Physics-guided surrogate learning enables zero-shot control of turbulent wings

2026-04-10

AI Summary

This study addresses the significant drag induced by turbulent boundary layers on aircraft, a challenge exacerbated by multiscale dynamics, spatial heterogeneity, and prohibitive computational costs. The authors propose a reinforcement learning–based control strategy trained in channel flow configurations whose statistical properties are matched to those of the target wing’s boundary layer. Leveraging physics-informed surrogate learning and boundary layer statistics alignment, the method achieves zero-shot transfer—requiring no retraining on the actual wing—and reduces skin-friction and total drag by 28.7% and 10.7%, respectively, at a chord Reynolds number of $Re_c = 2 \times 10^5$. This performance surpasses existing opposition control techniques while reducing training costs by four orders of magnitude.

Technology Category

• Machine Learning: Reinforcement Learning
• Search and Optimization: Learning to Search
• Intelligent Robots: Behavior Learning & Control

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Turbulent boundary layers over aerodynamic surfaces are a major source of aircraft drag, yet their control remains challenging due to multiscale dynamics and spatial variability, particularly under adverse pressure gradients. Reinforcement learning has outperformed state-of-the-art strategies in canonical flows, but its application to realistic geometries is limited by computational cost and transferability. Here we show that these limitations can be overcome by exploiting local structures of wall-bounded turbulence. Policies are trained in turbulent channel flows matched to wing boundary-layer statistics and deployed directly onto a NACA4412 wing at $Re_c=2\times10^5$ without further training, being the so-called zero-shot control. This achieves a 28.7\% reduction in skin-friction drag and a 10.7\% reduction in total drag, outperforming the state-of-the-art opposition control by 40\% in friction drag reduction and 5\% in total drag. Training cost is reduced by four orders of magnitude relative to on-wing training, enabling scalable flow control.

Problem

• turbulent boundary layers
• drag reduction
• zero-shot control
• flow control
• adverse pressure gradients

Innovation

• physics-guided surrogate learning
• zero-shot control
• turbulent boundary layer
• reinforcement learning
• drag reduction