At present, large-eddy simulations (LES) of turbulent flames with multi-species finite-rate kinetics is computationally infeasible due to the enormous cost associated with computation of reaction kinetics in 3D flows. In a recent study, In-Situ Adaptive Tabulation (ISAT) and Artificial Neural Network (ANN) methodologies were developed for computing finite-rate kinetics in a cost effective manner. Although ISAT reduces the cost of direct integration considerably, the ISAT tables require significant on-line storage in memory and can continue to grow over multiple flow-through times (an essential feature in LES). Hence, direct use of ISAT in LES may not be practical, especially in parallel solvers. In this study, a storage-efficient Artificial Neural Network (ANN) is investigated for LES application. Preliminary studies using ANN to predict freely propagating turbulent premixed flames over a range of operational parameters are described and issues regarding the implementation of such ANNs for engineering LES are discussed.
DeepM&Mnet for hypersonics: Predicting the coupled flow and finite-rate chemistry behind a normal shock using neural-network approximation of operators
