一种混合粒子群优化算法在TSP中的应用  

An Improved Hybrid Particle Swarm Optimization Algorithm for TSP

作　　者：谢旻[1] 

机构地区：[1]南京工业大学电子与信息工程学院,南京210009

出　　处：《太原理工大学学报》2013年第4期506-509,513,共5页Journal of Taiyuan University of Technology

基　　金：国家自然科学基金资助项目(61073098);江苏省高校自然科学基金资助项目(11KJD520007)

摘　　要：针对TSP,提出一种混合粒子群优化算法IHPSO,将种群划分成若干子种群,在子种群内部实施遗传策略。算法在PSO-GA的基础上,引入克隆免疫机制,通过计算粒子间的亲和度来进行复制和变异,从而保留最佳粒子和改进较差粒子。算法中设计了克隆算子、交叉算子、自适应变异算子和抗体重组算子等4个算子。通过实验比较,用所提出的混合粒子群优化算法求解TSP在收敛速度、全局搜索能力和最优解结果上都较优。To solve the travelling salesman problem, an improved hybrid particle swarm opti- mization algorithm was proposed, in which the population is divided into several sub-populations where the genetic mechanisms are applied. On the basis of PSO-GA, the proposed algorithm a- dopted clone immune mechanism and designed four operators, including clone operator, crossover operator, auto-adaptive mutation operator and antibody restructuring operator. Computer numerical experiments show that the presented algorithm achieved a higher convergence rate, better global optimization and optimal solution.

关 键 词：TSP 克隆免疫 交叉算子 自适应变异 抗体重组 

分 类 号：TP312[自动化与计算机技术—计算机软件与理论]