Shocks Under Control: Taming Transonic Compressible Flow over an RAE2822 Airfoil with Deep Reinforcement Learning

A study published on November 12, 2025, explores the use of deep reinforcement learning (DRL) to control transonic compressible flow over an RAE2822 airfoil at a Reynolds number of 50,000. The research addresses complex shock-boundary layer interactions and aims to improve aerodynamic performance. By employing synthetic jet actuation and a high-fidelity computational fluid dynamics (CFD) solver, the DRL agent autonomously develops effective control strategies. The results show a significant reduction in drag by 13.78% and an increase in lift by 131.18%, leading to a 121.52% improvement in the lift-to-drag ratio. This advancement in managing complex flow dynamics is crucial for enhancing the efficiency of aerodynamic systems.