Fractional Hammerstein system identification using polynomial non-linear state space model

Fractional systems are known to model complex dynamics with a reduced number of parameters. This paper deals with identification of discrete fractional order systems based on non-linear Hammerstein models. Such systems consist of a static non-linear block followed by a linear dynamic system. The polynomial non-linear state space equations (PNLSS) are used to represent the fractional Hammerstein system and an output error identification method is developed. Different simulations test the method fitting ability to approximate the non linear fractional system behaviour at various signal to noise ratios.