基于MFE的滚动轴承故障诊断方法研究

针对滚动轴承故障振动信号含噪声多、复杂程度高的特点,为实现准确的故障诊断,提出一种基于多尺度模糊熵(MFE)的滚动轴承故障诊断方法。由于LCD方法可以起到降噪的作用,故选用LCD分解后的ISC分量作为粗粒序列,计算分量的MFE。将MFE计算得到的特征参数输入到极限学习机(ELM)分类器中,分类识别滚动轴承的4种状态。实验结果表明,该方法可以有效地提取出滚动轴承的故障特征,实现故障诊断。

Research on Fault Diagnosis Method of Rolling Bearing Based on MFE

Aiming at the vibration signal of rolling bearing fault that is characterized by much noise and high complexity,in order to realize the fault diagnosis accurately,a fault diagnosis method of rolling bearing basedonmulti-scalefuzzyentropy(MFE)wasproposed.BecauseLCDmethodcanreducenoise,ISC component after LCD decomposition was selected as coarse-grained sequence to calculate MFE of the component.The feature parameters calculated by MFE were input into the extreme learning machine(ELM)classifier to recognize four states of rolling bearing.Experimental results show that this method can effectively extract the fault features of rolling bearing and realize fault diagnosis.