Reinforcement Learning for Active Flow Control in Experiments
This work demonstrates RL's feasibility in experimental fluid mechanics, potentially enabling new optimal control strategies for complex applications.
The study tackled active flow control in turbulent fluid dynamics by using reinforcement learning to automatically discover control strategies for reducing drag or maximizing power efficiency on a cylinder setup, achieving results comparable to optimal static control after tens of experiments.
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.