一种量子粒子群算法的改进方法  

One Method of Improving Quantum-behaved Particle Swarm Optimization

作　　者：杨传将[1] 刘清[1] 黄珍[1] 

机构地区：[1]武汉理工大学自动化学院,湖北武汉430063

出　　处：《计算技术与自动化》2009年第1期100-103,共4页Computing Technology and Automation

摘　　要：针对量子粒子群算法存在的问题,设计基于公共历史的两种群并行搜索的量子粒子群算法。在利用群体历史优质解及最优粒子变异的基础上,对粒子群进行筛选,加快粒子群的收敛速度,并采用两种群并行搜索,防止同时陷入局部极值。通过多个函数的测试,该算法在收敛速度及寻找全局最优方面,都表现出较好的效果。According to still existing problem of Quantum- behaved Particle Swarm Optimization（QPSO）, a new QPSO with two Particle Swarms based on public history researching side-by - side（TPHQPSO）is presented, on the base of using the better recording locations of all particles and the mutation of the best behaved particle, the Particle Swarm is filtrated, accelerating the convergence speed. Considering it is difficult for one Particle Swarm to run out of the local optima, two Particle Swarms are used to research side - by - side, avoiding running into local optima at the same time. Comparative experiments on testing functions indicate that this method improves convergence speed and enhances the global searching ability, It has the better performance than traditional QPSO.

关 键 词：粒子群优化算法 量子粒子群优化算法 公共历史 并行搜索 局部最优 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]