Robust adaptive control using single-hidden-layer feedforward neural networks

This paper describes a hybrid approach to the problem of controlling a class of nonlinear systems in the face of both unknown nonlinearities and unmodeled dynamics. In the proposed methodology, neural networks with a single hidden-layer are used to parametrize unknown nonlinearities while dynamic nonlinear damping provides robustness to unmodeled dynamics. To illustrate the theoretical development, the authors present a longitudinal autopilot based on simplified nonlinear missile aerodynamics with first-order actuation.