Article: LES using artificial neural networks for chemistry representation Journal: Progress in Computational Fluid Dynamics, An International Journal (PCFD) 2005 Vol.5 No.7 pp.375 - 385 Abstract: In this work, a large-eddy simulation (LES) was performed using artificial neural networks (ANN) for chemistry representation. The case of Flame D, a turbulent non-premixed piloted methane/air flame, was chosen to validate this new strategy. A second LES utilising a classical structured chemistry table for a steady flamelet model was used for comparison. A Smagorinsky model applying the dynamic procedure by Germano to determine the Smagorinsky parameter was used for the subgrid stresses. It is shown that the new procedure yields approximately three orders of magnitude lower memory requirements, while the required CPU time for the application of the networks increases only little. The results obtained from the two simulations do not differ significantly. Furthermore, the smooth approximation of the chemistry table with the neural networks stabilises the LES of turbulent reactive flows and allows the application of advanced chemistry models with higher dimensionality. Inderscience Publishers - linking academia, business and industry through research

Title: LES using artificial neural networks for chemistry representation

Authors: Felix Flemming, Amsini Sadiki, Johannes Janicka

Addresses: Institute for Energy and Power Plant Technology, Darmstadt University of Technology, Petersenstr. 30, Darmstadt D 64287, Germany. ' Institute for Energy and Power Plant Technology, Darmstadt University of Technology, Petersenstr. 30, Darmstadt D 64287, Germany. ' Institute for Energy and Power Plant Technology, Darmstadt University of Technology, Petersenstr. 30, Darmstadt D 64287, Germany

Abstract: In this work, a large-eddy simulation (LES) was performed using artificial neural networks (ANN) for chemistry representation. The case of Flame D, a turbulent non-premixed piloted methane/air flame, was chosen to validate this new strategy. A second LES utilising a classical structured chemistry table for a steady flamelet model was used for comparison. A Smagorinsky model applying the dynamic procedure by Germano to determine the Smagorinsky parameter was used for the subgrid stresses. It is shown that the new procedure yields approximately three orders of magnitude lower memory requirements, while the required CPU time for the application of the networks increases only little. The results obtained from the two simulations do not differ significantly. Furthermore, the smooth approximation of the chemistry table with the neural networks stabilises the LES of turbulent reactive flows and allows the application of advanced chemistry models with higher dimensionality.

Keywords: artificial neural networks; ANNs; multi-layer perceptrons; large-eddy simulation; turbulent non-premixed combustion; chemistry representation; steady flamelets; turbulent combustion; subgrid stresses; turbulent reactive flows; advanced chemistry models.

DOI: 10.1504/PCFD.2005.007424

Progress in Computational Fluid Dynamics, An International Journal, 2005 Vol.5 No.7, pp.375 - 385

Published online: 18 Jul 2005 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: LES using artificial neural networks for chemistry representation

Keep up-to-date