论文部分内容阅读
The controller design for a near-space hypersonic vehicle (NHV) is challenging due to its plant uncertainties and sensitivity to atmospheric disturbances such as gusts and turbulence. This paper first derives 12 states equations of NHVs subjected to variable wind field, and presents a novel recurrent neural network (RNN) control method for restraining atmospheric disturbances. The method devises a new B-spline recurrent functional link network (BRFLN) and combines it with the nonlinear generalized predictive control (NGPC) algorithm. Moreover, the proportional-derivative (PD) correction BRFLN is proposed to approximate atmo- spheric disturbances in flight. The weights of BRFLN are online tuned by the adaptive law based on Lyapunov stability theorem. Finally, simulation results show a satisfactory performance for the attitude tracking of the NHV in the mesosphere, and also illustrate the controller’s robustness to wind turbulence.
The controller design for a near-space hypersonic vehicle (NHV) is challenging due to its plant uncertainties and sensitivity to atmospheric disturbances such as gusts and turbulence. This paper first derives 12 states equations of NHVs subjected to variable wind field, and presents a novel recurrent neural network (RNN) control method for restraining atmospheric disturbances. The method devises a new B-spline recurrent functional link network (BRFLN) and ways it with the nonlinear generalized predictive control (NGPC) algorithm. ) The weights of BRFLN are online tuned by the adaptive law based on Lyapunov stability theorem. Finally, simulation results show a satisfactory performance for the attitude tracking of the NHV in the mesosphere, and also illustrate the controller’s robustness to wind turbulence.