文章导读
总览 评价 张兆军 1,2, , 冯祖仁 1,3,* ( 1、 西安交通大学系统工程研究所,西安 710049; 2、 江苏师范大学电气工程及自动化学院,徐州 221116; 3、 西安交通大学机械制造系统工程国家重点实验室,西安 710049; ) 摘要: 为研究蚁群优化算法在有限
张兆军1,2,, 冯祖仁1,3,*
(
1、西安交通大学系统工程研究所,西安 710049; 2、江苏师范大学电气工程及自动化学院,徐州 221116; 3、西安交通大学机械制造系统工程国家重点实验室,西安 710049; )
摘要:
为研究蚁群优化算法在有限时间内产生解的质量问题,根据蚁群算法的搜索特点以及在算法运行过程中可行解的特点,借鉴序优化相关知识提出一种蚁群算法解质量的序性能评价方法。该方法以算法求解旅行商问题产生的解样本出发,通过聚类实现近似分区均匀化,利用序性能曲线以及算法特点实现对足够好解的分配,最终得到配准概率,实验结果表明了方法的可行性和有效性。
关键词:
系统工程;蚁群优化算法;解质量;序性能
ZHANG Zhaojun1,, FENG Zuren2,*
(
1、Systems Engineering Institute, Xi’an Jiaotong University, Xi’an 710049; 2、School of Electrical Engineering and Automation, Jiangsu Normal University, Xuzhou, 221116; )
Abstract:
In order to study the quality of the solution obtained by ant colony optimization (ACO) algorithm in a finite time, according to the characteristics of search process and feasible solution in the running process of ACO, a solution quality assessment method of ordinal performance is proposed drawing on the experience of ordinal optimization knowledge. Based on the solution sample from the algorithm for solving the traveling salesman problem (TSP), using clustering method, a number of uniformly-distributed subclass is obtained. Then, the good enough subset is decomposed according to the ordered performance curve of problem and characteristic of ACO. Finally, the alignment probability is calculated. The simulation results show the effectiveness and feasibility of the proposed method.
Tag:
点此返回栏目查看更多>>>参考论文