2020/05/28 by Zeinab Shadram, Tuan M. Nguyen, Shadram, Zeinab +5 · 2 citations
Engineering · #Combustion and flame dynamics #FOS: Physical sciences #Fluid Dynamics (physics.flu-dyn) #Heat transfer and supercritical fluids #Rocket and propulsion systems research
paper · pdf · doi:10.48550/arxiv.2005.14167
openalex publication_date 2020/05/28 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
In this paper, neural network (NN)-based models are generated to replace\nflamelet tables for sub-grid modeling in large-eddy simulations of a\nsingle-injector liquid-propellant rocket engine. In the most accurate case,\nseparate NNs for each of the flame variables are designed and tested by\ncomparing the NN output values with the corresponding values in the table. The\ngas constant, internal flame energy, and flame heat capacity ratio are\nestimated with 0.0506%, 0.0852%, and 0.0778% error, respectively. Flame\ntemperature, thermal conductivity, and the coefficient of heat capacity ratio\nare estimated with 0.63%, 0.68%, and 0.86% error, respectively. The progress\nvariable reaction rate is also estimated with 3.59% error. The errors are\ncalculated based on mean square error over all points in the table. The\ndeveloped NNs are successfully implemented within the CFD simulation, replacing\nthe flamelet table entirely. The NN-based CFD is validated through comparison\nof its results with the table-based CFD.\n