Neural-network-based adaptive control of wing rock motion

Wing rock motion is mathematically described by a nonlinear differential equation with coefficients varying with angle of attack. In the paper, a neural-network-based adaptive control system is developed for wing rock motion control. The adaptive controller comprises a neural network controller and a compensation controller. The neural network controller using a recurrent neural network is utilized to approximate a nonlinear system dynamic function and the compensation controller is a compensator for the difference between the system dynamic function and the recurrent neural network. The online parameter adaptation laws are derived based on a Lyapunov function; thus the stability of the system can be guaranteed. Simulations are performed to illustrate the effectiveness of the proposed neural-network-based adaptive control system. Simulation results demonstrate that the proposed design method can achieve favorable control performances for wing rock motion control with completely unknown system dynamic function.