Applying deep reinforcement learning to active flow control in turbulent conditions

TL;DR

This paper demonstrates that deep reinforcement learning can effectively control turbulent flow around a cylinder at Re=1000, achieving significant drag reduction despite increased flow complexity, marking a milestone in turbulent flow control.

Contribution

First successful application of deep reinforcement learning for active flow control in weak turbulent conditions, advancing the field towards turbulent flow regimes.

Findings

Achieved around 30% drag reduction at Re=1000

DRL requires more episodes to learn effective control strategies

Reduced turbulent fluctuations and elongated recirculation bubble

Abstract

Machine learning has recently become a promising technique in fluid mechanics, especially for active flow control (AFC) applications. A recent work [J. Fluid Mech. (2019), vol. 865, pp. 281-302] has demonstrated the feasibility and effectiveness of deep reinforcement learning (DRL) in performing AFC over a circular cylinder at $Re = 100$, i.e., in the laminar flow regime. As a follow-up study, we investigate the same AFC problem at an intermediate Reynolds number, i.e., $Re = 1000$, where the turbulence in the flow poses great challenges to the control. The results show that the DRL agent can still find effective control strategies, but requires much more episodes in the learning. A remarkable drag reduction of around $30\%$ is achieved, which is accompanied by elongation of the recirculation bubble and reduction of turbulent fluctuations in the cylinder wake. To our best knowledge, this study is the first successful application of DRL to AFC in weak turbulent conditions. It therefore sets a new milestone in progressing towards AFC in strong turbulent flows.