High-lift Wing Separation Control via Bayesian Optimization and Deep Reinforcement Learning

2026-05-12

AI Summary

This study addresses the challenge of flow separation-induced stall at high angles of attack in high-lift airfoils, which significantly degrades aerodynamic efficiency. For the first time, it systematically compares open-loop Bayesian optimization (BO) and closed-loop deep reinforcement learning (DRL) for synthetic jet-based active flow control in a high-Reynolds-number, high-lift configuration, integrating wall-resolved large-eddy simulation with distributed sensor feedback. The work highlights the critical influence of reward function design on DRL performance: BO achieves a 10.9% improvement in aerodynamic efficiency—reducing drag by 9.7% while maintaining lift—whereas a penalty-dominated DRL formulation yields only marginal gains. These findings provide crucial insights for selecting and designing intelligent flow control strategies.

Abstract

This study investigates active flow control (AFC) of a 30P30N high-lift wing at a Reynolds number Re$_c$ = 450,000 and angle of attack $α$ = 23$^\circ$ using wallresolved large-eddy simulations (LES). Two optimization strategies are explored: open-loop Bayesian optimization (BO) and closed-loop deep reinforcement learning (DRL), both targeting the mitigation of stall and the improvement of aerodynamic efficiency via synthetic jets on the slat, main, and flap elements. The uncontrolled configuration was validated against literature data, confirming the reliability of the LES setup. The BO framework successfully identified steady jet velocities that increased efficiency by +10.9% through a -9.7% drag reduction while maintaining lift. In contrast, the DRL agent, despite leveraging instantaneous flow information from distributed sensors, achieved only minor improvements in lift and drag, with negligible efficiency gain. Training analysis indicated that the penalty-dominated reward constrained exploration. These results highlight the need for carefully designed rewards and computational acceleration strategies in DRL-based flow control at high Reynolds numbers.

Problem

• flow separation
• high-lift wing
• stall mitigation
• aerodynamic efficiency
• active flow control

Innovation

• Bayesian Optimization
• Deep Reinforcement Learning
• Active Flow Control
• High-lift Wing
• Large-Eddy Simulation