Volume 3, issue 2 | Copyright
Wind Energ. Sci., 3, 767-790, 2018
https://doi.org/10.5194/wes-3-767-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

Research articles 24 Oct 2018

Research articles | 24 Oct 2018

From wind to loads: wind turbine site-specific load estimation with surrogate models trained on high-fidelity load databases

Nikolay Dimitrov, Mark C. Kelly, Andrea Vignaroli, and Jacob Berg Nikolay Dimitrov et al.
  • DTU Wind Energy, Technical University of Denmark, Risø Campus, Frederiksborgvej 399, 4000 Roskilde, Denmark

Abstract. We define and demonstrate a procedure for quick assessment of site-specific lifetime fatigue loads using simplified load mapping functions (surrogate models), trained by means of a database with high-fidelity load simulations. The performance of five surrogate models is assessed by comparing site-specific lifetime fatigue load predictions at 10 sites using an aeroelastic model of the DTU 10MW reference wind turbine. The surrogate methods are polynomial chaos expansion, quadratic response surface, universal Kriging, importance sampling, and nearest-neighbor interpolation. Practical bounds for the database and calibration are defined via nine environmental variables, and their relative effects on the fatigue loads are evaluated by means of Sobol sensitivity indices. Of the surrogate-model methods, polynomial chaos expansion provides an accurate and robust performance in prediction of the different site-specific loads. Although the Kriging approach showed slightly better accuracy, it also demanded more computational resources.

Publications Copernicus
Download
Short summary
Wind energy site suitability assessment procedures often require estimating the loads a wind turbine will be subject to when installed. The estimation is often time-consuming and requires several iterations. We have developed a procedure for quick and accurate estimation of site-specific wind turbine loads. Our approach employs computationally efficient parametric models that are calibrated to high-fidelity load simulations. The result is a significant reduction in computation efforts.
Wind energy site suitability assessment procedures often require estimating the loads a wind...
Citation
Share