基于MHITD与MFE的往复压缩机故障特征提取方法

A Fault Feature Extraction Method Based on MHITD and MFE for Reciprocating Compressor

针对往复压缩机振动信号的非平稳和非线性特性,提出一种基于改进ITD(MHITD)方法与多尺度模糊熵(MFE)的往复压缩机轴承故障特征提取方法。MHITD方法解决了ITD方法分量波形失真的问题,其采用单调三次Hermite插值代替了ITD方法中的线性变换。利用MHITD方法将故障振动信号分解为一系列旋转分量之和,根据相关性系数筛选包含故障主要信息的分量。利用多尺度模糊熵对各分量进行定量描述,并以类间平均欧氏距离对尺度因子进行优选,得出可分性良好的特征向量。通过该方法提取往复压缩机故障轴承间隙故障的特征向量,与ITD和样本熵方法进行对比分析,验证了该方法的有效性。

Aiming at the non-stationary and nonlinearity characteristics of reciprocating compressor vibration signal, a feature extraction method for bearing fault of reciprocating compressor based on Monotone Hermite interpolation Intrinsic time-scale decomposition （MHITD）and Muhiscale fuzzy entropy （MFE）is proposed. MHITD method used monotone hermite interpolation to replace linear transformation of the ITD method, which solved the problem of the component waveform distortion. Vibration signals in each state are decomposed into a series of PR components with MHITD method, and the PR components which contain the main information of fault state are chosen according to relative coefficient. MFE of the selected PR components was calculated, and the optimized scale factor was selected based on the maximum of average distances between different states, so the eigenvectors which have the best divisibility were extracted. Bearing clearance faults of reciprocating compressor were diagnosed by this method accurately and the superiority of this method is verified by comparing the eigenvectors extracted by ITD and sample entropy method.