Identification approach for nonlinear systems based on particle swarm optimization

An identification approach is proposed for a single-input and single-output nonlinear dynamic system of discrete time.In this method,the improved universal model with error correcting is taken as the structure model of the system,and the particle swarm optimization(PSO) algorithm is adopted to optimize the time-varying characteristic parameter and the error correcting coefficient.The model after optimization can approximate the nonlinear system.This method is simple and easy to implement.The simulation results of Box-Jenkins gas furnace data etc.and the analysis of the model show the effectiveness of the method.