Real-time parameter identification for highly coupled nonlinear systems using adaptive particle swarm optimization

Abstract

The In this paper, an Adaptive Particle Swarm Optimization (APSO) method is proposed for parameter identification of highly coupled electromechanical sys-tems. Using some modifications on the APSO, better com-putational efficiency is achieved. In this way, the speed of real-time identification procedure is improved. In addition, to show the effectiveness of the proposed method, it is im-plemented on a real ball on plate setup and its dynamic model is achieved. Both the simulation and the experimen-tal results show that parameter identification of the pro-posed algorithm is significantly improved when compared with other existing identification methods based on the traditional PSO and Genetic Algorithm (GA).