Numerical evaluation of Particle Swarm Optimization based identification for continuous-time systems

This paper is concerned with easy-to-use identification method for various types of continuous-time systems. First, it is shown how to identify continuous-time systems by using the Particle Swarm Optimization, which attracts a lot of attention recently in the evolutionary computation area due to its empirical evidence of its superiority in solving various non-convex problems. Second, its effectiveness is evaluated through numerical examples for various types of systems including closed loop and nonlinear ones. Furthermore, its performance for an open loop linear system is compared with one of the most powerful existing methods.