|
Neural networks applications to combustion process simulation
B. V. Kryzhanovskya, N. N. Smirnovba, V. F. Nikitinab, Ia. M. Karandasheva, M. Yu. Malsagova, E. V. Mikhalchenkoba a Federal State Institution “Scientific Research Institute for System Analysis of the Russian Academy of Sciences”, Moscow, Russian Federation
b Lomonosov Moscow State University, Moscow, Russian Federation
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.
Keywords:
chemical kinetics, combustion simulation, artificial neural networks, multi-layer networks, recursive approach.
Citation:
B. V. Kryzhanovsky, N. N. Smirnov, V. F. Nikitin, Ia. M. Karandashev, M. Yu. Malsagov, E. V. Mikhalchenko, “Neural networks applications to combustion process simulation”, Russian Journal of Cybernetics, 2:4 (2021), 15–29
Linking options:
https://www.mathnet.ru/eng/uk86 https://www.mathnet.ru/eng/uk/v2/i4/p15
|
Statistics & downloads: |
Abstract page: | 49 | Full-text PDF : | 42 |
|