EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Estimating RANS model uncertainty using machine learning

Jan Heyse, Aashwin Mishra, Gianluca Iaccarino

Journal of the Global Power and Propulsion Society · 21.05.2021 · (May) · 1-14

DOI: 10.33737/jgpps/134643 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the Global Power and Propulsion Society, online erschienen am 21.05.2021. Verfasst von Jan Heyse und 2 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this work we present a machine-learning strategy developed to estimate the uncertainty introduced by a turbulence model for the prediction of a turbulent separated flows. The approach is based on the introduction of eigenvalue perturbations of the Reynolds stress anisotropy; the amount of perturbation is predicted by a random forest algorithm trained on high-fidelity simulations of the flow over a wavy wall. The proposed method is applied to the flow in an asymmetric diffuser and demonstrates how the approach correctly identifies the regions in which modeling errors occur and accurately quantifies the amount of errors when compared to experimental observations.

Zitieren

APA

Heyse, J., Mishra, A., & Iaccarino, G. (2021). Estimating RANS model uncertainty using machine learning. Journal of the Global Power and Propulsion Society, 1-14. https://doi.org/10.33737/jgpps/134643

Vancouver

Heyse J, Mishra A, Iaccarino G. Estimating RANS model uncertainty using machine learning. Journal of the Global Power and Propulsion Society. 2021:1-14. doi:10.33737/jgpps/134643

BibTeX
@article{Heyse2021,
  author = {Heyse, Jan and Mishra, Aashwin and Iaccarino, Gianluca},
  title = {Estimating RANS model uncertainty using machine learning},
  journal = {Journal of the Global Power and Propulsion Society},
  year = {2021},
  number = {May},
  pages = {1--14},
  doi = {10.33737/jgpps/134643}
}
Kostenlos starten →