Nonlinear System Identification of Hammerstien and Wiener Model Using Swarm Intelligence

Abstract

In this paper a novel approach for nonlinear system identification is proposed using particle swarm optimization (PSO) and quantum-behaved particle swarm optimization (QPSO). PSO and QPSO algorithm, the most successful and representative swarm intelligence optimization techniques, were demonstrated as an efficient global search method for complex surfaces. The proposed method formulates the nonlinear system identification as an optimization problem in parameter space, and then PSO and QPSO are used in the optimization process to find the optimal estimation of the system parameters respectively. Application to Hammerstein and Wiener nonlinear model, in which the nonlinear static subsystems and linear dynamic subsystems are separated in different order, is studied and the simulation results show that the identification by swarm intelligence is easy in computation and superior in accuracy.