Multi-Scale Permutation Entropy Based on Improved LMD and HMM for Rolling Bearing Diagnosis
Multi-Scale Permutation Entropy Based on Improved LMD and HMM for Rolling Bearing Diagnosis
复制标题
基于改进LMD和HMM的多尺度排列熵滚动轴承诊断
DOI：
10.3390/e19040176
复制
发表时间：
2017-04-01
期刊：
影响因子：
2.7
通讯作者：
Song, Wanqing
中科院分区：
文献类型：
--
作者：
Gao, Yangde;Villecco, Francesco;Song, Wanqing
基于改进的局部均值分解（LMD）、多尺度排列熵（MPE）和隐马尔可夫模型（HMM）相结合，诊断轴承的故障类型。基于滚动轴承振动信号的自相似性，提出了改进的LMD，通过扩展原始信号的左右两侧来抑制其边缘效应。首先，通过改进的LMD将滚动轴承的振动信号分别分解为多个乘积函数（PF）分量。然后，利用互信息（MI）法和伪最近邻（FNN）法对PF1进行相空间重构，计算延迟时间和嵌入维数，然后设置尺度，得到PF1的MPE。之后，提取滚动轴承的MPE特征。最后利用MPE的特征作为HMM的训练和诊断。实验结果表明，该方法能够有效识别滚动轴承的不同故障。
Based on the combination of improved Local Mean Decomposition (LMD), Multi-scale Permutation Entropy (MPE) and Hidden Markov Model (HMM), the fault types of bearings are diagnosed. Improved LMD is proposed based on the self-similarity of roller bearing vibration signal by extending the right and left side of the original signal to suppress its edge effect. First, the vibration signals of the rolling bearing are decomposed into several product function (PF) components by improved LMD respectively. Then, the phase space reconstruction of the PF1 is carried out by using the mutual information (MI) method and the false nearest neighbor (FNN) method to calculate the delay time and the embedding dimension, and then the scale is set to obtain the MPE of PF1. After that, the MPE features of rolling bearings are extracted. Finally, the features of MPE are used as HMM training and diagnosis. The experimental results show that the proposed method can effectively identify the different faults of the rolling bearing.