Discovering Flow Separation Control Strategies in 3D Wings via Deep Reinforcement Learning
By: R. Montalà , B. Font , P. Suárez and more
Potential Business Impact:
Makes airplane wings fly better with less drag.
In this work, deep reinforcement learning (DRL) is applied to active flow control (AFC) over a threedimensional SD7003 wing at a Reynolds number of Re = 60,000 and angle of attack of AoA = 14 degrees. In the uncontrolled baseline case, the flow exhibits massive separation and a fully turbulent wake. Using a GPU-accelerated CFD solver and multi-agent training, DRL discovers control strategies that enhance lift (79%), reduce drag (65%), and improve aerodynamic efficiency (408%). Flow visualizations confirm reattachment of the separated shear layer, demonstrating the potential of DRL for complex and turbulent flows.
Similar Papers
Deep Reinforcement Learning for Active Flow Control around a Three-Dimensional Flow-Separated Wing at Re = 1,000
Computational Engineering, Finance, and Science
Makes airplane wings fly better in strong winds.
Transfer learning-enhanced deep reinforcement learning for aerodynamic airfoil optimisation subject to structural constraints
Machine Learning (CS)
Designs better airplane wings for speed and strength.
Active Control of Turbulent Airfoil Flows Using Adjoint-based Deep Learning
Fluid Dynamics
Makes airplane wings fly better and use less fuel.