Stability Convergence of Balloon Particle Swarm Optimizer and its Application on Vehicle Vibratory Response Modelling

Authors:	Feng Pan, Beijing Institute of Technology, China Chen Jie, Beijing Institute of Technology, China Gan Ming-Gang, Beijing Institute of Technology, China Cai Tao, Beijing Institute of Technology, China Tu Xu-yan, Beijing Institute of Technology, China
Topic:	2.4 Optimal Control
Session:	Optimal Control Theory and Design Methods
Keywords:	Particle Swarm Optimizer (PSO), Balloon PSO (BPSO), asymptotic stability, global convergence

Abstract

Particle Swarm Optimizer, PSO, exhibits good performance for optimization problem, although, PSO can not guarantee convergence of a global minimum, even a local minimum. However, there are some adjustable parameters and restrictive conditions which can affect performance of the algorithm. In this paper, a new adaptive PSO algorithm—Balloon PSO (BPSO) is proposed. The sufficient conditions for asymptotic stability of acceleration factor and inertia weight are deduced. Furthermore it is proved that BPSO is a global research algorithm. Simulation results of power spectral density (PSD) of vehicle vibratory signal estimation show the good performance of BPSO.