基于神经网络的多目标综合评价

本文提出了基于神经网络的多目标综合评价方法。这种方法通过利用神经网络对于以往成功的评价样本的学习, 使得神经网络反映评价指标的偏好, 从而代替评价人进行评价。文章研究了神经网络学习的BP算法, 并分析了某大型水利工程水位方案评价问题。

A Neural Network Based Model for Multicriteria Comprehensive Assessment

The multicriteria comprehensive assessment problems are comsidered and a model based on neural network for this kind of problems is presented in this article. Through the learning of the neural network, the model can express the preferences and knowledge of the decision makers(or ex- perts)about the assessment problems, and thus the model can be used as the assessment experts. The learning algorithm of the neural network is discussed and the assessment problem of Three Groge Pro- ject is analyred.