Fuzzy Neural Network based Sliding Mode Control for Hypersonic Vehicles

According to the air-breathing hypersonic vehicle(AHV) model with perturbation of aerodynamic coefficients and uncertain parameters in the system, taking into account the problems of aerodynamic co-efficients approximation and uncertain parameter identification, fuzzy function(FF) and Radial Basis Neural Network(RBNN) based sliding mode control is proposed. AHV control model has the characteristics of multivariable, strong coupling and nonlinear. Applying the powerful function approximation function of fuzzy function to approach the aerodynamic coefficient, using RBNN self-learning identification ability to identify the system uncertain parameters, combined with sliding mode variable structure control, to eliminate the aircraft's buffeting problem to some extent and improve the robustness of the system. Simulation results show that the system can maintain stability after adding velocity step instructions and altitude step instructions, and has strong robustness to uncertain parameters, and overcome the chattering problem.