A fault feature extraction method for reciprocating compressor based on optimized local mean decomposition

2020 ◽  
Author(s):  
Hongbin Zhang ◽  
Jindong Wang ◽  
Haiyang Zhao ◽  
Shuxin Chen ◽  
Zhidong Wu ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Extraction Method ◽  
Reciprocating Compressor ◽  
Local Mean Decomposition ◽  
Feature Extraction Method ◽  
Local Mean ◽  
Fault Feature Extraction

A Fault Feature Extraction Method Based on LMD and MSE for Reciprocating Compressor

2014 ◽  
Vol 530-531 ◽  
pp. 345-348
Author(s):  
Min Qiang Xu ◽  
Hai Yang Zhao ◽  
Jin Dong Wang
Keyword(s):  
Feature Extraction ◽  
Extraction Method ◽  
Vibration Signal ◽  
Multiscale Entropy ◽  
Reciprocating Compressor ◽  
Feature Extraction Method ◽  
Feature Vectors ◽  
Euclidean Distances ◽  
Coupling Characteristics ◽  
Fault Feature Extraction

This paper presents a feature extraction method based on LMD and MSE for reciprocating compressor according to the strong nonstationarity, nonlinearity and features coupling characteristics of vibration signal. The vibration signal was decomposed into a set of PFs, and then multiscale entropy of the first several PFs were calculated as feature vectors with different scale factors. Based on the maximum of average Euclidean distances, the feature vectors which have the best divisibility were selected. The feature vectors of reciprocating compressor at different bearing clearance states were extracted using this method, and superiority of this method is verified by comparing with the results of sample entropy.

Sign in / Sign up

Export Citation Format

Share Document