基于MFO-VMD和GMFE的往复压缩机轴承间隙故障诊断方法

Fault diagnosis method for bearing clearance of reciprocating compressor based on MFO-VMD and GMFE

基于往复压缩机轴承间隙故障呈现非线性、非稳定性和特征耦合的特点,本文提出了飞蛾捕焰优化算法(MFO)优化变分模态分解方法(VMD)和广义多尺度模糊熵(GMFE)的往复压缩机轴承间隙故障诊断新方法。首先,利用MFO对VMD的模态数k和惩罚因子α两个参数进行优化,得到最佳参数组合[k,α],从而利用优化后的VMD对轴承间隙振动信号进行信号分解处理,并进行振动信号的重构分析;然后,采用GMFE熵值算法对重构信号进行故障特征提取研究,从而得到所需的故障特征向量集;最后将提取的故障特征向量集输入智能分类算法支持向量机中进行故障的分类诊断研究。研究结果表明,本文提出的往复压缩机轴承间隙故障诊断方法有效地提高诊断的准确率,具有较好的故障特征提取优越性。

Based on the nonlinear,unstable and feature-coupled characteristics of bearing clearance faults of reciprocating compressors,a new fault diagnosis method for bearing clearance faults of reciprocating compressors based on MFO optimization and generalized multi-scale fuzzy entropy(GMFE)is proposed in this paper.Firstly,the MFO algorithm is used to optimize the two parameters of the mode number k and penalty factorαof the VMD method,and the optimal parameter combination[k,α]is obtained.Then the optimized VMD method is used to decompose the vibration signal of the bearing clearance,and the reconstruction analysis of the vibration signal is carried out.Then,the GMFE entropy algorithm is used to extract fault features from the reconstructed signal,and the required fault feature vector set is obtained.Finally,the extracted fault feature vector set is input into intelligent classification algorithm support vector machine for fault classification and diagnosis.The results show that the fault diagnosis method proposed in this paper can effectively improve the accuracy of diagnosis and has the advantages of better fault feature extraction.