Probabilistic surrogate modeling of damage equivalent loads on onshore and offshore wind turbines using mixture density networks
Preprint
- 6 March 2024
- preprint
- Published by Copernicus GmbH in EGUsphere
- Vol. 2024, 1-28
Abstract
The use of load surrogates in offshore wind turbine site assessment has gained attention as a way to speed up the lengthy and costly siting process. We propose a novel probabilistic approach using mixture density networks to map 10-minute average site conditions to the corresponding load statistics. The probabilistic framework allows for the modeling of the uncertainty in the loads as a response to the stochastic inflow conditions. We train the data-driven model on the OpenFAST simulations of the IEA-10MW-RWT and compare the predictions to the widely used Gaussian process regression. We show that mixture density networks can recover the accurate mean response in all load channels with values for the coefficient of determination (R2) greater than 0.95 on the test dataset. Mixture density networks completely outperform Gaussian process regression in predicting the quantiles, showing an excellent agreement with the reference. We compare onshore and offshore sites for training to conclude the need for a more extensive training dataset in offshore cases due to the larger feature space and more noise in the data.Keywords
All Related Versions
- Published version: Wind Energy Science, 9 (10), 1885.
Funding Information
- Horizon 2020 (860737)
This publication has 39 references indexed in Scilit:
- Pattern Recognition and Machine Learning2021
- Multibody modeling for concept-level floating offshore wind turbine designMultibody System Dynamics, 2020
- Surrogate-Model-Based Design and Optimization2019
- Surrogate models for parameterized representation of wake‐induced loads in wind farmsWind Energy, 2019
- Conditional deep surrogate models for stochastic, high-dimensional, and multi-fidelity systemsComputational Mechanics, 2019
- Reduced Order Model for Control Applications in Offshore Wind Turbines**This work has been carried out at the Centre for Autonomous Marine Operations and Systems at the Norwegian University of Science and Technology (NTNU AMOS). The Norwegian Research Council is acknowledged as the main sponsor of NTNU AMOS. This work was supported by the Research Council of Norway through the Centres of Excellence funding scheme, Project number 223254 - NTNU AMOS.IFAC-PapersOnLine, 2016
- The simulation error caused by input loading variability in offshore wind turbine structural analysisWind Energy, 2014
- Neural Networks: Tricks of the Trade2012
- The Wasserstein distances2009
- On Early Stopping in Gradient Descent LearningConstructive Approximation, 2007