Neural adaptive control of air-breathing hypersonic vehicles robust to actuator dynamics.

This paper investigates the neural adaptive control problem for air-breathing hypersonic vehicles. For the velocity subsystem, a radial basis function neural network (RBFNN)-based adaptive controller is first designed, which employs the auxiliary variable to compensate for the saturation nonlinearity of the scramjet control command. For the altitude subsystem, an RBFNN-based controller addresses actuator constraints and dynamics using the model predictive control, as well as counteracts uncertainties and disturbances using the neural adaptive mechanism. The effectiveness of the proposed control is verified by simulations.