Adaptive Vibration Control for Two-Stage Bionic Flapping Wings Based on Neural Network Algorithm

Abstract

Vibration control is of critical importance for bionic flapping-wing robotic aircraft and autonomous ornithopter applications. Focused on the two-stage bionic flapping wings of the aircraft, which is a rigid-flexible coupling mechanism with light weight and low energy consumption, this paper firstly establishes the visualization model of the rigid-flexible coupled bionic flapping wing by the advanced system-level modeling software MapleSim. A novel adaptive vibration controller based on neural network (NN) algorithm is subsequently proposed to compensate the system uncertainties. The proposed method can successfully suppress the vibration of the flapping wing while accurately track the desired trajectory. Furthermore, the semi-global uniformly ultimately boundness (SGUUB) of the closed-loop system is proved through the Lyapunov's direct method. Finally, co-simulation results from the advanced system-level modeling software MapleSim and Matlab/Simulink validate the effectiveness of the proposed method.