Adaptive SDRE Based Boost-Phase Missile Autopilot Design Using Single and Modular Neural Networks

Abstract

Adaptive autopilot is designed using State-Dependent Riccati Equation (SDRE) and Neural Networks (NN), which guarantees the control performance during the boost-phase of missile. Rapid changes of parameters and aerodynamic uncertainties degrade the control performance of missile during the boost-phase. To deal with the nonlinearity of the missile system due to the rapid changes of parameters, SDRE technique is adopted to design baseline controller, and to compensate the effects of aerodynamic uncertainties, modular NN is proposed to design auxiliary controller. Numerical simulations are performed to demonstrate the performance of the proposed autopilot.