An efficient surrogate model for emulation and physics extraction of large eddy simulations

TL;DR

This paper introduces a new surrogate model for turbulent flow prediction in swirl injectors that leverages physical properties to achieve fast, accurate predictions and extract flow physics, significantly reducing computational costs.

Contribution

The novel surrogate model incorporates physical flow properties into statistical modeling, enabling rapid and accurate turbulence predictions and physics extraction from large simulation datasets.

Findings

Flow predictions in about an hour of computation.

Significant reduction in training and prediction time compared to existing emulators.

Ability to extract useful flow physics to guide further research.

Abstract

In the quest for advanced propulsion and power-generation systems, high-fidelity simulations are too computationally expensive to survey the desired design space, and a new design methodology is needed that combines engineering physics, computer simulations and statistical modeling. In this paper, we propose a new surrogate model that provides efficient prediction and uncertainty quantification of turbulent flows in swirl injectors with varying geometries, devices commonly used in many engineering applications. The novelty of the proposed method lies in the incorporation of known physical properties of the fluid flow as {simplifying assumptions} for the statistical model. In view of the massive simulation data at hand, which is on the order of hundreds of gigabytes, these assumptions allow for accurate flow predictions in around an hour of computation time. To contrast, existing flow emulators which forgo such simplications may require more computation time for training and prediction than is needed for conducting the simulation itself. Moreover, by accounting for coupling mechanisms between flow variables, the proposed model can jointly reduce prediction uncertainty and extract useful flow physics, which can then be used to guide further investigations.