Reinforcement Learning for Active Flow Control in Experiments

03/06/2020

∙

We demonstrate experimentally the feasibility of applying reinforcement learning (RL) in flow control problems by automatically discovering active control strategies without any prior knowledge of the flow physics. We consider the turbulent flow past a circular cylinder with the aim of reducing the cylinder drag force or maximizing the power gain efficiency by properly selecting the rotational speed of two small diameter cylinders, parallel to and located downstream of the larger cylinder. Given properly designed rewards and noise reduction techniques, after tens of towing experiments, the RL agent could discover the optimal control strategy, comparable to the optimal static control. While RL has been found to be effective in recent computer flow simulation studies, this is the first time that its effectiveness is demonstrated experimentally, paving the way for exploring new optimal active flow control strategies in complex fluid mechanics applications.

READ FULL TEXT

Reinforcement Learning for Active Flow Control in Experiments

Gym-preCICE: Reinforcement Learning Environments for Active Flow Control

How to Control Hydrodynamic Force on Fluidic Pinball via Deep Reinforcement Learning

Comparative analysis of machine learning methods for active flow control

Symmetry reduction for deep reinforcement learning active control of chaotic spatiotemporal dynamics

Zermelo's problem: Optimal point-to-point navigation in 2D turbulent flows using Reinforcement Learning

Optimal control of point-to-point navigation in turbulent time-dependent flows using Reinforcement Learning

Reinforcement Learning reveals fundamental limits on the mixing of active particles

Reinforcement Learning for Active Flow Control in Experiments

Related Research

Gym-preCICE: Reinforcement Learning Environments for Active Flow Control

How to Control Hydrodynamic Force on Fluidic Pinball via Deep Reinforcement Learning

Comparative analysis of machine learning methods for active flow control

Symmetry reduction for deep reinforcement learning active control of chaotic spatiotemporal dynamics

Zermelo's problem: Optimal point-to-point navigation in 2D turbulent flows using Reinforcement Learning

Optimal control of point-to-point navigation in turbulent time-dependent flows using Reinforcement Learning

Reinforcement Learning reveals fundamental limits on the mixing of active particles