蚁群算法在单级多时段多资源约束的生产批量问题中的应用研究  

Application of an Improved Ant Colony Optimization Algorithm for Solving Single-level Multi-period Capacitated Dynamic Lot-sizing Problem

作　　者：李英俊[1] 陈志祥[1] 

机构地区：[1]中山大学,广州510275

出　　处：《中国机械工程》2012年第19期2326-2331,共6页China Mechanical Engineering

基　　金：国家自然科学基金资助项目(70972079)

摘　　要：设计了一个用于求解具有多时段连续与整数混合规划问题的算法结构,并以单级多时段多资源约束的生产批量问题(CLSP)的模型为背景进行了应用研究,根据此类问题的特点设计了新颖的蚁群算法,阐明了算法的具体实现过程。通过对其他文献中的例子进行计算和结果比较,表明提出的改进蚁群算法在寻优方面比退火惩罚混合遗传算法和传统的遗传算法要好,验证了所提算法对解决此类问题的可行性和适用性。One algorithm structure of an ant colony optimization（ACO） for solving multi--periods continuous and mixed integer programming problem was first designed herein and then its application in the single--level multi--period capacitated dynamic lot--sizing problem（CLSP） was introduced. The algorithm was based on the model characteristics of CLSP and improvements of traditional ant colony algorithm. Compared with other algorithms of other literature, the algorithm presented herein performs better than that the traditional genetic algorithm and the hybrid of simulated annealing penalty and genetic algorithm do;it has higher ability of obtaining optimal value. The application results show the method is feasible and effective for solving this kind problem.

关 键 词：生产批量计划 多资源约束 蚁群算法 混合整数规划 

分 类 号：F406[经济管理—产业经济] TP29[自动化与计算机技术—检测技术与自动化装置]