上海交通大学学报(自然版) ›› 2015, Vol. 49 ›› Issue (08): 1123-1130.

• 自动化技术、计算机技术 • 上一篇    下一篇

基于多目标离散粒子群的产品服务系统方案配置规则提取

刘园1,张在房1,姚迪2,褚学宁3   

  1. (1.上海大学 机电工程与自动化学院,上海 200072; 2.华东理工大学 机械与动力工程学院,上海 200237; 3.上海交通大学 机械与动力工程学院,上海 200240)
  • 收稿日期:2014-07-16 出版日期:2015-08-31 发布日期:2015-08-31
  • 基金资助:

    上海市科技创新行动计划重点项目(13111102900),国家自然科学基金项目(51205242,51075261),上海高校优秀青年教师培养资助计划(B.37010912007)资助

Extraction of Product Service System Configuration Rules Based on Multi-objective DPSO Algorithm

LIU Yuan1,ZHANG Zaifang1,YAO Di2,CHU Xuening3   

  1. (1. School of Mechatronic and Automation Engineering, Shanghai University, Shanghai 200072, China; 2. School of Mechanical and Power Engineering, East China University of Science and Technology, Shanghai 200237, China; 3. School of Mechanical Engineering, Shanghai Jiaotong University, Shanghai 200240, China)
  • Received:2014-07-16 Online:2015-08-31 Published:2015-08-31

摘要:

摘要:  为有效辅助工程师将顾客需求转化为产品服务系统方案,针对其技术特征,提出一种离散粒子群优化算法(DPSO)与帕累托(Pareto)结合的配置规则提取方法.该方法包括建立产品服务系统配置规则模型及构造ParetoDPSO算法模型.ParetoDPSO算法基于Sobol序列的频率初始化方法及离散化粒子更新方式,将连续粒子映射到十进制离散空间;并利用Pareto进行多目标下粒子优劣性评价,以获取非支配的最优规则集.以汽车产品服务系统方案配置设计为例,经与常规多目标粒子群算法及DPSO算法对比,验证了该方法对于解决多维空间内产品服务配置规则挖掘的可行性及有效性.

关键词: 产品服务系统, 配置规则, 多目标优化, 帕累托, 离散粒子群优化算法

Abstract:

Abstract: To assist engineers to map customer requirements into technical characteristics of product service system effectively, a kind of rule extraction method combining DPSO with Pareto was proposed. The method includes establishing the model of product service system configuration rules and constructing the model of ParetoDPSO. In ParetoDPSO, continuous particle was mapped into a decimal discrete space using the frequency initialization method based on Sobol sequence and the particle discrete update method; Pareto was used to obtain the optimal set of rules by evaluating multiple target functions. By comparing with OMOPSO and DPSO, the feasibility and validity of the proposed method was verified by applying in the example of automotive product service system configuration design.

Key words: product service system, configuration rules, multiobjective optimization, Pareto, discrete particle swarm optimization (DPSO)

中图分类号: