The aim of this work is to apply and analyze machine learning methods for uncertainty quantification of turbulence models. In this work we investigate the classical and data-driven variants of the eigenspace perturbation method. This methodology is designed to estimate the uncertainties related to the shape of the modeled Reynolds stress tensor in the Navier-Stokes equations for Computational Fluid Dynamics (CFD). The underlying methodology is extended by adding a data-driven, physics-constrained machine learning approach in order to predict local perturbations of the Reynolds stress tensor. Using separated two-dimensional flows, we investigate the generalization properties of the machine learning models and shed a light on impacts of applying a data-driven extension.


    Access

    Download


    Export, share and cite



    Title :

    Applicability of machine learning in uncertainty quantification of turbulence models


    Contributors:

    Publication date :

    2022-10-01


    Type of media :

    Miscellaneous


    Type of material :

    Electronic Resource


    Language :

    English




    Applicability of machine learning in uncertainty quantification of turbulence models

    Matha, Marcel / Kucharczyk, Karsten | German Aerospace Center (DLR) | 2022

    Free access


    Fusing Physics and Machine Learning in Uncertainty Quantification

    Geoffrey Bomarito / P Leser / J Warner et al. | NTRS


    Machine Learning for Uncertainty Quantification: Trusting the Black Box

    J. Warner / G. Bomarito / P. Leser et al. | NTIS | 2022


    Machine Learning based Uncertainty Quantification for Wind- Tracking Algorithms

    Su, Hui / Posselt, Derek / Nguyen, Hai et al. | NTRS | 2019