Generalization of machine-learned turbulent heat flux models applied to film cooling flows

TL;DR

This paper develops machine learning-based turbulent heat flux models that predict spatially varying turbulent Prandtl numbers to improve heat transfer predictions in film cooling flows, demonstrating better generalization over traditional models.

Contribution

Introduces machine learning models to predict non-uniform turbulent Prandtl numbers, enhancing the accuracy of heat flux modeling in film cooling flows beyond conventional isotropic models.

Findings

ML models successfully predict non-uniform Pr_t fields.

Models generalize well to unseen flow conditions.

Visualization aids in understanding model performance.

Abstract

The design of film cooling systems relies heavily on Reynolds-Averaged Navier-Stokes (RANS) simulations, which solve for mean quantities and model all turbulent scales. Most turbulent heat flux models, which are based on isotropic diffusion with a fixed turbulent Prandtl number ($Pr_t$), fail to accurately predict heat transfer in film cooling flows. In the present work, machine learning models are trained to predict a non-uniform $Pr_t$ field, using various datasets as training sets. The ability of these models to generalize beyond the flows on which they were trained is explored. Furthermore, visualization techniques are employed to compare distinct datasets and to help explain the cross-validation results.