Abstract
A new identification approach based on an over-sampling scheme is proposed for a Hammerstein model which consists of a nonlinear element followed by a linear dynamic model. Making use of an observation set of the system input and over-sampled output, the unknown linear transfer function model can be identified independently of identification of the nonlinear element. Therefore, it can be clarified that the consistency of the parameter estimates of the linear dynamic part is assured. The nonlinear element is given by a mapping between a given input and recovered intermediate input. The prior information of the nonlinear element is not necessary in the new algorithm.
