面向大规模定制的混流装配线平衡研究  

Mixed-model assembly line balance for mass customization

作　　者：苑明海[1] 李东波[1] 于敏建[1] 

机构地区：[1]南京理工大学机械工程学院,江苏南京210094

出　　处：《计算机集成制造系统》2008年第1期79-83,131,共6页Computer Integrated Manufacturing Systems

基　　金：国防科技重点实验室基金资助项目(51458100205BQ0203)~~

摘　　要：为解决面向大规模定制的混流装配线的平衡问题,分析了这一类装配线的特点,并综合考虑工作站的数量、工作站的负荷及装配线效率三个因素,提出了面向大规模定制的混流装配线的平衡模型和优化装配线平衡的混合遗传算法。该算法将模拟退火算法和遗传算法相结合,采用了交叉概率和变异概率的自适应重构策略,有效避免了算法的早熟,增强了算法全局寻优能力。实例仿真计算表明,该算法比标准的遗传算法和模拟退火算法具有更高的求解质量和求解效率。To deal with mixed-model assembly balance for mass customization, characteristics of mixed-model assembly for mass customization were analyzed, and factors such as workstation numbers, workstation load and assembly efficiency were also taken into consideration. Balance model of mixed-model assembly oriented to mass customization was proposed, and a hybrid genetic algorithm was developed. To prevent the premature convergence problem and improve the global-optimization capability, Genetic Algorithm （GA） was combined with Simulated-annealing Algorithms （SA）, and the adaptive crossover and mutation probabilities method were also employed. Results of the simulation indicated the proposed hybrid GA had better efficiency and optimization performance than simple GA and SA, and would be one effective way to optimize the mixed-model assembly line balance.

关 键 词：大规模定制 混流装配线 平衡 混合遗传算法 

分 类 号：TH132[机械工程—机械制造及自动化]