基于单亲遗传算法的动态设备布局仿真研究  

Simulation of the dynamic plant layout problem based on partheno genetic algorithm

作　　者：李波[1] 邱枫[1] 

机构地区：[1]天津大学管理学院,天津300072

出　　处：《智能系统学报》2007年第1期74-79,共6页CAAI Transactions on Intelligent Systems

基　　金：国家自然科学基金资助项目(70572045).

摘　　要：针对柔性生产环境下的设备布局问题,提出了一种基于单亲遗传算法原理的启发式算法.发展了一种新颖的适用于动态设备布局的遗传换位操作算子,并提出在单期布局编码子串上应用换位概率的策略,增加了种群的多样性.Matlab编程实现算法,通过大量仿真模拟并与其他算法进行比较分析,证实了所提出方法的有效性.提出的算法在问题规模不大时可以迅速而准确的获得优化解,在问题规模较大时也能在较短时间(与其他算法相比)获得满意解,因此具有较好的综合性能.A heuristic algorithm based on PGA was proposed to solve the plant layout problem in flexible manufacturing systems. A new position-switch genetic operator for DPLP was developed. Position-switch probability strategy on single-period-layout was used to increase individuals＇ diversity. The effectiveness of proposed method is demonstrated by simulation examples and comparison with other approaches. Proposed algorithm produces optimal solutions speedily and accurately and provides acceptable solution in a reasonable time. Its performance is very good while considering both solution quality and computational time.

关 键 词：动态设备布局问题 启发式算法 单亲遗传算法 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]