ADAPTIVE ROBUST NEURAL-NETWORK BASED CONTROL FOR BANK-TO-TURN MISSILE AUTOPILOT

摘要

In this paper, an adaptive robust neural-network based control approach which exploits the merits of sliding mode technique is proposed for For that scheme, a stable adaptive law is determined by Lyapunov theory, and the boundedness of all signals in the closed-loop system are guaranteed. No prior off-line training phase is needed. It is proved that the tracking errors converge to a neighborhood of zero. The simulation results have shown the satisfactory performance.