Feature extraction method based on VMD and MFDFA for fault diagnosis of reciprocating compressor valve
Aiming at the nonlinearity, nonstationarity and multi-component coupling characteristics of reciprocating compressor vibration signals, an integrated feature extraction method based on the variational mode decomposition (VMD) and multi-fractal detrended fluctuation analysis (MFDFA) is proposed for a...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
JVE International
2017-12-01
|
Series: | Journal of Vibroengineering |
Subjects: | |
Online Access: | https://www.jvejournals.com/article/18726 |
id |
doaj-61d9218f44d347f1a0e03cdafbc99dd3 |
---|---|
record_format |
Article |
spelling |
doaj-61d9218f44d347f1a0e03cdafbc99dd32020-11-25T00:45:16ZengJVE InternationalJournal of Vibroengineering1392-87162538-84602017-12-011986007602010.21595/jve.2017.1872618726Feature extraction method based on VMD and MFDFA for fault diagnosis of reciprocating compressor valveYan Liu0Jindong Wang1Ying Li2Haiyang Zhao3Shuxin Chen4Mechanical Science and Engineering Institute, Northeast Petroleum University, Daqing, ChinaMechanical Science and Engineering Institute, Northeast Petroleum University, Daqing, ChinaMechanical Science and Engineering Institute, Northeast Petroleum University, Daqing, ChinaMechanical Science and Engineering Institute, Northeast Petroleum University, Daqing, ChinaMechanical and Electrical Engineering Institute, Qiqihar University, Qiqihar, ChinaAiming at the nonlinearity, nonstationarity and multi-component coupling characteristics of reciprocating compressor vibration signals, an integrated feature extraction method based on the variational mode decomposition (VMD) and multi-fractal detrended fluctuation analysis (MFDFA) is proposed for a fault diagnosis for a reciprocating compressor valve. Firstly, to eliminate the noise interference, a novel VMD method with superior anti-interference performance was utilized to obtain several components of the quasi-orthogonal band-limited intrinsic mode function (BLIMF) from a strong non-stationarity vibration signal, and a consistent number K of BLIMFs was selected based on a novel criterion for all fault states. Secondly, the MFDFA method, which can describe the multi-fractal structure feature of non-stationary time series, was applied to analyze each BLIMF component, and the parameters of MFDFA were employed as the eigenvectors to reflect the structure characteristics and local scale behavior of the vibration signal. Then, the principal component analysis (PCA) was introduced to refine the eigenvectors for a higher recognition efficiency and accuracy. Finally, the vibration signals of four types of reciprocating compressor valve faults were analyzed by this method, and the faults were identified correctly by pattern classifiers of BTSVM and CNN. Further results comparison with other feature extraction methods verifies the superiority of the proposed method.https://www.jvejournals.com/article/18726fault diagnosisreciprocating compressor valvevariational mode decomposition (VMD)multi-fractal detrended fluctuation analysis (MFDFA)principal component analysis (PCA) |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yan Liu Jindong Wang Ying Li Haiyang Zhao Shuxin Chen |
spellingShingle |
Yan Liu Jindong Wang Ying Li Haiyang Zhao Shuxin Chen Feature extraction method based on VMD and MFDFA for fault diagnosis of reciprocating compressor valve Journal of Vibroengineering fault diagnosis reciprocating compressor valve variational mode decomposition (VMD) multi-fractal detrended fluctuation analysis (MFDFA) principal component analysis (PCA) |
author_facet |
Yan Liu Jindong Wang Ying Li Haiyang Zhao Shuxin Chen |
author_sort |
Yan Liu |
title |
Feature extraction method based on VMD and MFDFA for fault diagnosis of reciprocating compressor valve |
title_short |
Feature extraction method based on VMD and MFDFA for fault diagnosis of reciprocating compressor valve |
title_full |
Feature extraction method based on VMD and MFDFA for fault diagnosis of reciprocating compressor valve |
title_fullStr |
Feature extraction method based on VMD and MFDFA for fault diagnosis of reciprocating compressor valve |
title_full_unstemmed |
Feature extraction method based on VMD and MFDFA for fault diagnosis of reciprocating compressor valve |
title_sort |
feature extraction method based on vmd and mfdfa for fault diagnosis of reciprocating compressor valve |
publisher |
JVE International |
series |
Journal of Vibroengineering |
issn |
1392-8716 2538-8460 |
publishDate |
2017-12-01 |
description |
Aiming at the nonlinearity, nonstationarity and multi-component coupling characteristics of reciprocating compressor vibration signals, an integrated feature extraction method based on the variational mode decomposition (VMD) and multi-fractal detrended fluctuation analysis (MFDFA) is proposed for a fault diagnosis for a reciprocating compressor valve. Firstly, to eliminate the noise interference, a novel VMD method with superior anti-interference performance was utilized to obtain several components of the quasi-orthogonal band-limited intrinsic mode function (BLIMF) from a strong non-stationarity vibration signal, and a consistent number K of BLIMFs was selected based on a novel criterion for all fault states. Secondly, the MFDFA method, which can describe the multi-fractal structure feature of non-stationary time series, was applied to analyze each BLIMF component, and the parameters of MFDFA were employed as the eigenvectors to reflect the structure characteristics and local scale behavior of the vibration signal. Then, the principal component analysis (PCA) was introduced to refine the eigenvectors for a higher recognition efficiency and accuracy. Finally, the vibration signals of four types of reciprocating compressor valve faults were analyzed by this method, and the faults were identified correctly by pattern classifiers of BTSVM and CNN. Further results comparison with other feature extraction methods verifies the superiority of the proposed method. |
topic |
fault diagnosis reciprocating compressor valve variational mode decomposition (VMD) multi-fractal detrended fluctuation analysis (MFDFA) principal component analysis (PCA) |
url |
https://www.jvejournals.com/article/18726 |
work_keys_str_mv |
AT yanliu featureextractionmethodbasedonvmdandmfdfaforfaultdiagnosisofreciprocatingcompressorvalve AT jindongwang featureextractionmethodbasedonvmdandmfdfaforfaultdiagnosisofreciprocatingcompressorvalve AT yingli featureextractionmethodbasedonvmdandmfdfaforfaultdiagnosisofreciprocatingcompressorvalve AT haiyangzhao featureextractionmethodbasedonvmdandmfdfaforfaultdiagnosisofreciprocatingcompressorvalve AT shuxinchen featureextractionmethodbasedonvmdandmfdfaforfaultdiagnosisofreciprocatingcompressorvalve |
_version_ |
1725271087465365504 |