基于灰色粗糙集与BP神经网络的设备故障预测

为更有效预测设备故障，提出一种基于灰色粗糙集与BP神经网络的设备故障预测模型。用灰色关联分析和粗糙集理论分别对二维故障决策表进行横向和纵向两个维度的约简，将冗余的数据和属性去掉，并将约简后的数据输入到BP神经网络，预测设备故障。最后以地铁信号设备故障预测为例进行实例验证，结果表明，该模型预测误差更小，预测准确率更高。

Equipment fault prediction based on grey rough set and BP neural network

In order to predict equipment failure more effectively, the paper proposed a model of equipment fault prediction based on the grey rough set and BP neural network. By use of grey incidence analysis and rough set theory, the paper reduced a two-dimensional fault decision table from both horizontal and vertical dimensions, and removed the redundant data and attributes of the decision table, after the reduction, input the data to the BP neural network to predict the equipment failure. Finally, the paper carried out a case study on the fault prediction of subway signal equipment, and the results show that the model has smaller prediction error and higher accuracy.