Kernel-smoothed proper orthogonal decomposition (KSPOD)-based emulation for prediction of spatiotemporally evolving flow dynamics

TL;DR

This paper introduces a kernel-smoothed POD (KSPOD) method that significantly accelerates the prediction of complex flow dynamics, enabling rapid design exploration with high accuracy compared to traditional high-fidelity simulations.

Contribution

The study develops a novel KSPOD-based surrogate model that improves upon previous CPOD methods by incorporating kernel smoothing and kriging, greatly enhancing prediction efficiency and fidelity.

Findings

KSPOD model accurately captures spatiotemporal flow dynamics.

Prediction speed is 42,000 times faster than high-fidelity simulations.

Model effectively supports rapid design exploration.

Abstract

This interdisciplinary study, which combines machine learning, statistical methodologies, high-fidelity simulations, and flow physics, demonstrates a new process for building an efficient surrogate model for predicting spatiotemporally evolving flow dynamics. In our previous work, a common-grid proper-orthogonal-decomposition (CPOD) technique was developed to establish a physics-based surrogate (emulation) model for prediction of mean flowfields and design exploration over a wide parameter space. The CPOD technique is substantially improved upon here using a kernel-smoothed POD (KSPOD) technique, which leverages kriging-based weighted functions from the design matrix. The resultant emulation model is then trained using a dataset obtained through high-fidelity simulations. As an example, the flow evolution in a swirl injector is considered for a wide range of design parameters and operating conditions. The KSPOD-based emulation model performs well, and can faithfully capture the spatiotemporal flow dynamics. The model enables effective design surveys utilizing high-fidelity simulation data, achieving a turnaround time for evaluating new design points that is 42,000 times faster than the original simulation.