一种基于粗糙集与BP神经网络集成的新方法

A New Method Based on Rough Set and Integration of BP Neural Network

在分析了粗糙集理论和神经网络理论各自优势和存在问题的基础上,设计了将两者综合集成的新方法。该方法主要思想是利用粗糙集理论对神经网络待处理的数据进行属性约简,借此来简化神经网络的结构。利用该方法对航材的消耗进行预测,实验结果表明,该方法减少了训练次数并且预测效果比传统神经网络效果好。

After analysis of respective advantages and problems of rough set and neural network theory, a new way is found to synthesize the two theories. The way is to use the rough set to make property reduction on data processed by the neural network and simplify the structure of the neural network. The way can be used to predict consumption of aero - materials. The findings show the way reduced training frequency and was more effective than the traditional one.