Keywords
combustion simulation
artificial neural networks
multi-layer networks
recursive approach
How to Cite
Abstract
Combustion process simulations are the key aspect enabling full-scale 3D simulations of advanced aerospace engines. This work studies solving chemical kinetics problems with artificial neural networks. The training datasets were generated by classical numerical methods. Choosing a multi-layer neural network architecture and fine-tuning its parameters, we developed a simple model that can solve the problem. The neural network obtained works is recursive, and by running many iterations it can predict the behavior of a chemical multimodal dynamic system.
References
C. Pantano. Direct simulation of non-premixed flame extinction in a methane–air jet with reduced chemistry, J. Fluid Mech. 514 (2004) 231–270. DOI: 10.1017/S0022112004000266.
N. N. Smirnov, V. B. Betelin, V. F. Nikitin, L. I. Stamov, D. I. Altoukhov. Accumulation of errors in numerical simulations of chemically reacting gas dynamics, Acta Astronautica 117(2015) 338–355. DOI: 10.1016/j.actaastro.2015.08.013.
N. N. Smirnov, V. B. Betelin, V. F. Nikitin, Y. G. Phylippov, J. Koo. Detonation engine fed by acetylene–oxygen mixture, Acta Astronautica 104 (2014) 134–146. DOI: 10.1016/j.actaastro.2014.07.019.
N. N. Smirnov, O. G. Penyazkov, K. L. Sevrouk, V. F. Nikitin, L. I. Stamov, V. V. Tyurenkova. Onset of detonation in hydrogen-air mixtures due to shock wave reflection inside a combustion chamber, Acta Astronautica 149 (2018) 77–92. DOI: 10.1016/j.actaastro.2018.05.024.
S. Lam, D. Goussis, Understanding complex chemical kinetics with computational singular perturbation, Symp. (Int.) Combust. 22 (1) (1989) 931–941. DOI: 10.1016/S0082-0784(89)80102-X.
U. Maas, S.B. Pope, Simplifying chemical kinetics: intrinsic low-dimensional manifolds in composition space, Combust. Flame 88 (3–4) (1992) 239–264. DOI: 10.1016/S0082-0784(89)80102-X. DOI: 10.1016/0010-2180(92)90034-M.
T. Lovas, Automatic generation of skeletal mechanisms for ignition combustion based on level of importance analysis, Combust. Flame 156 (7) (2009) 1348–1358. DOI: 10.1016/j.combustflame.2009.03.009.
J. Y. Chen, Development of reduced mechanisms for numerical modeling of turbulent combustion, Workshop on Numerical Aspects of Reduction in Chemical Kinetics, CERMICS-ENPC Cite Descartes—Champus sur Marne, France (1997)
C. Sung, C. Law, J.-Y. Chen, An augmented reduced mechanism for methane oxidation with comprehensive global parametric validation, Symp. (Int.) Combust. 27 (1) (1998) 295–304. DOI: 10.1016/S0082-0784(98)80416-5.
W. P. Jones, S. Rigopoulos, Reduced chemistry for hydrogen and methanol premixed flames via RCCE, Combust. Theor. Model. 11 (2007) 755–780. DOI: 10.1080/13647830701206866.
P. Koniavitis, S. Rigopoulos, W. P. Jones, A methodology for derivation of RCCE-reduced mechanisms via CSP, Combust. Flame 183 (2016) 126–143. DOI: 10.1016/j.combustflame.2017.05.010.
T. Lu, C. K. Law, Toward accommodating realistic fuel chemistry in large-scale computations, Prog. Energy Combust. Sci. 35 (2) (2009) 192–215. DOI: 10.1016/j.pecs.2008.10.002.
E. V. Mikhalchenko, V. F. Nikitin, V. D. Goryachev. Simulation of the operation of a detonation engine. Lecture notes in mechanical engineering, (2021).(in press)
S. B. Pope, Combust. Theory Modell. 1 (1) (1997) 41–63. DOI: 10.1080/713665229.
S. R. Tonse, N. W. Moriarty, N. J. Brown, M. Frencklach, Israel J. Chem. 39 (1) (1999) 97–106
M. Ihme, C. Schmitt, H. Pitsch Optimal artificial neural networks and tabulation methods for chemistry representation in LES of a bluff-body swirl-stabilized flame, Proceedings of the Combustion Institute 32 (2009) 1527–1535. DOI: 10.1016/J.PROCI.2008.06.100.
L. L. Franke, A. K. Chatzopoulos, S. Rigopoulos Tabulation of combustion chemistry via Artificial Neural Networks (ANNs): Methodology and application to LES-PDF simulation of Sydney flame L, Combustion and Flame 185 (2017) 245–260. DOI: 10.1016/j.combustflame.2017.07.014.
A. K. Chatzopoulos, S. Rigopoulos. A chemistry tabulation approach via Rate-Controlled Constrained Equilibrium (RCCE) and Artificial Neural Networks (ANNs), with application to turbulent non-premixed CH4/H2/N2 flames. Proceedings of the Combustion Institute 34 (2013) 1465–1473. DOI: 10.1016/j.proci.2012.06.057.
GRI-Mech Version 3.0 7/30/99 CHEMKINII format, at http://www.me.berke-ley.edu/gri_mech/.
CHEMKIN. A software package for the analysis of gas-phase chemical and plasma kinetics. CHE-036-1. Chemkin collection release 3.6. Reaction Design, September 2000.
E. A. Новиков. Исследование (m,2)-методов. решения жестких систем. Вычислительные технологии, 12 (5) (2007) 103-115.
V. B. Betelin, V. F. Nikitin, E. V. Mikhalchenko. 3D numerical modeling of a cylindrical RDE with an inner body extending out of the nozzle, Acta Astronautica 176 (2020) 628–646. DOI: 10.1016/j.actaastro.2020.03.051.
K. He, X. Zhang, S. Ren, J. Sun. Deep Residual Learning for Image Recognition, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016). DOI: 10.1109/CVPR.2016.90.