Preprints
https://doi.org/10.5194/wes-2022-13
https://doi.org/10.5194/wes-2022-13
 
07 Apr 2022
07 Apr 2022
Status: this preprint is currently under review for the journal WES.

A WaveNet-Based Fully Stochastic Dynamic Stall Model

Jan-Philipp Küppers and Tamara Reinicke Jan-Philipp Küppers and Tamara Reinicke
  • Chair of Product Development, Universität Siegen, Paul-Bonatz-Str. 9-11, 57076 Siegen, Germany

Abstract. Accurate modeling of the dynamic stall remains a challenge for the design and construction of turbine blades and helicopter rotors. At the same time, wind turbines, for instance, are becoming steadily larger, further increasing the demands on their structure and necessitating even more detailed modeling of the forces at hand. The primarily used (semi-)empirical models today have a long research history and are invariably based on phase-averaged data from oscillating blade pitch experiments. However, much potential for more accurate modeling of uncertainties and force peaks is wasted here, since averaging blurs many features of the response signals. Even computational fluid dynamics can help little in this regard, since the Reynolds-averaged Navier-Stokes equations used in practice cannot account for cycle variations, and scale-resolving models require extremely large amounts of computational resources. This paper presents an approach for a fully stochastic machine learning model that can nevertheless simulate these critical properties. Aerodynamic coefficients are compared with experimental data for different test cases. It is shown that synthetic force profiles can be generated which cannot be distinguished from the experimental data visually and are very close to them in the frequency spectrum. Additionally, attention is drawn to the difficulty of evaluating such a model, as traditional error metrics are of little use. A combination of Dynamic Time Warping and the Earth Mover Distance provides a robust solution for this problem.

Jan-Philipp Küppers and Tamara Reinicke

Status: open (until 31 May 2022)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on wes-2022-13', Galih Bangga, 14 May 2022 reply

Jan-Philipp Küppers and Tamara Reinicke

Jan-Philipp Küppers and Tamara Reinicke

Viewed

Total article views: 171 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
123 42 6 171 2 1
  • HTML: 123
  • PDF: 42
  • XML: 6
  • Total: 171
  • BibTeX: 2
  • EndNote: 1
Views and downloads (calculated since 07 Apr 2022)
Cumulative views and downloads (calculated since 07 Apr 2022)

Viewed (geographical distribution)

Total article views: 171 (including HTML, PDF, and XML) Thereof 171 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 20 May 2022
Download
Short summary
Airfoils play a major role in the technical harnessing of energy from currents such as wind and water. When the angle of attack of a wing changes dynamically, the forces on the wing often change more than would have been assumed from static measurements alone. Since these dynamic forces have a strong influence e.g. on the performance of airplanes and wind turbines, a neural network-based model was created that can predict these loads and their stochastic fluctuations.