一种基于全局视角的并行网络DEA模型  被引量:1

A parallel network DEA model based on a global perspective

在线阅读下载全文

作  者:马占新[1] 张传哲 MA Zhanxin;ZHANG Chuanzhe(School of Economics and Management,Inner Mongolia University,Hohhot 010021,China)

机构地区:[1]内蒙古大学经济管理学院,呼和浩特010021

出  处:《系统工程理论与实践》2024年第6期2059-2074,共16页Systems Engineering-Theory & Practice

基  金:国家自然科学基金(72161031);国家自然科学基金(71661025);内蒙古自然科学基金(2021MS07025);内蒙古草原英才项目(12000-12102012)。

摘  要:具有并行网络结构的生产系统是一类具有代表性的复杂生产系统.由于一些重要的并行网络DEA模型还没有处理好决策单元与其内部的子单元之间的关系,因此,可能导致DEA投影点溢出生产可能集以及目标函数无法准确反映决策单元效率的问题.为了解决这些问题,本文首先通过实例分析了原有并行网络DEA模型存在的问题.然后,提出一种基于全局视角的并行网络DEA模型,并讨论了该模型的相关性质.最后,将本文模型应用于中国台湾林地生产效率的实证分析.结果表明,本文模型不仅可以从全局的角度测算决策单元的效率、给出无效决策单元及其子单元调整的信息,而且还能解决子单元数量存在差异的效率分析问题.Production systems with parallel network structure are a representative class of complex production systems.Since some important parallel network DEA models have not well dealt with the relationship between the decision making unit(DMU)and its internal subunits,this leads to the problems that the DEA projection points may overflow the production possibility set and the objective function may not accurately reflect the efficiency of DMUs.In order to solve these problems,this paper first analyzes the problems of the original parallel network DEA model through some examples.Then,a parallel network DEA model based on a global perspective is proposed,and the relevant properties of the model are discussed.Finally,the model of this paper is applied to the empirical analysis of forest production efficiency in Taiwan,China.The results show that the model of this paper can not only measure the efficiency of DMUs from a global perspective,give information on the adjustment of inefficient DMUs and their subunits,but also solve the problem of efficiency analysis with differences in the numbers of subunits.

关 键 词:综合评价 多目标决策 数据包络分析 并行网络 DEA有效 

分 类 号:N94[自然科学总论—系统科学]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象