Adaptive Fuzzy Wavelet Neural Networks Control for Nonlinear MIMO Missile Autopilot

Abstract

In this paper, the integration of fuzzy set theory and wavelet neural networks is proposed to design an adaptive autopilot for BTT missile. Fuzzy wavelet neural networks (FWNN) can accurately approximate unknown dynamics of missile systems by using an adaptive learning algorithm. In addition, the proposed learning algorithm can on-line tune parameters of dilation and translation of fuzzy wavelet basis functions and hidden-to-output weights. To eliminate uncertainties including the inevitable approximation errors, a robust control law is proposed. A nonlinear six-degree-of-freedom BTT missile simulation is used to demonstrate the potential of this new control approach, which shows the overall adaptive control scheme can guarantee the global stability of the resulting closed-loop system in the sense that all signals involved are uniformly bounded.