Active flow control strategies for three-dimensional bluff bodies are challenging to design, yet critical for industrial applications. Here we explore the potential of discovering novel drag-reduction strategies using deep reinforcement learning. We introduce a high-dimensional active flow control setup on a three-dimensional cylinder at Reynolds numbers (Re _D) from 100 to 400, spanning the transition to three-dimensional wake instabilities. The setup involves multiple zero-net-mass-flux jets and couples a computational fluid dynamics solver with a numerical multi-agent reinforcement learning framework based on the proximal policy optimization algorithm. Our results demonstrate up to 16% drag reduction at Re _D = 400, outperforming classical periodic control strategies. A proper orthogonal decomposition analysis reveals that the control leads to a stabilized wake structure with an elongated recirculation bubble. These findings represent the first demonstration of training on three-dimensional cylinders and pave the way toward active flow control of complex turbulent flows.

This study presents novel drag reduction active-flow-control (AFC) strategies for a three-dimensional cylinder immersed in a flow at a Reynolds number based on freestream velocity and cylinder diameter of ReD=3900. The cylinder in this subcritical flow regime has been extensively studied in the literature and is considered a classic case of turbulent flow arising from a bluff body. The strategies presented are explored through the use of deep reinforcement learning. The cylinder is equipped with 10 independent zero-net-mass-flux jet pairs, distributed on the top and bottom surfaces, which define the AFC setup. The method is based on the coupling between a computational-fluid-dynamics solver and a multi-agent reinforcement-learning (MARL) framework using the proximal-policy-optimization algorithm. This work introduces a multi-stage training approach to expand the exploration space and enhance drag reduction stabilization. By accelerating training through the exploitation of local invariants with MARL, a drag reduction of approximately 9% is achieved. The cooperative closed-loop strategy developed by the agents is sophisticated, as it utilizes a wide bandwidth of mass-flow-rate frequencies, which classical control methods are unable to match. Notably, the mass cost efficiency is demonstrated to be two orders of magnitude lower than that of classical control methods reported in the literature. These developments represent a significant advancement in active flow control in turbulent regimes, critical for industrial applications.

The aim of this study is to discover new active-flow-control (AFC) techniques for separation mitigation in a two-dimensional NACA 0012 airfoil at a Reynolds number of 3000. To find these AFC strategies, a framework consisting of a deep-reinforcement-learning (DRL) agent has been used to determine the action strategies to apply to the flow. The actions involve blowing and suction through jets at the airfoil surface. The flow is simulated with the numerical code Alya, which is a low-dissipation finite-element code, on a high-performance computing system. Various control strategies obtained through DRL led to 43.9% drag reduction, while others yielded an increase in aerodynamic efficiency of 58.6%. In comparison, periodic-control strategies demonstrated lower energy efficiency while failing to achieve the same level of aerodynamic improvements as the DRL-based approach. These gains have been attained through the implementation of a dynamic, closed-loop, time-dependent, active control mechanism over the airfoil.