In order to improve the performance of particle swarm optimization(PSO) algorithm, an improved global particle swarm optimization(IGPSO) is presented. Based on a balance between exploitation and exploration ability, the global neighborhood search strategy and disturbance strategy are proposed to reduce the possibility of falling into local minima. Meanwhile, a perturbation operation with probabilities is implemented in the global best particle, which aims at accelerating the convergence speed. The test results demonstrate the effectiveness of the IGPSO algorithm in terms of accuracy, convergence speed, and nonparametric statistical significance when compared with other state-of-the-art intelligent algorithms.