解决一类家纺企业生产计划排单问题的并行混合遗传算法  

Parallel hybrid genetic algorithm for solving MPS problem in a kind of textile enterprises

作　　者：高家全[1] 

机构地区：[1]浙江工业大学之江学院,浙江杭州310024

出　　处：《浙江工业大学学报》2006年第4期402-405,共4页Journal of Zhejiang University of Technology

基　　金：浙江省教委基金资助项目(20051436)

摘　　要：为了解决一类家纺企业的生产计划排单问题,提出了一个基于自然编码的混合遗传算法,此算法具有如下特点:一方面编码方式能有效地反映调度方案;另一方面对每子代得到的调度方案利用爬山算法对其进行了局部调整,大大加快了收敛速度.同时为了更好地适应调度实时性和解大规模此类问题的需要,基于遗传算法自然并行性特点的基础上,实现了主从式控制网络模式下并行混合遗传算法.计算结果表明,此算法是有效的,优于普通的遗传算法,有着较高的并行性,并能适用于解决大规模此类企业生产计划排单问题.In order to solve MPS problem in a kind of textile enterprises, a hybrid genetic algorithm based on nature coding scheme is suggested. The algorithm has the following characteristics： on one hand, its coding method can effectively reflect the virtual scheduling policy; on the other hand, a climbing method is adopted to adjust local solutions in order to accelerate the speed of convergence in this algorithm. Meanwhile, under the mode of master-slave control networks, parallel hybrid genetic algorithm is applied in order to meet the requirement of lager scale and real-time scheduling problems of these enterprises. The computational results show that the algorithm is effective, and is better than common genetic algorithms. It has much more parallel characteristics. The method can be applied to solve larger scale MPS problems in this kind of textile enterprises.

关 键 词：生产计划排单 并行遗传算法 调度问题 家纺企业 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]