基于遗传算法的网络化制造单元选择问题研究

摘要/Abstract

摘要： 为解决网络化协同制造过程中物理制造单元选择问题，提出一种改进的基于遗传算法的物理制造单元优化选择算法。算法采用整数编码，每个染色体代表一条可执行加工路线；为获取最优的可执行加工路线，以总的运行成本、运行时间和加工质量为优化目标构造目标函数；求解过程中，在每一代种群中计算出与每个染色体相对应的成本、时间、质量指标及目标非标准化对决策的影响度，进而利用影响度因子确定群体中每个染色体对最小运行成本、最小运行时间及最优加工质量的相对优属度，再利用相对优属度构造相对适应度函数，并求取相应的适应度函数值，减小了目标非标准化对优化结果的影响。最后给出了应用该算法处理复杂零件协同制造中制造单元选择的一个实例，以证明算法的可行性与有效性。

关键词: 制造单元, 遗传算法, 影响度因子, 相对优属度, 适应度函数

Abstract: To solve physical manufacturing unit (PMU) selection question in the networked cooperative manufacturing process, an improved algorithm based on GA was proposed. Integer coding method was adopted in the algorithm, and a chromosome represented an executive manufacturing process (EMP). In order to obtain the optimized EMP, the objective function was constructed according to the optimizing objective, namely the total running costs, time and machining quality (CTQ). During seeking the answer to this question, the CTQ’s value of each chromosome and the influence degree to decision making due to the CTQ’s non-standardization were calculated in every generation. Through making using of the influence degree coefficient, the relative membership degree of each chromosome to the least total running cost, time and the best machining quality was calculated. Then, the relative fitness function was set up and its value was computed by using the relative membership degree to reduce the influence degree of CTQ’s non-standardization to decision-making. At last, an example was given to prove the algorithm’s feasibility and validity.

Key words: manufacturing unit, genetic algorithm, influence degree coefficient, relative membership degree, fitness function

中图分类号:

TH165

姚倡锋，张定华，彭文利. 基于遗传算法的网络化制造单元选择问题研究[J]. .

YAO Chang-feng, ZHANG Ding-hua, PENG Wen-li. Research on networked manufacturing unit selection based on genetic algorithm[J]. .

参考文献

［1］FAN Yushun. Connotation and key technologies of networked manufacturing[J].Computer Integrated Manufacturing Systems,2003,9(7):556-582(in Chinese).[范玉顺. 网络化制造的内涵与关键技术问题[J].计算机集成制造系统,2003,9(7):556-582.]

[2]YAO Changfeng,PENG Wenli,ZHANG Dinghua，et al. Study on modeling of physical manufacturing unit based on Internet[J]. Manufacturing Automation, 2003,25(10):5-8(in Chinese).[姚倡锋,彭文利,张定华，等.基于Internet的制造单元建模研究[J].制造业自动化,2003,25(10):5-8.]

[3]FENG Weidong, CHEN Jian, ZHAO Chunjun. Partners selection process and optimization model for virtual corporations based on genetic algorithms[J]. Journal of Tsinghua University (Sci&Tech), 2000,40(10):120-124(in Chinese).[冯蔚东,陈剑,赵纯均.基于遗传算法的动态联盟伙伴选择过程及优化模型[J].清华大学学报,2000,40(10):120-124.]

[4]SILVA C M, BISCAIA E C Jr. Genetic algorithm development for multi-objective optimization of batch free-radical polymerization reactors［J］. Computers and Chemical Engineering,2003,27:1329-1344.

[5]HAJELA P, LIN C Y. Genetic search strategies in multi-criterion optimal design［J］. Structural Optimization，1992，5(4)：99-107.

[6]HAO Jumin, JI Zhuoshang, DAI Yinsheng, et al. Multi-objective fuzzy comprehensive assessment and its application to assessment of ship’s principal dimensions[J].Journal of Dalian University of Technology,1998,38(4):373-377(in Chinese).[郝聚民,纪卓尚,戴寅生,等.多目标模糊优选及其在船舶主尺度优选中的应用[J].大连理工大学学报,1998,38(4):373- 377.]

[7]CHEN Shouyu. System fuzzy decision-making theory and application[M]. Dalian:Dalian University of Technology Press，1994(in Chinese).[陈守煜.系统模糊决策理论与应用[M].大连:大连理工大学出版社,1994.]

[8]WANG Xiaoping, CAO Liming. Genetic algorithms-theory, application and software implement[M].Xi’an: Xi’an Jiaotong University Press,2002(in Chinese).[王小平,曹立明.遗传算法-理论、应用与软件实现[M].西安:西安交通大学出版社,2002.]

[9]PENG Wenli, YAO Changfeng, ZHANG Dinghua. The research on advanced deployment of manufacturing resources based on logical manufacturing units for CAPP[J].Modern Manufacturing Engeering,2003，(8)：7-9(in Chinese).[彭文利,姚倡锋,张定华.面向CAPP基于逻辑制造单元的制造资源预配置研究[J].现代制造工程，2003，(8)：7-9.]

[1]	陈年,金涛,王建民. 基于变异反馈的临床路径优化[J]. 计算机集成制造系统, 2021, 27(9): 2556-2564.
[2]	黎英杰,刘建军,陈庆新,毛宁. 多层级装配作业车间等量分批策略与调度算法[J]. 计算机集成制造系统, 2021, 27(8): 2307-2320.
[3]	王文中,张树生,余隋怀,陈登凯. 基于解构·重构思维的潜水器舱室布局优化[J]. 计算机集成制造系统, 2021, 27(7): 2045-2052.
[4]	王勇,周雪,刘永,许茂增. 基于车辆共享的多中心共同配送联盟优化[J]. 计算机集成制造系统, 2021, 27(6): 1820-1832.
[5]	张昊鹏,郭宇,汤鹏洲,黄少华,刘道元,李晗. 基于图像匹配的增强现实装配系统跟踪注册方法[J]. 计算机集成制造系统, 2021, 27(5): 1281-1291.
[6]	胡金昌,刘紫薇,马文凯,吴耀华. 考虑学习效应的单人作业车间多目标调度算法[J]. 计算机集成制造系统, 2021, 27(5): 1361-1370.
[7]	刘俊琦,张则强,王沙沙,曾艳清. 考虑不规则物流交互点的过道布置问题建模与优化[J]. 计算机集成制造系统, 2021, 27(4): 1155-1166.
[8]	裴小兵,李依臻. 新型混合改进遗传算法求解零等待流水车间调度问题[J]. 计算机集成制造系统, 2021, 27(3): 815-827.
[9]	李从东,章志伟,曹策俊,张帆顺. 复杂产品设计变更传播路径的多目标优选[J]. 计算机集成制造系统, 2021, 27(3): 842-856.
[10]	杨小明,徐子奇,金雯,舒帆. 复合拣选策略下堆垛机作业序列优化问题[J]. 计算机集成制造系统, 2021, 27(3): 933-942.
[11]	李丽丽,陈琨,高建民,李辉,冯增行,张建. 采用优化概率神经网络的质量异常识别方法[J]. 计算机集成制造系统, 2021, 27(10): 2813-2821.
[12]	薛玲玲. 作业车间调度的块结构邻域搜索遗传算法[J]. 计算机集成制造系统, 2021, 27(10): 2848-2857.
[13]	罗焕,陈浩杰,宋小欣,张剑. 带有缓存约束的作业车间调度求解方法[J]. 计算机集成制造系统, 2021, 27(10): 2880-2888.
[14]	张韵,钟慧超,张春江,李新宇,丛建臣. 基于机器学习的多策略并行遗传算法[J]. 计算机集成制造系统, 2021, 27(10): 2921-2928.
[15]	狄卫民,王然. 考虑多级设施中断的供应链选址—库存决策模型及优化算法[J]. 计算机集成制造系统, 2021, 27(1): 270-283.