Abstract
A novel system identification algorithm for a linear discrete-time multivariable closed-loop system is proposed based on an output over-sampling scheme. If the feedback subsystem is operating with period T, the structure and parameters of forward and feedback subsystems can be determined simultaneously by using the over-sampled output data, which contain more information about the input to the forward subsystem. It can be used in both control area and social system dynamics even though neither the knowledge of the forward and feedback subsystems are known nor the observation of input to the forward subsystem can be available.
