基于最大离差和最大联合熵的多方案优选方法  

Combination Weighting Approach Based on Maximal Deviation and Maximal Joint-entropy

作　　者：张国权[1] 李文立[1] 杨件[1] 

机构地区：[1]大连理工大学系统工程研究所,辽宁大连116023

出　　处：《运筹与管理》2007年第4期12-18,共7页Operations Research and Management Science

基　　金：国家自然科学基金资助项目(70572099);辽宁省自然科学基金资助项目(1050349)

摘　　要：针对多方案优选中指标权重确定问题,提出了基于最小离散和最大广义联合熵的组合赋权方法,建立了组合权系数优化模型。该方法一方面根据评价指标对方案决策所起作用大小赋予不同的权重;另一方面尽量能够消除组合赋权中的不稳定性,使各方法各指标权数赋予平衡因子后广义的联合熵最大,从而使得全局的不确定性最小。最后通过实例说明了此方法合理、稳健。In order to give weight correctly, a new method based on minimal deviations and maximal joint -entropy is proposed. This method bases on evaluation attributes playing the role in the plan decisionmaking to assign the different weight to attributes. On the other hand, it makes the joint-entropy at the multi--indicator vectors the most by choosing the balancing element and the uncertainty at the overall situation the least. According to this, it constructs the optimization model about the weight vectors combination. At last an example is given to demonstrate the precision and reliability and validity of the method in this paper.

关 键 词：多指标决策 组合赋权 离差 联合熵 权重 

分 类 号：C934[经济管理—管理学]