Adaptive state tracking

The problem of adaptive state tracking is considered, where a specified state is required to follow the reference input signal. It is assumed that the system is completely controllable and observable, but the particular state is not directly available for measurement and the measurements are contaminated with stochastic noise. It is also assumed that there is little prior knowledge of the reference input, and its parameters have to be detected by the control system. The recursive prediction error method is used for joint estimation of the parameters and states of the process to be controlled. The controller design is based on the placement of the poles and zeros of the state tracking error transfer function. As a result, adaptive state tracking is obtained for arbitrary external reference signals.