Identification of Wiener Fractional model using Self-Adaptive Velocity Particle Swarm Optimization

This paper deals with identification of discrete non-linear fractional order systems based on wiener models. Such systems consist of a linear dynamic block followed by a static non-linearity; in this study they are described using Polynomial Non Linear State Space(PNLSS) fractional models. Self Adaptive Velocity Particle Swarm Optimization (SAVPSO) is used; it is a modified PSO, which allows the constraints handling for solving constrained optimization problems (COPs). The wiener system identification is performed based on SAVPSO, and its efficiency is investigated on numerical simulations for different signal to noise rations.