Score: 0

Discovering Flow Separation Control Strategies in 3D Wings via Deep Reinforcement Learning

Published: September 12, 2025 | arXiv ID: 2509.10185v1

By: R. Montalà , B. Font , P. Suárez and more

Potential Business Impact:

Makes airplane wings fly better with less drag.

Business Areas:
Drone Management Hardware, Software

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.

Country of Origin
🇪🇸 Spain

Page Count
6 pages

Category
Computer Science:
Computational Engineering, Finance, and Science