Subspace Identification of Closed-loop Errors-in-variables Systems

This paper studies an identification method for errors-in-variables (EIV) systems governed by an observer based state feedback control law. Due to the input and output measurement noises, traditional identification methods are typically inapplicable in most cases. In order to estimate such a closed-loop EIV system, a coprime factor (CF) model for the true plant is first identified from the available reference, input and output measurements by using the subspace identification method and then a plant estimation model is able to be extracted from the identified CF model. Finally, a numerical simulation is given to show the effectiveness of the studied identification method.