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

Min Qiang Xu; Hai Yang Zhao; Jin Dong Wang

doi:10.4028/www.scientific.net/AMM.530-531.345

Paper Titles

Optimal Placement of Sensors for Monitoring Systems on Suspension Bridges Using Genetic Algorithms
p.320

Partial Dicharge Signal Analysis in Insulation Oil Using Optical Chromatic Technique
p.332

Sensors Distribution Program in Health Monitoring of Side Forklift Steering Mechanism
p.336

A One-Stop Method for EMI Analysis Based on Wavelet Packet and SOM
p.341

A Fault Feature Extraction Method Based on LMD and MSE for Reciprocating Compressor
p.345

Investigation on the Thermal Radiation Distribution of Oil Tank Fires
p.349

Research on Single-Phase Grounding Fault in Distribution Networks with a DC Power Positioning Method
p.353

Research and Simulation on Interference Signal Detection of Distributed Generation Connected to the Grid Based on Duffing Oscillator
p.357

A Hybrid Intelligent Algorithm for Fuzzy Programming Problem under Credibility Theory
p.363

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 530-531A Fault Feature Extraction Method Based on LMD and...

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

Abstract:

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.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 530-531)

Pages:

345-348

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.530-531.345

Citation:

Cite this paper

Online since:

February 2014

Authors:

Min Qiang Xu, Hai Yang Zhao*, Jin Dong Wang

Keywords:

Feature Extraction, LMD, Multiscale Entropy, Reciprocating Compressor

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] M. Elhaj, F. Gub A.D. Ballb: Numerical simulation and experimental study of a two- stagereciprocating compressor for condition monitoring, Mechanical Systems and Signal Processing. 22 (2008)374–389.

DOI: 10.1016/j.ymssp.2007.08.003

Google Scholar

[2] Smith, J. S: The local mean decomposition and its application to EEG perception data, J. R. Soc. Interface. 2 (2005)443–454.

DOI: 10.1098/rsif.2005.0058

Google Scholar

[3] Zhiwen Liu, Xuefeng Chen: LMD Method and Multi-Class RWSVM of Fault Diagnosis for Rotating Machinery Using Condition Monitoring Information, Sensors. 13 (2013)8679–8694.

DOI: 10.3390/s130708679

Google Scholar

[4] Costa, M., Goldberger, A., Peng, C: Multiscale entropy analysis of biologicalsystems. Physical Review Letters. 71 (2005)1–18.

Google Scholar

[5] Jun-Lin Lin, Yu-Chih Liu, Chih-Wen Li: Motor shaft misalignment detection using multiscale entropywith wavelet denoising, Expert Systems with Applications. 37 (2010)7200–7204.

DOI: 10.1016/j.eswa.2010.04.009

Google Scholar