Preprints
https://doi.org/10.5194/wes-2024-20
https://doi.org/10.5194/wes-2024-20
06 Mar 2024
 | 06 Mar 2024
Status: a revised version of this preprint is currently under review for the journal WES.

Probabilistic surrogate modeling of damage equivalent loads on onshore and offshore wind turbines using mixture density networks

Deepali Singh, Richard Dwight, and Axelle Viré

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.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Deepali Singh, Richard Dwight, and Axelle Viré

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on wes-2024-20', Anonymous Referee #1, 03 Apr 2024
  • RC2: 'Comment on wes-2024-20', Anonymous Referee #2, 27 May 2024
  • RC3: 'Comment on wes-2024-20', Anonymous Referee #3, 31 May 2024
  • AC1: 'Comment on wes-2024-20', Deepali Singh, 04 Jul 2024
Deepali Singh, Richard Dwight, and Axelle Viré

Data sets

Training and validation datasets for training probabilistic machine learning models on NREL's 10-MW reference wind turbine Deepali Singh https://doi.org/10.4121/21939995

Deepali Singh, Richard Dwight, and Axelle Viré

Viewed

Total article views: 568 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
440 102 26 568 22 16
  • HTML: 440
  • PDF: 102
  • XML: 26
  • Total: 568
  • BibTeX: 22
  • EndNote: 16
Views and downloads (calculated since 06 Mar 2024)
Cumulative views and downloads (calculated since 06 Mar 2024)

Viewed (geographical distribution)

Total article views: 553 (including HTML, PDF, and XML) Thereof 553 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 14 Jul 2024
Download
Short summary
The selection of a suitable site for the installation of a wind turbine plays an important role in ensuring a safe operating lifetime of the structure. In this study, we show that mixture density networks can accelerate this process by inferring functions from data that can accurately map the environmental conditions to the loads but also propagate the uncertainty from the inflow to the response.
Altmetrics