Enhancing airfoil performance through reinforcement learning-based closed loop flow control

We perform a reinforcement learning (RL)-based closed-loop flow control to enhance the lift-to-drag ratio of a wing section with an NLF(1)-0115 airfoil at angles of attack of 5 degrees and 10 degrees.The effects of key control parameters, including actuation location, observed state, reward function, and control actuation update interval, are evaluated at a chord length-based Reynolds number of Re=20,000. Results show that all parameters significantly influence control performance, with the update interval playing a particularly critical role. Properly chosen update intervals introduce a broader spectrum of actuation frequencies, enabling more effective interactions with a wider range of flow structures and contributing to improved control effectiveness. The optimally trained RL controller is further evaluated in a three-dimensional numerical setup at the same Reynolds number. Actuation is applied using both spanwise-uniform and spanwise-varying control profiles. The results demonstrate that the pretrained controller, combined with a physics-informed spanwise distribution, achieves substantial performance gains. The results show that using a pretrained RL-based control strategy is adaptable to larger or more complicated flows. Specifically, it can be applied to more complex airfoil flow scenarios than the one it was originally trained on.