Adaptive neural control based on HGO for hypersonic flight vehicles

Abstract

This paper describes the design of adaptive neural controller for the longitudinal dynamics of a generic hypersonic flight vehicle (HFV) which are decomposed into two functional systems, namely the altitude subsystem and the velocity subsystem. For each subsystem, one adaptive neural controller is investigated based on the normal output-feedback formulation. For the altitude subsystem, the high gain observer (HGO) is taken to estimate the unknown newly defined states. Only one neural network (NN) is employed to approximate the lumped uncertain system nonlinearity during the controller design which is considerably simpler than the ones based on back-stepping scheme with the strict-feedback form. The Lyapunov stability of the NN weights and filtered tracking error are guaranteed in the semiglobal sense. Numerical simulation study of step response demonstrates the effectiveness of the proposed strategy in spite of system uncertainty.