Application and extension of a data-driven turbulence modeling method using Machine Learning
P. Khurana (TU Delft - Aerospace Engineering)
Cornelia Grabe – Mentor (Deutsches Zentrum für Luft- und Raumfahrt (DLR))
R. P. Dwight – Mentor (TU Delft - Aerodynamics)
Florian Jäckel – Mentor (Deutsches Zentrum für Luft- und Raumfahrt (DLR))
More Info
expand_more
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.
Abstract
In recent years, many data-driven approaches which leverage high-fidelity reference data have been developed to augment the performance of Reynolds Averaged Navier–Stokes (RANS) turbulence models by providing an improved closure to the governing fluid flow equations. The goal of this M.Sc. thesis is to apply and extend one such data-driven approach, “Field Inversion and Machine Learning”, to improve the negative Spalart-Allmaras turbulence model, with specific application to the shock-induced boundary layer separation on a 2D airfoil profile. Field inversion procedure results in a corrective, spatially distributed discrepancy field for the baseline RANS model. Machine learning algorithms are trained on an appropriately chosen set of flow features from the field inversion solution. This work’s primary objectives are to identify flow features relevant to shock-induced flow separation. The improved RANS model is tested on unseen flow conditions to evaluate the generalisation capability of the machine learning augmentation.