Applying Physics-Informed Enhanced Super-Resolution Generative Adversarial Networks to Turbulent Premixed Combustion and Engine-like Flame Kernel Direct Numerical Simulation Data

TL;DR

This paper enhances a physics-informed generative adversarial network to model turbulent premixed combustion, enabling accurate, cost-effective simulations of complex flame dynamics on coarser meshes.

Contribution

It introduces modifications to the PIESRGAN model to better incorporate physical effects like density changes in turbulent combustion modeling.

Findings

PIESRGAN accurately reproduces DNS data on coarser meshes.

The model reduces computational costs significantly.

It effectively captures cycle-to-cycle variations in flame kernels.

Abstract

Models for finite-rate-chemistry in underresolved flows still pose one of the main challenges for predictive simulations of complex configurations. The problem gets even more challenging if turbulence is involved. This work advances the recently developed PIESRGAN modeling approach to turbulent premixed combustion. For that, the physical information processed by the network and considered in the loss function are adjusted, the training process is smoothed, and especially effects from density changes are considered. The resulting model provides good results for a priori and a posteriori tests on direct numerical simulation data of a fully turbulent premixed flame kernel. The limits of the modeling approach are discussed. Finally, the model is employed to compute further realizations of the premixed flame kernel, which are analyzed with a scale-sensitive framework regarding their cycle-to-cycle variations. The work shows that the data-driven PIESRGAN subfilter model can very accurately reproduce direct numerical simulation data on much coarser meshes, which is hardly possible with classical subfilter models, and enables studying statistical processes more efficiently due to the smaller computing cost.