求解TSP问题的混合杂草优化算法  

Hybrid Invasive Weed Optimization Algorithm to Solve Traveling Salesman Problem

作　　者：彭斌[1,2] 胡常安[1,2] 邵兵[1,2] 谢小正[1,2] 郑玉巧[1,2] 

机构地区：[1]兰州理工大学数字制造技术与应用省部共建教育部重点实验室,兰州730050 [2]兰州理工大学机电工程学院,兰州730050

出　　处：《振动．测试与诊断》2013年第S1期52-55,218,共5页Journal of Vibration,Measurement & Diagnosis

基　　金：国家自然科学基金资助项目(51275226);浙江省自然科学基金资助项目(LY12E05010);留学回国人员择优资助项目(1002ZSB114);甘肃省自然科学基金资助项目(1112RJZA003);甘肃省高校基本业务费资助项目(1202ZTC057)

摘　　要：根据组合优化问题的特点,提出一种离散混合杂草优化算法来解决旅行商问题,通过对算法中正态分布于父代周围的子代进行离散化分析,并引入遗传操作中的单点顺序交叉法和对换变异法,从而有效防止了算法的早熟收敛。计算机仿真结果表明,离散混合杂草优化算法相对于基本粒子群算法具有更好的性能。Weeds optimization algorithm(IWO) is a very innovative and efficient global optimization algorithm, this algorithm simulates natural behavior of weeds cloning and reproduction, which has advantage of good robustness, adaptive and randomness characteristics. A discrete hybrid invasive weed optimization algorithm(DHIWO) is designed to tackle the traveling salesman problem(TSP). Based on the characteristics of combinatorial optimization problem, this paper disperses the distribution of the offspring. In order to restrain premature stagnation, single point ordered and swap mutation operator of the genetic algorithm are applied to the new algorithm. The experiment results show that the algorithm,with the smaller populations and the fewer number of iterations, can produce good results, compared with the particle swarm optimization algorithm for TSP.

关 键 词：离散混合杂草优化算法 旅行商问题 组合优化 正态分布 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]