基于粗糙集-神经网络故障诊断技术的研究

提出了一种基于粗糙集-神经网络故障诊断新方法,该方法利用粗糙集理论对数据样本进行数据浓缩,提取初步的映射规则.该规则通过神经网络进行粗映射,利用神经网络的分类逼近能力,建立输入状态空间到输出空间的精确映射,大大提高了神经网络的收敛速度和逼近精度.通过对一个电力电子电路进行实验,实验结果表明,该方法可以有效地减少输入层神经元个数,提高神经网络模型的学习效率和诊断的准确性,在故障诊断中有良好的应用前景.

Research of Fault Diagnosis Technology Based on Rough Set-neural Network

In this paper presents a new method based on Rough Set - neural Network. It uses rough set theory to enrich data and extract the mapping rules from the sample data. Then exploiting rough set neural network describe the extracted rules, the approach to construct the exact mapping between input state - space and output space is presented. The example of power electronic circuits, the model can decrease the number of the network input nerve cells effectively. The results show that the strategy has better study efficiency and diagnosis accuracy. It is estimated that the optimized strategy may be further applied in fault diagnosis.