对微粒群算法进行改进,使之具有多峰寻优能力,并将其与山峰聚类法相结合,提出了基于改进的微粒群优化算法的山峰聚类算法(A Mountain Clustering Based on Improved PSO,MCBIPSO).文中给出了该方法的原理和计算步骤.仿真结果表明.该算法物理意义明确,用于基于密度的样本聚类时,计算简单快捷.能有效搜寻到数据样本空间的各个聚类中心.从而实现对数据样本的准确聚类. This paper improves the particle swarm optimization algorithm to make it have multi-peak optimization ability, and combines it with the mountain cluster method to propose a mountain clustering based on improved particle swarm optimization algorithm (A Mountain Clustering Based on Improved PSO, MCBIPSO The principle and calculating steps of the method are given in the paper.The simulation results show that the algorithm has a clear physical meaning and can be used for the clustering based on density, In order to achieve accurate clustering of data samples.