Nonlinear control for hypersonic vehicles based on RCMAC disturbance observer

In virtue of the nonlinearity approximating ability and self learning ability of recurrent cerebella model neural network (RCMAC), an adaptive nonlinear control strategy combined with feedback linearization and backstepping method is established and adopted to design controller of high-speed reentry vehicle. An RCMAC disturbance observer (RCDO) is developed to deal with uncertainties in the system, and the backstepping method is utilized to design pseudo linear terms where signal functions are presented to estimate the upper bound of approximation errors. The weights adjusting law is derived according to Lyapunov stability theory, which can guarantee the boundedness of all signals in the system. Six degrees of freedom simulation results demonstrate the effectiveness and robustness of the proposed approach.