Quantum reinforcement learning-based active flow control

TL;DR

This paper introduces a quantum reinforcement learning framework that uses variational quantum circuits combined with policy optimization to actively control fluid flow, demonstrating effectiveness in vortex suppression and drag reduction in simulations.

Contribution

The study develops a novel hybrid quantum-classical RL framework for active flow control, integrating VQCs with PPO to handle high-dimensional fluid dynamics problems efficiently.

Findings

QRL reduces mean drag and lift oscillations in simulations.

VQC enhances learning efficiency and robustness in RL tasks.

Flow control via QRL suppresses vortex shedding effectively.

Abstract

Active flow control remains a significant challenge due to the high-dimensional, nonlinear nature of fluid dynamics. Quantum machine learning may prove effective in addressing these issues, given that quantum computing possesses superiority over traditional computing in some extend. Thus, this study developed a quantum reinforcement learning (QRL) based active flow control framework, integrating variational quantum circuits (VQCs) with the proximal policy optimization (PPO) algorithm to learn a real time controller. Firstly, we tested the QRL in a CartPole problem. The QRL shows parameter efficiency and enhanced learning capability, indicating VQC acts as promising candidates for advancing RL, particularly in scenarios requiring both computational efficiency and robust performance. The active control of flow past a square circular cylinder at a Reynolds number of 100 was tested via QRL. Our hybrid architecture encodes high-dimensional flow states into a quantum policy network, which generates continuous blowing/suction actions on the cylinder surface, and thus suppress the vortex shedding to achieve drag reduction. Numerical simulations demonstrate the QRL successfully reduces the mean drag and attenuates lift oscillations. Flow field analysis confirms that QRL control effectively suppresses large-scale vortex shedding, leading to a narrower wake compared to the uncontrolled baseline. These results validate the potential of quantum-enhanced learning for tackling complex fluid dynamics problems. The proposed QRL framework establishes a promising blueprint for quantum-AI accelerated solutions in aerospace design, energy-efficient turbomachinery, and other applications involving sophisticated fluid-structure interactions.