基于旋转机械滚动轴承的时域故障诊断方法

Time Domain Fault Diagnosis Method Based on Rolling Machinery Rolling Bearing

针对旋转机械滚动轴承的故障问题,本文提出了一种时域故障诊断方法。首先对滚动轴承的原始振动信号进行3层的小波包分解,并选取前4个小波系数进行重构,接着在时域分析上对每1个小波系数分别提取7个特征值,然后通过BP神经网络获得滚动轴承故障分类的结果。最终实验表明,该方法有效地解决了滚动轴承存在的故障问题,确保了旋转机械安全、可靠、稳定地运行。

Aiming at the fault problem of rolling bearings in rotating machinery,this paper proposes a time domain fault diagnosis method.Firstly,the vibration signal of the rolling bearing is decomposed by 3 layers of wavelet packet,and the first four wavelet coefficients are selected for reconstruction.Then,in the time domain analysis,7 eigenvalues are extracted for each wavelet coefficient,and then the rolling bearing fault classification results are obtained by BP neural network.Finally,the experimental results show that the method can effectively solve the problem of rolling bearing fault and ensure the safe,reliable and stable operation of rotating machinery.