基于AHP-PNN的电网企业科研项目前评估体系研究

Research on Pre-evaluation System of Power Grid Scientific Research Projects Based on AHP-PNN

为构建全面、科学的项目前评估体系,论文提出一种基于AHP-PNN的电网企业科研项目前评估体系构建方法。首先利用层次分析法对项目评估体系的指标进行权重划分,再通过概率神经网络对项目进行分类,然后将该分类结果与BP神经网络分类结果进行对比。结果表明,相较于BP神经网络,论文所提出的AHP-PNN方法具有更高的分类准确率,可以对电网企业科研项目进行合理等级划分。

In order to build a comprehensive and scientific pre-project evaluation system,this paper proposes a method for constructing a pre-evaluation system for power grid research projects based on AHP-PNN.The analytic hierarchy process(AHP)is used to divide the weights of the project evaluation system indicators.The projects are classified through the probabilistic neural network(PNN),and the classification results are compared with the BP neural network classification results.The results show that compared with the BP neural network,the AHP-PNN method proposed in this paper has higher classification accuracy and can classify the scientific research projects of power grid enterprises reasonably.