基于证据推理的信息不完全的多准则排序方法

针对有训练集的准则权系数信息不完全确定且准则值信息不完全或缺失的多准则决策问题,提出了一种基于证据推理的决策方法.该方法首先通过证据推理算法将方案的准则值集成,然后将效用值集成,结合准则权系数和等级效用的不完全确定信息和训练集的排序等建立非线性规划模型,利用遗传算法来求解非线性规划模型,得到各准则的权系数和各等级效用值,进而得到整个方案集的排序.最后用实例说明该方法的有效性和可行性.

Multi-criteria ranking approach based on evidential reasoning with incomplete certain information

For multi-criteria decision making problems with traiming set,in which the information on the criteria's weights is incomplete certain and the value of the criteria is incomplete or not given,an approach based on evidential reasoning is proposed.In this approach,through evidential reasoning algorithms,the criteria values are aggregated.After aggregating the utility,a nonlinear programming model is developed by using the incomplete certain information on weights and utilities of the categories and ranking on reference set.Then using genetic algorithms(GA) to solve the nonlinear programming models,the criteria's weights and utilities of the categories are gained.So the ranking of the alternatives can be attained.Finally,an example is given to show the feasibility and availability of this method.