Effects of compressed sensing on classification of bearing faults with entropic features

M. L. Dennis Wong; M. Zhang; Asoke K. Nandi

doi:10.1109/EUSIPCO.2015.7362786

Effects of compressed sensing on classification of bearing faults with entropic features

M. L. Dennis Wong, M. Zhang, Asoke K. Nandi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

16 Citations (Scopus)

Abstract

The ability of automatically determining the underlying fault type in-situ for a roller element bearing is highly desired in machine condition monitoring applications nowadays. In this paper, we classify roller element fault types under a compressed sensing framework. Firstly, vibration signals of roller element bearings are acquired in the time domain and resampled with a random Bernoulli matrix to emulate the compressed sensing mechanism. Sample entropy based features are then computed for both the normalized raw vibration signals and the reconstructed compressed sensed signals. Classification performance using Support Vector Machine (SVM) shows slight per formance degradation with significant reduction of the bandwidth requirement.

Original language	English
Title of host publication	2015 23rd European Signal Processing Conference, EUSIPCO 2015
Publisher	IEEE
Pages	2256-2260
Number of pages	5
ISBN (Electronic)	9780992862633
DOIs	https://doi.org/10.1109/EUSIPCO.2015.7362786
Publication status	Published - Dec 2015
Event	23rd European Signal Processing Conference 2015 - Nice, France Duration: 31 Aug 2015 → 4 Sept 2015

Conference

Conference	23rd European Signal Processing Conference 2015
Abbreviated title	EUSIPCO 2015
Country/Territory	France
City	Nice
Period	31/08/15 → 4/09/15

Keywords

Bearing Fault Classification
Com pressed Sensing
Machine Condition Monitoring
Sample Entropy

ASJC Scopus subject areas

Media Technology
Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/EUSIPCO.2015.7362786

Cite this

@inproceedings{163a12d7911c46ba96ec777698a02fa1,

title = "Effects of compressed sensing on classification of bearing faults with entropic features",

abstract = "The ability of automatically determining the underlying fault type in-situ for a roller element bearing is highly desired in machine condition monitoring applications nowadays. In this paper, we classify roller element fault types under a compressed sensing framework. Firstly, vibration signals of roller element bearings are acquired in the time domain and resampled with a random Bernoulli matrix to emulate the compressed sensing mechanism. Sample entropy based features are then computed for both the normalized raw vibration signals and the reconstructed compressed sensed signals. Classification performance using Support Vector Machine (SVM) shows slight per formance degradation with significant reduction of the bandwidth requirement.",

keywords = "Bearing Fault Classification, Com pressed Sensing, Machine Condition Monitoring, Sample Entropy",

author = "Wong, {M. L. Dennis} and M. Zhang and Nandi, {Asoke K.}",

year = "2015",

month = dec,

doi = "10.1109/EUSIPCO.2015.7362786",

language = "English",

pages = "2256--2260",

booktitle = "2015 23rd European Signal Processing Conference, EUSIPCO 2015",

publisher = "IEEE",

address = "United States",

note = "23rd European Signal Processing Conference 2015, EUSIPCO 2015 ; Conference date: 31-08-2015 Through 04-09-2015",

}

TY - GEN

T1 - Effects of compressed sensing on classification of bearing faults with entropic features

AU - Wong, M. L. Dennis

AU - Zhang, M.

AU - Nandi, Asoke K.

PY - 2015/12

Y1 - 2015/12

N2 - The ability of automatically determining the underlying fault type in-situ for a roller element bearing is highly desired in machine condition monitoring applications nowadays. In this paper, we classify roller element fault types under a compressed sensing framework. Firstly, vibration signals of roller element bearings are acquired in the time domain and resampled with a random Bernoulli matrix to emulate the compressed sensing mechanism. Sample entropy based features are then computed for both the normalized raw vibration signals and the reconstructed compressed sensed signals. Classification performance using Support Vector Machine (SVM) shows slight per formance degradation with significant reduction of the bandwidth requirement.

AB - The ability of automatically determining the underlying fault type in-situ for a roller element bearing is highly desired in machine condition monitoring applications nowadays. In this paper, we classify roller element fault types under a compressed sensing framework. Firstly, vibration signals of roller element bearings are acquired in the time domain and resampled with a random Bernoulli matrix to emulate the compressed sensing mechanism. Sample entropy based features are then computed for both the normalized raw vibration signals and the reconstructed compressed sensed signals. Classification performance using Support Vector Machine (SVM) shows slight per formance degradation with significant reduction of the bandwidth requirement.

KW - Bearing Fault Classification

KW - Com pressed Sensing

KW - Machine Condition Monitoring

KW - Sample Entropy

UR - http://www.scopus.com/inward/record.url?scp=84963976707&partnerID=8YFLogxK

U2 - 10.1109/EUSIPCO.2015.7362786

DO - 10.1109/EUSIPCO.2015.7362786

M3 - Conference contribution

AN - SCOPUS:84963976707

SP - 2256

EP - 2260

BT - 2015 23rd European Signal Processing Conference, EUSIPCO 2015

PB - IEEE

T2 - 23rd European Signal Processing Conference 2015

Y2 - 31 August 2015 through 4 September 2015

ER -

Effects of compressed sensing on classification of bearing faults with entropic features

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this