基于偏差的不确定型多属性决策的综合集成方法

对不确定型条件下的多属性决策问题,规范化后的区间数能消除属性值之间量纲的差异,建立了相离度偏差、中间值偏差和理想方案偏差计算公式,构建了以总偏差平方和为目标函数的综合集成优化模型,求解出各属性的客观权重,提出了一种客观属性权重的可能度法,为不确定型多属性决策提供了一种简单实用的可靠方法.最后通过一个算例说明了该方法的实用性和有效性.

Integrated Method of Uncertain Multi-attribute Decision-making Based on Total Difference Deviations

This paper gives two formulas for normalizing the decision matrix in uncertain multi-attribute decision - making problem, which are used to deal with the interval numbers. It establishes the optimization model dealing with the weights of index based on the total square sum of the difference deviation, mean deviation and ideal solution deviation. And it gives a method of possibility degree for deciding objective weights, which provides a simple and practical method for uncertain multi-attribute decision-making. Finally, a numerical example is given to show the feasibility and effectiveness of the method.