基于粗糙集和神经网络的内燃机转子振动故障诊断方法研究

摘要

提出了一种基于粗糙集和神经网络的柴油机转子振动故障诊断方法.首先计算传感器采集数据的小波包,提取振动信号能量特征,其次粗糙集对不同振动信号能量特征数据离散方法的基础上,针对数据结构特征确定了等频离散法与公平尺度法相结合的离散方法,最后以获取的规则为输入,利用BP神经网络进行故障诊断.将我们建立的故障诊断方法应用到柴油机转子振动系统中去,表明了该种方法的有效性.%Amethod of diesel rotor vibration fault diagnosis based on rough set and neural network was proposed. Firstly wavelet packet of collected data was calculated, energy feature of vibration signal was extracted. On the basis of different data discrete method, a combined discrete method was determined by data construct. Finally, faults were diagnosed by BPnetwork, using simplified rule. The fault diagnosis method was applied to diesel, which is feasible.