Adaptive Neural Network Control for Missile Systems With Unknown Hysteresis Input

Most existing results do not take the effects of backlash hysteresis of actuators into account in a controller design of missile systems, but such hysteresis seems inevitable in practice. In this paper, a robust adaptive neural network (NN) control law for a missile system with unknown parameters and hysteresis input is proposed based on a backstepping technique. The controller is designed by introducing NN approximation, which can be adjusted by an adaptive law based on the backstepping approach. The developed NN controller does not require a priori knowledge of the unknown backlash hysteresis. In particular, unlike existing results on adaptive compensation for unknown backlash hysteresis, the sign of b is no longer needed. It is shown that the designed controller can ensure the stability and tracking performance of the closed-loop system.