Experimental Study on Closed-loop Flow Separation Control Utilizing Deep Q-Network over Fixed Angle-of-Attack Airfoil

Abstract

This paper experimentally investigates a closed-loop flow separation control system on a NACA 0015 airfoil using a DBD plasma actuator at the chord-Reynolds number of 63,000. The closed-loop control system is constructed utilizing the Deep Q-Network. The plasma actuator is installed to the surface of the airfoil at 5% of the chord length from the leading edge and driven with AC voltage. The time series data of surface pressure was used as the input data to the neural network, and the neural network is trained through the reinforce learning strategy (Q-learning) to select the optimum burst frequency of the actuator at angles of attacks of 12, 14, 14.5 degs. As a result, the trained neural network successfully selected the optimum burst frequency at 12 and 14 degs and controlled better than burst actuation with fixed F+ at angle of attack of 14.5deg.