Learning Physics-Based Reduced-Order Models for a Single-Injector Combustion Process

What is it about?

This paper presents a physics-based data-driven method to learn predictive reduced-order models (ROMs) from high-fidelity simulations, and illustrates it in the challenging context of a single-injector combustion process. The method combines the perspectives of model reduction and machine learning to identify a set of transformed physical variables that expose quadratic structure in the combustion governing equations, and then learns a quadratic ROM from the transformed snapshot data. This learning does not require access to or interface with the high-fidelity model implementation. Numerical experiments show that the ROM accurately predicts temperature, pressure, velocity, species concentrations, and the limit-cycle amplitude, with speedups of more than five orders of magnitude over high-fidelity models.

Featured Image