only. Moreover, revenue maximization by balancing power production and structural load reduction is demonstrated at the example of a single wind turbine.
Tuhfe Göçmen, Filippo Campagnolo, Thomas Duc, Irene Eguinoa, Søren Juhl Andersen, Vlaho Petrović, Lejla Imširović, Robert Braunbehrens, Jaime Liew, Mads Baungaard, Maarten Paul van der Laan, Guowei Qian, Maria Aparicio-Sanchez, Rubén González-Lope, Vinit V. Dighe, Marcus Becker, Maarten J. van den Broek, Jan-Willem van Wingerden, Adam Stock, Matthew Cole, Renzo Ruisi, Ervin Bossanyi, Niklas Requate, Simon Strnad, Jonas Schmidt, Lukas Vollmer, Ishaan Sood, and Johan Meyers
Wind Energ. Sci., 7, 1791–1825, https://doi.org/10.5194/wes-7-1791-2022, https://doi.org/10.5194/wes-7-1791-2022, 2022
Short summary
Short summary
The FarmConners benchmark is the first of its kind to bring a wide variety of data sets, control settings, and model complexities for the (initial) assessment of wind farm flow control benefits. Here we present the first part of the benchmark results for three blind tests with large-scale rotors and 11 participating models in total, via direct power comparisons at the turbines as well as the observed or estimated power gain at the wind farm level under wake steering control strategy.
Haichen Zuo, Charlotte Bay Hasager, Ioanna Karagali, Ad Stoffelen, Gert-Jan Marseille, and Jos de Kloe
Atmos. Meas. Tech., 15, 4107–4124, https://doi.org/10.5194/amt-15-4107-2022, https://doi.org/10.5194/amt-15-4107-2022, 2022
Short summary
Short summary
The Aeolus satellite was launched in 2018 for global wind profile measurement. After successful operation, the error characteristics of Aeolus wind products have not yet been studied over Australia. To complement earlier validation studies, we evaluated the Aeolus Level-2B11 wind product over Australia with ground-based wind profiling radar measurements and numerical weather prediction model equivalents. The results show that the Aeolus can detect winds with sufficient accuracy over Australia.
Tuhfe Göçmen, Albert Meseguer Urbán, Jaime Liew, and Alan Wai Hou Lio
Wind Energ. Sci., 6, 111–129, https://doi.org/10.5194/wes-6-111-2021, https://doi.org/10.5194/wes-6-111-2021, 2021
Short summary
Short summary
Currently, the available power estimation is highly dependent on the pre-defined performance parameters of the turbine and the curtailment strategy followed. This paper proposes a model-free approach for a single-input dynamic estimation of the available power using RNNs. The unsteady patterns are represented by LSTM neurons, and the network is adapted to changing inflow conditions via transfer learning. Including highly turbulent flows, the validation shows easy compliance with the grid codes.
Cited articles
Bech, J. I., Hasager, C. B., and Bak, C.: Extending the life of wind turbine blade leading edges by reducing the tip speed during extreme precipitation events, Wind Energ. Sci., 3, 729–748, https://doi.org/10.5194/wes-3-729-2018, 2018. a, b
Bech, J. I., Johansen, N. F.-J., Madsen, M. B., Hannesdóttir, Á., and
Hasager, C. B.: Experimental Study on the Effect of Drop Size in Rain Erosion
Test and on Lifetime Prediction of Wind Turbine Blades, available at SSRN 4011160, https://doi.org/10.1016/j.renene.2022.06.127, 2022.
a
Bengtsson, L., Andrae, U., Aspelien, T., Batrak, Y., Calvo, J., de Rooy, W.,
Gleeson, E., Sass, B. H., Homleid, M., Hortal, M., Ivarsson, K.-I.,
Lenderink, G., Niemelä, S., Nielsen, K. P., Onvlee, J., Rontu, L.,
Samuelsson, P., Santos Muñoz, D., Subias, A., Tijm, S., Toll, V., Yang, X., and Køltzow, M. Ø.: The HARMONIE–AROME Model Configuration in the
ALADIN–HIRLAM NWP System, Mon. Weather Rev., 145, 1919–1935,
https://doi.org/10.1175/MWR-D-16-0417.1, 2017. a
Best, A.: The size distribution of raindrops, Q. J. Roy. Meteorol. Soc., 76, 16–36, 1950. a
Bonab, H. R. and Can, F.: A theoretical framework on the ideal number of
classifiers for online ensembles in data streams, in: Proceedings of the 25th ACM International on Conference on Information and Knowledge Management,
24–28 October 2016, Indianapolis, IN, USA, 2053–2056, https://doi.org/10.1145/2983323.2983907, 2016. a
Breiman, L.: Bagging predictors, Machine learning, 24, 123–140, 1996. a
Cappugi, L., Castorrini, A., Bonfiglioli, A., Minisci, E., and Campobasso,
M. S.: Machine learning-enabled prediction of wind turbine energy yield
losses due to general blade leading edge erosion, Energy. Conver. Manage., 245, 114567, https://doi.org/10.1016/j.enconman.2021.114567, 2021. a, b
Castorrini, A., Venturini, P., Corsini, A., and Rispoli, F.: Machine learnt
prediction method for rain erosion damage on wind turbine blades, Wind
Energy, 24, 917–934, 2021. a
Council, G. W. E.: GWEC | global wind report 2021, Global Wind Energy Council, Brussels, Belgium, https://gwec.net/wp-content/uploads/2021/03/GWEC-Global-Wind-Report-2021.pdf (last access: 14 February 2023), 2021. a
Dietterich, T. G.: Ensemble Methods in Machine Learning, in: Multiple Classifier Systems, MCS 2000, Lecture Notes in Computer Science, vol. 1857, Springer, Berlin, Heidelberg, https://doi.org/10.1007/3-540-45014-9_1, 2000a. a
Dietterich, T. G.: An experimental comparison of three methods for constructing ensembles of decision trees: Bagging, boosting, and randomization, Mach. Learn., 40, 139–157, 2000b. a
Duthé, G., Abdallah, I., Barber, S., and Chatzi, E.: Modeling and
Monitoring Erosion of the Leading Edge of Wind Turbine Blades, Energies, 14,
7262, https://doi.org/10.3390/en14217262, 2021. a
Dykes, K., Resor, B., Platt, A., Guo, Y., Ning, A., King, R., Parsons, T.,
Petch, D., and Veers, P.: Effect of tip-speed constraints on the optimized
design of a wind turbine, Tech. rep., NREL – National Renewable Energy Lab.,
Golden, CO, USA, https://www.nrel.gov/docs/fy15osti/61726.pdf (last access: 14 February 2023), 2014. a
Ehrmann, R. S., Wilcox, B., White, E. B., and Maniaci, D. C.: Effect of Surface Roughness on Wind Turbine Performance, Tech. rep., SNL-NM – Sandia National Lab., Albuquerque, NM, USA, https://energy.sandia.gov/wp-content/uploads/2017/10/LEE_Ehrmann_SAND2017-10669.pdf (last access: 14 February 2023), 2017. a
Foote, G. B. and Du Toit, P.: Terminal velocity of raindrops aloft, J. Appl. Meteorol., 8, 249–253, https://doi.org/10.1175/1520-0450(1969)008<0249:TVORA>2.0.CO;2, 1969. a
Hasager, C. B., Vejen, F., Skrzypiński, W. R., and Tilg, A.-M.: Rain
Erosion Load and Its Effect on Leading-Edge Lifetime and Potential of
Erosion-Safe Mode at Wind Turbines in the North Sea and Baltic Sea, Energies,
14, 1959, https://doi.org/10.3390/en14071959, 2021. a
Herring, R., Dyer, K., Martin, F., and Ward, C.: The increasing importance of
leading edge erosion and a review of existing protection solutions, Renew.
Sustain. Energ. Rev., 115, 109382, https://doi.org/10.1016/j.rser.2019.109382, 2019. a, b
Herring, R., Dyer, K., Howkins, P., and Ward, C.: Characterisation of the offshore precipitation environment to help combat leading edge erosion of wind turbine blades, Wind Energ. Sci., 5, 1399–1409, https://doi.org/10.5194/wes-5-1399-2020, 2020. a, b
King, R.: Erosion by Liquid Impact, Aeronaut. J., 80, 492–493, https://doi.org/10.1017/S0001924000034552, 1976. a
Kruse, E. K., Bak, C., and Olsen, A. S.: Wind tunnel experiments on a NACA 633-418 airfoil with different types of leading edge roughness, Wind Energy, 24, 1263–1274, https://doi.org/10.1002/we.2630, 2021a. a
Kruse, E. K., Sørensen, N. N., and Bak, C.: A two-dimensional quantitative
parametric investigation of simplified surface imperfections on the
aerodynamic characteristics of a NACA 633-418 airfoil, Wind Energy, 24,
310–322, https://doi.org/10.1002/we.2573, 2021b. a
Lakshminarayanan, B., Pritzel, A., and Blundell, C.: Simple and scalable
predictive uncertainty estimation using deep ensembles, Adv. Neural
Inform. Process. Syst., 30, https://doi.org/10.48550/arXiv.1612.01474, 2017. a
Letson, F., Barthelmie, R., and Pryor, S.: Sub-Regional Variability in Wind
Turbine Blade Leading-Edge Erosion Potential, J. Phys.: Confer. Ser., 1618, 032046, https://doi.org/10.1088/1742-6596/1618/3/032046, 2020a. a
Letson, F., Barthelmie, R. J., and Pryor, S. C.: Radar-derived precipitation climatology for wind turbine blade leading edge erosion, Wind Energ. Sci., 5, 331–347, https://doi.org/10.5194/wes-5-331-2020, 2020b. a
Lorenz, E. N.: Deterministic Nonperiodic Flow, J. Atmos. Sci., 20, 130–141,
https://doi.org/10.1175/1520-0469(1963)020<0130:DNF>2.0.CO;2, 1963. a
Lussana, C., Saloranta, T., Skaugen, T., Magnusson, J., Tveito, O. E., and Andersen, J.: seNorge2 daily precipitation, an observational gridded dataset over Norway from 1957 to the present day, Earth Syst. Sci. Data, 10, 235–249, https://doi.org/10.5194/essd-10-235-2018, 2018. a
Martinez, C., Asare Yeboah, F., Herford, S., Brzezinski, M., and Puttagunta,
V.: Predicting wind turbine blade erosion using machine learning, SMU Data Science Review, https://scholar.smu.edu/datasciencereview/vol2/iss2/17 (last access: 14 February 2023) 2019. a
McCartney, M., Haeringer, M., and Polifke, W.: Comparison of machine learning
algorithms in the interpolation and extrapolation of flame describing
functions, J. Eng. Gas Turb. Power, 142, 061009, https://doi.org/10.1115/1.4045516, 2020. a
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., and Galstyan, A.: A survey on bias and fairness in machine learning, ACM Comput. Surv., 54,
1–35, 2021. a
Mishnaevsky Jr., L.: Repair of wind turbine blades: Review of methods and
related computational mechanics problems, Renew. Energy, 140, 828–839, 2019. a
Mishnaevsky Jr., L. and Thomsen, K.: Costs of repair of wind turbine blades:
Influence of technology aspects, Wind Energy, 23, 2247–2255, 2020. a
Naftaly, U., Intrator, N., and Horn, D.: Optimal ensemble averaging of neural
networks, Network, 8, 283–296, https://doi.org/10.1088/0954-898x_8_3_004, 1997. a
Nielsen, N. W., Yang, X., Nielsen, K. P., and Andersen, B. S.: HIRLAM versus
HARMONIE: An Intercomparison Study, Tech. rep., Danish Meteorological
Institute, https://www.dmi.dk/fileadmin/Rapporter/TR/tr10-20.pdf (last access: 14 February 2023), 2010. a
Ning, A. and Dykes, K.: Understanding the benefits and limitations of
increasing maximum rotor tip speed for utility-scale wind turbines, J. Phys.: Conf. Ser., 524, 012087, https://doi.org/10.1088/1742-6596/524/1/012087, 2014. a
Prein, A. F. and Holland, G. J.: Global estimates of damaging hail hazard,
Weather Clim. Ext., 22, 10–23, 2018. a
Prieto, R. and Karlsson, T.: A model to estimate the effect of variables
causing erosion in wind turbine blades, Wind Energy, 24, 1031–1044,
https://doi.org/10.1002/we.2615, 2021. a, b
Punge, H. J. and Kunz, M.: Hail observations and hailstorm characteristics in
Europe: A review, Atmos. Res., 176, 159–184, 2016. a
Sareen, A., Sapre, C. A., and Selig, M. S.: Effects of leading edge erosion on wind turbine blade performance, Wind Energy, 17, 1531–1542, 2014. a
Tilg, A.-M., Hasager, C. B., Kirtzel, H.-J., and Hummelshøj, P.: Brief communication: Nowcasting of precipitation for leading-edge-erosion-safe mode, Wind Energ. Sci., 5, 977–981, https://doi.org/10.5194/wes-5-977-2020, 2020. a
Tilg, A.-M., Hagen, M., Vejen, F., and Hasager, C. B.: Variation of
leading-edge-erosion relevant precipitation parameters with location and
weather type, Meteorol. Z., 30, 251–269, 2021. a
Verma, A. S., Jiang, Z., Caboni, M., Verhoef, H., van der Mijle Meijer, H.,
Castro, S. G., and Teuwen, J. J.: A probabilistic rainfall model to estimate
the leading-edge lifetime of wind turbine blade coating system, Renew. Energy, 178, 1435–1455, 2021a. a
Yang, X., Andersen, B. S., Dahlbom, M., Sass, B. H., Zhuang, S., Amstrup, B.,
Petersen, C., Nielsen, K. P., Nielsen, N. W., and Mahura, A.: NEA, the
Operational Implementation of HARMONIE 40h1.1 at DMI, ALADIN-HIRLAM
Newsletter 8, 104–111, http://www.umr-cnrm.fr/aladin/meshtml/NL8-final.pdf (last access: 14 February 2022), 2017. a
Short summary
This paper presents a data-driven framework for modeling erosion damage based on real blade inspections and mesoscale weather data. The outcome of the framework is a machine-learning-based model that can predict and/or forecast leading-edge erosion damage based on weather data and user-specified wind turbine characteristics. The model output fits directly into the damage terminology used by the industry and can therefore support site-specific maintenance planning and scheduling of repairs.
This paper presents a data-driven framework for modeling erosion damage based on real blade...
Altmetrics
Final-revised paper
Preprint