Parameter Identification of Nonlinear Systems Using a Particle Swarm Optimization Approach

This paper applies a particle swarm optimization (PSO) approach to the parameter identification for a class of nonlinear systems. In the PSO optimization process, the unknown system parameters are arranged in the form of a parameter vector (i.e. a particle), and the PSO algorithm employs the velocity updating and position updating formulas to an initial population, which is constituted by a great number of particles, such that the excellent particle is generated. The proposed algorithm manipulates the parameter vectors directly as real numbers rather than binary strings. Therefore, to implement the PSO algorithm in computer codes becomes fairly straightforward. In this study, the PSO algorithm is applied to estimate the parameters of the Genesio-Tesi nonlinear chaotic systems. The estimation performance of the PSO algorithm is verified by examining different sets of random initial populations under the presence of measurement noises. The simulation results reveal that the PSO algorithm provides a simple and effective means of solving parameter estimation problem of nonlinear systems.