Identification of Continuous-time Wiener Models Using Nonlinear Basis Function

Abstract

This paper presents an approach to deal with the identification of continuous-time Wiener systems, characterized by a series connection of a linear dynamic element and a static nonlinear element. The static nonlinear element is a sum of known basis functions and the linear dynamic element is a parametric rational transfer function. The proposed method is based on the projection of input-output data onto the finite dimensional parameter space whose basis is determined by the structure of an overparameterized representation of the Wiener model. Simulation results show the effectiveness of the proposed continuous-time identification method.