基于可变模糊数据包络分析的多目标决策模型  

Multiple criteria decision model based on variable fuzzy data envelopment analysis

作　　者：双晴[1] 袁永博[1] 张明媛[1] 

机构地区：[1]大连理工大学建设工程学部,辽宁大连116024

出　　处：《大连理工大学学报》2013年第3期429-434,共6页Journal of Dalian University of Technology

基　　金：国家自然科学基金青年基金资助项目(51208081)

摘　　要：多目标决策问题的两个关键步骤是各指标权重的确定和距离函数基准点的选择.为直接从数据集中挖掘指标权重,获取样本的一致性排序,研究了样本权重未事先确定的多目标决策问题,建立了一种先优化每个指标的客观权重使赋权后每个样本综合属性值趋于理想值;再通过相对距离测定,利用可变模糊模型计算样本相对隶属度矩阵的两阶段决策模型,最后给出了应用算例并同其他方法进行了对比分析.结果显示这种新方法计算结果稳定,能够对样本进行有效排序,不仅可以有效解决数据包络分析模型解不唯一的问题,而且满足样本与理想点和非理想点距离之和为1的条件,生成一致排序.Two key steps in multiple criteria decision analysis （MCDA） problem are the determination of weights with individual criteria and the selection of benchmark for distance function. In order to obtain criteria weights from the data and achieve consistent ranking, a two-stage method for MCDA problem with weights information on objectives is presented. The general idea is to find a set of weights which produces the aggregate performance for all alternatives to be as close to the ideal point as possible, and then proposes a measure of relative distance, which involves the calculation of the relative membership grade matrix. An illustrative example is given to clarify the proposed method, and the results are compared with those obtained from other methods. The analytical results show that the performance is superior to existing systems and the evaluation is effectiveness in practice. The model provides a unique ordering of the alternatives. It can achieve the unique solution in data envelopment analysis, and the sum of distance of samples with ideal point and non-ideal point is one is satisfied, also the rankings obtained from the two criteria are the same.

关 键 词：多目标决策分析 可变模糊集 数据包络分析 客观权重 

分 类 号：C94[自然科学总论—系统科学]