Abstract: Aimed at the existing defects of traditional K-means, which is heavily dependent on the initial clustering center, and easy to trap into the local minimum, a new quantum particle swam optimization clustering method is proposed. The method introduces dynamic adjustment of quantum gate angle, quantum mutation operation, which can maintain the diversity and quality of varieties of the particles, avoid being trapped in local optimum. Furthermore, it combines with particle swarm optimization increasing the particle swarm’s global search capability. Simulation test results show that the proposed method improves the global optimal ability and the convergence rate.

Key words: quantum, Particle Swarm Optimization（PSO）, cluster, K-means

摘要： 针对K-均值聚类方法受初始聚类中心影响，容易陷入局部最优解的问题，提出一种基于量子粒子群算法的聚类方法，该方法引入了动态调整量子门旋转角和量子变异操作，采用改进的变异算子，使粒子群体保持品种的多样性和优良性，避免陷入局部最优，同时结合粒子群优化算法，增加粒子群的全局搜索能力。仿真实验表明该方法在全局寻优能力和收敛效率上都有所提高。

关键词: 量子, 粒子群优化（PSO）, 聚类, K-均值