Nonlinear system identification of fractional Wiener models

The Wiener model is a case of block-oriented model, which is suitable for modeling a large class of nonlinear systems. It consists of the cascade of two parts, where a linear dynamic part is followed by a static nonlinear part. On the other hand, fractional order models have gained increasing interest over the last decades due to their better representation of some physical phenomena. In this paper, the fractional Wiener system identification is aimed. The polynomial nonlinear fractional state space equations are used to describe the nonlinear model. Thus, the extension of an output error method (Levenberg Marquard algorithm) is developed to estimate the fractional Wiener system. The efficiency of the identification method is evaluated and confirmed by simulation examples.