多目标规划在储药柜设计中的应用  

Application of Multi- Objective Optimization( MOO) in Medicine Storage Design

作　　者：王妍[1] 孙士超[2] 陈佳慧[2] 张璐[2] 

机构地区：[1]北京财贸职业学院基础教育学院,北京101101 [2]北京财贸职业学院金融系,北京101101

出　　处：《北京工业职业技术学院学报》2015年第4期50-54,共5页Journal of Beijing Polytechnic College

基　　金：北京市教育委员会2015年度市级教学改革立项与研究项目(PXM2015-014260-000006)

摘　　要：在设计储药柜最优化方案时将部分限制条件进行预先处理,从而降低0-1变量个数,引用0-1线性规划模型。在此基础上将问题转化为多目标规划模型,进而采用LINGO软件求解得到有5种槽宽,此模型及软件使优化问题得以合理解决,但与实际的差别较大。进一步利用聚类分析对槽高类别进行优化,然后通过聚类结果的比对得到答案槽高为7种,此方法能够直观看出各变量的关系,且结果精确。In this paper we focus on the optimization design strategy of Medicine Storage. The 0 - 1 linear program- ming model is incorporated, and some constrained are pre - processed to reduce the number of binary variables. The problem is reformulated as a multi - objective optimization （MOO） model. It turns out that the optimal result is 5 distinct slot widths are needed, which is a reasonable answer to the model but not practical. The improved model uses clustering analysis to optimize the number of distinct slot widths, and obtained the more accurate result of 7 distinct slot widths, which could directly reflect the relationships between the variables.

关 键 词：数据处理 LINGO软件 聚类分析 0-1线性规划模型 多目标规划模型 

分 类 号：O29[理学—应用数学]