不确定可靠性优化问题的多目标粒子群优化算法  

Multi-objective particle swarm optimization for uncertain reliability optimization problems

作　　者：章恩泽 陈庆伟[1] 

机构地区：[1]南京理工大学自动化学院,南京210094

出　　处：《控制与决策》2015年第9期1701-1705,共5页Control and Decision

基　　金：国家自然科学基金项目(61074023);江苏省普通高校研究生科研创新计划项目(KYZZ_0121)

摘　　要：针对元件可靠性为区间值的系统可靠性优化问题,提出一种区间多目标粒子群优化方法.首先,建立问题的区间多目标优化模型;然后,利用粒子群算法优化该模型,定义一种不精确Pareto支配关系,并给出编码、约束处理、外部存储器更新、领导粒子选择等关键问题的解决方法;最后,将该方法应用于可靠性优化问题实例,验证了方法的有效性.To solve the reliability optimization problem of a system with interval valued reliability of each component,an interval multi-objective particle swarm optimization approach is proposed.Then,the problem is formulated as a multiobjective optimization problem with interval valued objectives.Then,the model is solved by using the particle swarm optimization algorithm.Specifically,the imprecise Pareto dominance relation is defined,and the solutions to the key problems such as encoding of particles,handling of constraints,updation of the external repository,and selection of particle leaders,are presented.Finally,a numerical example is given to illustrate the effectiveness of the proposed approach.

关 键 词：可靠性优化 不确定 区间 多目标优化 粒子群优化 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]