基于免疫遗传算法的装配顺序优化  

Optimization of Assembly Sequence Using Immune Genetic Algorithm

作　　者：苏强[1] 吴海龙[1] 赖盛杰[2] 

机构地区：[1]同济大学经济与管理学院,上海201804 [2]上海交通大学机械与动力工程学院,上海200240

出　　处：《同济大学学报（自然科学版）》2015年第6期944-950,共7页Journal of Tongji University:Natural Science

基　　金：国家自然科学基金(71072026;71090404;71432007)

摘　　要：采用装配角度、装配方向、装配稳定性和重定位次数4个指标构建装配顺序优化模型,并用疫苗自动获取的免疫遗传算法(IGABVAU)求解.提出4种免疫疫苗用于提升算法运行效率,其中KP和NL型疫苗由人工指定,BP和NT型疫苗在算法运行中自动获取.船舶工段装配实验结果表明,该算法具有较快的收敛速度.进一步研究发现,免疫疫苗的质量会影响疫苗自动获取的免疫遗传算法收敛速度,人工指定的KP和NL型疫苗可以提高初始种群的质量,自动获取的BP和NT型疫苗可以为装配顺序的进化提供方向.An assembly optimal model combining with the immune genetic algorithm based on vaccine automatic updating （IGABVAU） was proposed to solve the assembly sequence plan problem （ ASPP ）. According to assembly problem characteristic, four kinds of immune vaccines were proposed in which the KP and NL vaccines were set manually and the BP and NT vaccines were created automatically. The standard genetic algorithm （GA） and standard immune genetic algorithm （IGA） was compared by using a ship part assembly as an example. The result shows that the immune genetic algorithm based on vaccine automatic updating has a faster convergent speed. The KP and NL vaccines could improve the quality of assembly sequence population while the BP and NT vaccines could provide directions for next evolution.

关 键 词：免疫遗传算法 疫苗自动更新 装配顺序规划 

分 类 号：TP11[自动化与计算机技术—控制理论与控制工程]