Deep reinforcement learning for active flow control in a turbulent separation bubble

作者：Bernat Font, Francisco Alcántara-Ávila, Jean Rabault, Ricardo Vinuesa, O. Lehmkuhl · 发表于：Nature Communications · 年份：2025 · DOI：10.1038/s41467-025-56408-6 · 被引用次数：48 · 研究领域：Fluid Dynamics and Turbulent Flows、Lattice Boltzmann Simulation Studies、Plasma and Flow Control in Aerodynamics

The control efficacy of deep reinforcement learning (DRL) compared with classical periodic forcing is numerically assessed for a turbulent separation bubble (TSB). We show that a control strategy learned on a coarse grid works on a fine grid as long as the coarse grid captures main flow features. This allows to significantly reduce the computational cost of DRL training in a turbulent-flow environment. On the fine grid, the periodic control is able to reduce the TSB area by 6.8%, while the DRL-based control achieves 9.0% reduction. Furthermore, the DRL agent provides a smoother control strategy while conserving momentum instantaneously. The physical analysis of the DRL control strategy reveals the production of large-scale counter-rotating vortices by adjacent actuator pairs. It is shown that the DRL agent acts on a wide range of frequencies to sustain these vortices in time. Last, we also introduce our computational fluid dynamics and DRL open-source framework suited for the next generation of exascale computing machines.