Generalization Capability of Convolutional Neural Networks for Progress Variable Variance and Reaction Rate Subgrid-Scale Modeling

Victor Xing,Thierry Poinsot,Thomas Jaravel,Corentin Lapeyre

doi:10.3390/en14165096

Abstract

Deep learning has recently emerged as a successful approach to produce accurate subgrid-scale (SGS) models for Large Eddy Simulations (LES) in combustion. However, the ability of these models to generalize to configurations far from their training distribution is still mainly unexplored, thus impeding their application to practical configurations. In this work, a convolutional neural network (CNN) model for the progress-variable SGS variance field is trained on a canonical premixed turbulent flame and evaluated a priori on a significantly more complex slot burner jet flame. Despite the extensive differences between the two configurations, the CNN generalizes well and outperforms existing algebraic models. Conditions for this successful generalization are discussed, including the effect of the filter size and flame–turbulence interaction parameters. The CNN is then integrated into an analytical reaction rate closure relying on a single-step chemical source term formulation and a presumed beta PDF (probability density function) approach. The proposed closure is able to accurately recover filtered reaction rate values on both training and generalization flames.

Highlights

The first 38 constitute the training set for the convolutional neural network (CNN), while the 4 form the validation set and the final 4 are kept as a hold-out test set for the results shown below
The CNN was shown to be able to learn a model for c02, which is accurate on the test and generalization configurations
In the following, modeled values of c02 are incorporated in the presumed beta probability density function (PDF) approach detailed in Section 2.2 to form the PB-CNN model for ω F

Summary

Introduction

One of the main challenges for LES is the modeling of the SGS reaction source term To this end, recent studies have successfully used machine learning to train artificial neural networks as SGS models. Recent studies have successfully used machine learning to train artificial neural networks as SGS models They have been applied to the modeling of scalar dissipation rates [1], filtered density functions [2,3], wrinkling functions [4,5], and have been used to predict LES filtered reaction rates directly [6,7] or by deconvolution [8]. These studies have consistently shown that neural networks can outperform physical algebraic models on test cases identical or similar to their training configuration

Methods

Results

Discussion

Conclusion