Deep Dynamical Modeling and Control of Unsteady Fluid Flows

TL;DR

This paper introduces a Koopman theory-based learning approach to model and control unsteady fluid flows, enabling stable predictions and effective vortex shedding suppression using model predictive control.

Contribution

It presents a novel method for learning fluid dynamics directly from CFD data and applying model predictive control for flow stabilization.

Findings

Stable dynamical models accurately predict flow evolution.

Effective vortex shedding suppression achieved.

Demonstrates the feasibility of learning-based flow control.

Abstract

The design of flow control systems remains a challenge due to the nonlinear nature of the equations that govern fluid flow. However, recent advances in computational fluid dynamics (CFD) have enabled the simulation of complex fluid flows with high accuracy, opening the possibility of using learning-based approaches to facilitate controller design. We present a method for learning the forced and unforced dynamics of airflow over a cylinder directly from CFD data. The proposed approach, grounded in Koopman theory, is shown to produce stable dynamical models that can predict the time evolution of the cylinder system over extended time horizons. Finally, by performing model predictive control with the learned dynamical models, we are able to find a straightforward, interpretable control law for suppressing vortex shedding in the wake of the cylinder.