Training convolutional neural networks to estimate turbulent sub-grid scale reaction rates

Corentin J Lapeyre (1) , Antony Misdariis (1) , Nicolas Cazard (1) , Denis Veynante (2) , Thierry Poinsot (3)

1 CERFACS - Centre Européen de Recherche et de Formation Avancée en Calcul Scientifique
2 EM2C - Laboratoire d'Énergétique Moléculaire et Macroscopique, Combustion
3 IMFT - Institut de mécanique des fluides de Toulouse

This work presents a new approach for premixed turbulent combustion modeling based on convolutional neural networks (CNN).1 We first propose a framework to reformulate the problem of subgrid flame surface density estimation as a machine learning task. Data needed to train the CNN is produced by direct numerical simulations (DNS) of a premixed turbulent flame stabilized in a slot-burner configuration. A CNN inspired from a U-Net architecture is designed and trained on the DNS fields to estimate subgrid-scale wrinkling. It is then tested on an unsteady turbulent flame where the mean inlet velocity is increased for a short time and the flame must react to a varying turbulent incoming flow. The CNN is found to efficiently extract the topological nature of the flame and predict subgrid-scale wrinkling, outperforming classical algebraic models.

Mots clés: Turbulent combustion; Deep learning; Flame surface density; Direct numerical simulation

Domaines: Mécanique des fluides [physics.class-ph]

Corentin J Lapeyre, Antony Misdariis, Nicolas Cazard, Denis Veynante, Thierry Poinsot. Training convolutional neural networks to estimate turbulent sub-grid scale reaction rates. Combustion and Flame, 2019, 203, pp.255-264. ⟨10.1016/j.combustflame.2019.02.019⟩. ⟨hal-02072920⟩