基于VMD与时间序列分析的滚动轴承故障特征提取方法

为了在非线性、非平稳的滚动轴承故障振动信号中有效提取出敏感的故障特征,提出了基于变分模态分解(VMD)与时间序列分析相结合的特征提取方法。首先通过VMD将原始信号分解为不同预设尺度的本征模态分量(IMF),对各个IMF分量建立时间序列预测模型,通过叠加重构得到最终的预测模型,比较评价指标确定最优参数的选取。最后,通过仿真信号与滚动轴承实际故障数据分析,并与经验模式分解(EMD)进行对比,结果表明该方法能够有效的提取到故障特征频率。

Rolling Bearing Fault Features Extraction Method Based on VMD and Time Series Analysis

In order to effectively extract sensitive fault features in nonlinear and non-stationary rolling bearing fault vibration signals, a feature extraction method based on variational mode decomposition(VMD) and time series analysis is proposed.Firstly, the original signal is decomposed into the intrinsic mode function(IMF) of different preset scale by VMD, and the time series prediction model is established for each IMF component. The final prediction model is obtained by superposition reconstruction,the comparison evaluation index determines the selection of the optimal parameters.Finally, through the simulation signal and the actual fault data analysis of the rolling bearing, and compared with the empirical mode decomposition(EMD), the results show that the method can effectively extract the fault characteristic frequency.