Novel adaptive neural control of flexible air-breathing hypersonic vehicles based on sliding mode differentiator

Abstract

A novel adaptive neural control strategy is exploited for the longitudinal dynamics of a generic flexible air-breathing hypersonic vehicle (FAHV). By utilizing functional decomposition method, the dynamics of FAHV is decomposed into the velocity subsystem and the altitude subsystem. For each subsystem, only one neural network is employed for the unknown function approximation. To further reduce the computational burden, minimal-learning parameter (MLP) technology is used to estimate the norm of ideal weight vectors rather than their elements. By introducing sliding mode differentiator (SMD) to estimate the newly defined variables, there is no need for the strict-feedback form and virtual controller. Hence the developed control law is considerably simpler than the ones derived from back-stepping scheme. Finally, simulation studies are made to illustrate the effectiveness of the proposed control approach in spite of the flexible effects, system uncertainties and varying disturbances.