A Posteriori Evaluation of a Physics-Constrained Neural Ordinary Differential Equations Approach Coupled with CFD Solver for Modeling Stiff Chemical Kinetics

arXiv:2312.00038v3 Announce Type: replace-cross
Abstract: The high computational cost associated with solving for detailed chemistry poses a significant challenge for predictive computational fluid dynamics (CFD) simulations of turbulent reacting flows. These models often require solving a system of coupled stiff ordinary differential equations (ODEs). While deep learning techniques have been experimented with to develop faster surrogate models, they often fail to integrate reliably with CFD solvers. This instability arises because deep learning methods optimize for training error without ensuring compatibility …

abstract arxiv cfd challenge chemistry computational cost cs.lg differential dynamics evaluation fluid dynamics modeling ordinary physics physics.chem-ph physics.comp-ph physics.flu-dyn predictive simulations solver type