Physics-based parameterized neural ordinary differential equations: prediction of laser ignition in a rocket combustor

TL;DR

This paper introduces a physics-based neural ODE framework for modeling laser ignition in rocket combustors, effectively predicting key quantities with limited data and satisfying physical constraints.

Contribution

The work develops a novel physics-based PNODE approach that accurately predicts ignition outcomes using high-dimensional parameters with fewer training samples.

Findings

PNODE outperforms kernel ridge regression and neural networks in accuracy.

PNODE requires fewer training samples to achieve reliable predictions.

The method successfully predicts temperature, pressure, and species concentrations during ignition.

Abstract

In this work, we present a novel physics-based data-driven framework for reduced-order modeling of laser ignition in a model rocket combustor based on parameterized neural ordinary differential equations (PNODE). Deep neural networks are embedded as functions of high-dimensional parameters of laser ignition to predict various terms in a 0D flow model including the heat source function, pre-exponential factors, and activation energy. Using the governing equations of a 0D flow model, our PNODE needs only a limited number of training samples and predicts trajectories of various quantities such as temperature, pressure, and mass fractions of species while satisfying physical constraints. We validate our physics-based PNODE on solution snapshots of high-fidelity Computational Fluid Dynamics (CFD) simulations of laser-induced ignition in a prototype rocket combustor. We compare the performance of our physics-based PNODE with that of kernel ridge regression and fully connected neural networks. Our results show that our physics-based PNODE provides solutions with lower mean absolute errors of average temperature over time, thus improving the prediction of successful laser ignition with high-dimensional parameters.