首页 | 本学科首页   官方微博 | 高级检索  
     

一种基于协同进化的流水线向Seru系统转化方法
引用本文:吴旭辉,杜劭峰,郝慧慧,于洋,殷勇,李冬妮.一种基于协同进化的流水线向Seru系统转化方法[J].自动化学报,2018,44(6):1015-1027.
作者姓名:吴旭辉  杜劭峰  郝慧慧  于洋  殷勇  李冬妮
作者单位:1.北京理工大学计算机学院智能信息技术北京市重点实验室 北京 100081 中国
基金项目:特种车辆及其传动系统智能制造国家重点实验室开放课题GZ2016KF003国家自然科学基金71401014
摘    要:Seru生产系统是一种被广泛应用于电子制造产业的新型生产模式,但由于流水线向Seru系统转化问题(Line-seru conversion)包含有Seru构建与Seru调度两个相互耦合的子问题,现有算法难以在同时兼顾解的质量与计算效率的情况下对问题进行求解.因此,本文针对流水线向Seru系统转化问题的特点,提出了一种协同进化算法,即在进化算法中加入了协同机制,将Seru构建与Seru调度子问题作为两个子种群利用该机制进行协同进化,从而弥补了现有算法的不足.并且,本文还针对问题特点设计了个体基因编码方式,从而使规划获得的Seru生产系统具有更优的生产性能及均衡性能.实验表明,采用加入了协同机制的进化算法比传统解决流水线向Seru系统转化问题的方法具有更好的性能,本文所提的方法在最小化产品流通时间和劳动时间有较好的性能表现,并且具有较高的计算效率.

关 键 词:协同进化    流水线    Seru系统    转化
收稿时间:2016-09-08

A Line-seru Conversion Approach by Means of Cooperative Coevolution
Affiliation:1.Beijing Laboratory of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology, Beijing 100081, China2.State Key Laboratory of Smart Manufacturing for Special Vehicles and Transmission System, Baotou 014000, China3.Institute of Systems Engineering, State Key Laboratory of Synthetic Automation for Process Industries, Northeastern University, Shenyang 110819, China4.Graduate School of Business, Doshisha University, Kyoto, Japan
Abstract:Line-seru conversion is an innovative assembly system applied widely in the electronics industry. However, extant algorithms can hardly come into play in solving the line-seru conversion problem. The reason lies in that the line-seru conversion problem consists of two interacting subproblems, i.e., seru formation and seru loading, so it is difficult to obtain high quality solutions with affordable computation efficiency. Thus, an evolutionary algorithm with a cooperation mechanism is proposed in this paper. With the cooperation mechanism, the two subproblems can cooperatively evolved as two subpopulations simultaneously so as to address the aforementioned problem. Moreover, the coding of chromosomes representing scheduling result is modified to satisfy the specific requirement of the conversion and acquire solutions with enhanced performance and balancing ability. Computational result shows a better performance of the proposed method in minimizing total throughput time, total labor hours and computational costs.
Keywords:
点击此处可从《自动化学报》浏览原始摘要信息
点击此处可从《自动化学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号