A Data-Driven Wall-Shear Stress Model for LES Using Gradient Boosted Decision Trees

Radhakrishnan, Sarath; Gyamfi, Lawrence Adu; Miro, Arnau; Font, B.; Calafell, Joan; Lehmkuhl, Oriol

A Data-Driven Wall-Shear Stress Model for LES Using Gradient Boosted Decision Trees

Conference paper (2021)

Authors

Sarath Radhakrishnan Barcelona Supercomputing Center

Lawrence Adu Gyamfi Barcelona Supercomputing Center

Arnau Miro Barcelona Supercomputing Center

B. Font Barcelona Supercomputing Center

Joan Calafell Barcelona Supercomputing Center

Oriol Lehmkuhl Barcelona Supercomputing Center

Affiliation

External organisation

Machine learning Turbulence XGBoost Wall models

To reference this document use:

http://resolver.tudelft.nl/uuid:d2c036b1-08f9-4011-adc4-01d6643a3886

More Info

expand_more

Published Date

2021

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Affiliation

External organisation

Abstract

With the recent advances in machine learning, data-driven strategies could augment wall modeling in large eddy simulation (LES). In this work, a wall model based on gradient boosted decision trees is presented. The model is trained to learn the boundary layer of a turbulent channel flow so that it can be used to make predictions for significantly different flows where the equilibrium assumptions are valid. The methodology of building the model is presented in detail. The experiment conducted to choose the data for training is described. The trained model is tested a posteriori on a turbulent channel flow and the flow over a wall-mounted hump. The results from the tests are compared with that of an algebraic equilibrium wall model, and the performance is evaluated. The results show that the model has succeeded in learning the boundary layer, proving the effectiveness of our methodology of data-driven model development, which is extendable to complex flows.