摘要
针对一类动态多指标决策问题 ,提出一种多目标多阶段动态决策模型 .文章提出了一种新颖的效用函数 ,并据此将具有不同量纲、不同物理含义、不同指标类型的决策矩阵归一化转换到相应的效用矩阵 ,该效用函数以指标的平均值为参考点 ,突出了“奖优罚劣”原则 ,提高了分辨精度 ,物理概念更加清晰 .文未提出了一种动态决策目标函数 ,并通过对某省五城市三年综合经济效益的评估实例 。
In this paper, first, a new kind of effective function is proposed, by which the evaluation values of decision making matrix with different dimensions and different kinds of indexes are changed uniformly into effective matrix in rage of \. The method emphasizes on the principle of 'rewarding good and punishing bad'. Second, A model for dynamic multiple attribute decision making is also given based on this new effective function. The principle and its calculation procedures are described in detail. Finally, The method of modeling is applied to a practical example and the results, which are satisfactory, show that the method is rational and effective.
出处
《系统工程理论与实践》
EI
CSCD
北大核心
2000年第6期32-36,共5页
Systems Engineering-Theory & Practice
基金
浙江省自然科学基金! 6980 13
关键词
多目标决策
效用函数
经济效益
奖优罚劣原则
decision modeling
multiple attribute decision making
decision matrix
time series
effective Function
