Entropy-Constrained Machine Learning with Residual Data Augmentation for Modeling Chemical Kinetics

2026-07-10

AI Summary

This work addresses the prohibitive computational cost of evaluating detailed chemical reaction source terms in high-fidelity direct numerical simulations (DNS) of turbulent combustion by proposing a physics-constrained machine learning surrogate model. The approach replaces expensive detailed chemistry calculations with predictions of reaction rates under a reduced thermochemical representation, while explicitly enforcing the second law of thermodynamics—specifically, non-negative entropy production—as a training constraint. Combined with residual-driven data augmentation and dimensionality reduction of the thermochemical state space, the model achieves high-fidelity generalization to unseen operating conditions without requiring additional CFD simulations. Validated on a two-dimensional lean methane–air flame DNS, the surrogate accurately reproduces results from full detailed chemistry at over an order-of-magnitude reduction in computational cost.

Abstract

We present a physics-constrained machine learning framework for accelerating the direct numerical simulation (DNS) of turbulent reacting flows. The model replaces the direct evaluation of detailed chemical source terms with a surrogate that predicts reaction rates from a reduced thermochemical state. To improve physical consistency, the second law of thermodynamics is incorporated as a training constraint by enforcing non-negative entropy generation, which restricts the evolution of the thermochemical state to physically admissible directions and improves stability during time integration. The approach is demonstrated on DNS of a two-dimensional planar lean premixed methane-air flame interacting with a turbulent flow field. The model reproduces detailed-chemistry results with high fidelity while achieving more than an order-of-magnitude reduction in computational cost. Furthermore, a residual-based synthetic data augmentation strategy enables parametric exploration by constructing new training data from the original dataset, allowing accurate simulation at new inlet conditions without additional detailed-chemistry CFD runs. These results demonstrate that thermodynamically constrained machine learning can provide reliable and computationally efficient surrogates for detailed chemistry in high-fidelity combustion simulations.

Problem

• chemical kinetics
• turbulent reacting flows
• computational cost
• physical consistency
• thermodynamic constraint

Innovation

• entropy-constrained learning
• residual data augmentation
• physics-informed machine learning
• chemical kinetics surrogate
• thermodynamic consistency