Deep Learning to advance the Eigenspace Perturbation Method for Turbulence Model Uncertainty Quantification

02/11/2022

∙

The Reynolds Averaged Navier Stokes (RANS) models are the most common form of model in turbulence simulations. They are used to calculate Reynolds stress tensor and give robust results for engineering flows. But RANS model predictions have large error and uncertainty. In past, there has been some work towards using data-driven methods to increase their accuracy. In this work we outline a machine learning approach to aid the use of the Eigenspace Perturbation Method to predict the uncertainty in the turbulence model prediction. We use a trained neural network to predict the discrepancy in the shape of the RANS predicted Reynolds stress ellipsoid. We apply the model to a number of turbulent flows and demonstrate how the approach correctly identifies the regions in which modeling errors occur when compared to direct numerical simulation (DNS), large eddy simulation (LES) or experimental results from previous works.

READ FULL TEXT

Deep Learning to advance the Eigenspace Perturbation Method for Turbulence Model Uncertainty Quantification

Quantifying model form uncertainty in Reynolds-averaged turbulence models with Bayesian deep neural networks

Evaluation of physics constrained data-driven methods for turbulence model uncertainty quantification

Prediction of Reynolds Stresses in High-Mach-Number Turbulent Boundary Layers using Physics-Informed Machine Learning

Improved self-consistency of the Reynolds stress tensor eigenspace perturbation for uncertainty quantification

Multi-Task Learning based Convolutional Models with Curriculum Learning for the Anisotropic Reynolds Stress Tensor in Turbulent Duct Flow

A data-driven approach for the closure of RANS models by the divergence of the Reynolds Stress Tensor

Considering discrepancy when calibrating a mechanistic electrophysiology model

Deep Learning to advance the Eigenspace Perturbation Method for Turbulence Model Uncertainty Quantification

Related Research

Quantifying model form uncertainty in Reynolds-averaged turbulence models with Bayesian deep neural networks

Evaluation of physics constrained data-driven methods for turbulence model uncertainty quantification

Prediction of Reynolds Stresses in High-Mach-Number Turbulent Boundary Layers using Physics-Informed Machine Learning

Improved self-consistency of the Reynolds stress tensor eigenspace perturbation for uncertainty quantification

Multi-Task Learning based Convolutional Models with Curriculum Learning for the Anisotropic Reynolds Stress Tensor in Turbulent Duct Flow

A data-driven approach for the closure of RANS models by the divergence of the Reynolds Stress Tensor

Considering discrepancy when calibrating a mechanistic electrophysiology model