High-angle-of-attack uncommanded roll oscillations are dangerous and can cause significant challenges in flight control. This paper constructs a stability augmented system to suppress roll oscillations with nonzero mean roll angles in a canard-configuration model. To overcome the problem of weak traditional ailerons caused by large-scale flow separations at high angles of attack, spanwise blowing was used as fluid effectors to generate lateral control moments. The control effect and mechanism of spanwise blowing were analyzed through the results of force measurements and experiments using particle image velocimetry (PIV), respectively. Spanwise blowing generates the control moment by changing the trajectory of the leading-edge vortex and delaying vortex breakdown. Subsequently, virtual flight experiment technology was used to train a policy for the stability augmented system based on real-world data using deep reinforcement learning in the wind tunnel. When testing the agent, the transient flow fields around the model were obtained synchronously using time-resolved particle image velocimetry (TR-PIV). The test results showed that the agent learned to keep the model roll at approximately zero by effectively controlling the flow field using fluid effectors.

The rapid development of artificial intelligence (AI) brings new ideas for various industries. Among various AI technologies, deep reinforcement learning is a self-evolving technique that is suitable for solving complex control and decision-making problems. on the other hand, the complex dynamic characteristics of aircraft at high angles of attack leads to the emergence of uncommanded motions, making flight dangerous. Therefore, this paper focuses on the suppression of uncommanded motion of canard configuration at high angles of attack, using deep reinforcement learning. The technology of jet flow control was used to play the role of aileron. After enough training in wind tunnel, the AI finally learned how to suppress the uncommanded motion of the aircraft and showed interesting behavioral logic. The results of this paper show that deep reinforcement learning can be used for complex control problems in aerospace science; however, the practicality of deep reinforcement learning in real flight needs further verification.