The Stabilized Explicit Variable-Load Solver with Machine Learning Acceleration for the Rapid Solution of Stiff Chemical Kinetics

TL;DR

This paper introduces a novel hybrid explicit solver for stiff chemical kinetics that leverages machine learning for efficiency, achieving over 200 times faster solutions while maintaining accuracy in fluid dynamics simulations.

Contribution

A new explicit stabilized variable-load solver with machine learning acceleration for rapid stiff chemistry integration in CFD applications.

Findings

Over 200 times reduction in chemistry solution time.

10-28% additional time savings with ML hardware.

Maintains accuracy comparable to traditional methods.

Abstract

In this study, a fast and stable machine-learned hybrid algorithm implemented in TensorFlow for the integration of stiff chemical kinetics is introduced. Numerical solutions to differential equations are at the core of computational fluid dynamics calculations. As the size and complexity of the simulations grow, so does the need for computational power and time. Many efforts have been made to implement stiff chemistry solvers on GPUs but have not been highly successful because of the logical divergence in traditional stiff solver algorithms. Because of these constrains, a novel Explicit Stabilized Variable-load (STEV) solver has been developed. Overstepping due to the relatively large time steps is prevented by introducing limits to the maximum changes of chemical species per time step. To prevent oscillations, a discrete Fourier transform is introduced to dampen ringing. In contrast to conventional explicit approaches, a variable-load approach is used where each cell in the computational domain is advanced with its unique time step. This approach allows cells to be integrated simultaneously while maintaining warp convergence but finish at different iterations and be removed from the workload. To improve the computational performance of the introduced solver, specific thermodynamic quantities of interest were estimated using shallow neural networks in place of polynomial fits, leading to an additional 10% savings in clock time with minimal training and implementation requirements. However ML specific hardware could increase the time savings to as much as 28%. While the complexity of these particular machine learning models is not high by modern standards, the impact on computational efficiency should not be ignored. The results show a dramatic decrease in total chemistry solution time (over 200 times) while maintaining a similar degree of accuracy.