Multi-Scale analysis based ball bearing defect diagnostics using mahalanobis distance and support vector machine

Shuen-De Wu, Chiu Wen Wu, Tian Yau Wu, Chun Chieh Wang

Research output: Contribution to journalArticle

51 Citations (Scopus)

Abstract

The objective of this research is to investigate the feasibility of utilizing the multi-scale analysis and support vector machine (SVM) classification scheme to diagnose the bearing faults in rotating machinery. For complicated signals, the characteristics of dynamic systems may not be apparently observed in a scale, particularly for the fault-related features of rotating machinery. In this research, the multi-scale analysis is employed to extract the possible fault-related features in different scales, such as the multi-scale entropy (MSE), multi-scale permutation entropy (MPE), multi-scale root-mean-square (MSRMS) and multi-band spectrum entropy (MBSE). Some of the features are then selected as the inputs of the support vector machine (SVM) classifier through the Fisher score (FS) as well as the Mahalanobis distance (MD) evaluations. The vibration signals of bearing test data at Case Western Reserve University (CWRU) are utilized as the illustrated examples. The analysis results demonstrate that an accurate bearing defect diagnosis can be achieved by using the extracted machine features in different scales. It can be also noted that the diagnostic results of bearing faults can be further enhanced through the feature selection procedures of FS and MD evaluations.

Original languageEnglish
Pages (from-to)416-433
Number of pages18
JournalEntropy
Volume15
Issue number2
DOIs
Publication statusPublished - 2013 Feb 1

Fingerprint

ball bearings
defects
machinery
entropy
evaluation
permutations
classifiers
vibration

Keywords

  • Fisher score (FS)
  • Mahalanobis distance (MD)
  • Multi-band spectrum entropy (MBSE)
  • Multi-scale entropy (MSE)
  • Multi-scale permutation entropy (MPE)
  • Multi-scale root-mean-square (MSRMS)
  • Support vector machine (SVM)

ASJC Scopus subject areas

  • Physics and Astronomy(all)

Cite this

Multi-Scale analysis based ball bearing defect diagnostics using mahalanobis distance and support vector machine. / Wu, Shuen-De; Wu, Chiu Wen; Wu, Tian Yau; Wang, Chun Chieh.

In: Entropy, Vol. 15, No. 2, 01.02.2013, p. 416-433.

Research output: Contribution to journalArticle

Wu, Shuen-De ; Wu, Chiu Wen ; Wu, Tian Yau ; Wang, Chun Chieh. / Multi-Scale analysis based ball bearing defect diagnostics using mahalanobis distance and support vector machine. In: Entropy. 2013 ; Vol. 15, No. 2. pp. 416-433.
@article{fcdbeff2f1cf406cb4a8e4b035151f57,
title = "Multi-Scale analysis based ball bearing defect diagnostics using mahalanobis distance and support vector machine",
abstract = "The objective of this research is to investigate the feasibility of utilizing the multi-scale analysis and support vector machine (SVM) classification scheme to diagnose the bearing faults in rotating machinery. For complicated signals, the characteristics of dynamic systems may not be apparently observed in a scale, particularly for the fault-related features of rotating machinery. In this research, the multi-scale analysis is employed to extract the possible fault-related features in different scales, such as the multi-scale entropy (MSE), multi-scale permutation entropy (MPE), multi-scale root-mean-square (MSRMS) and multi-band spectrum entropy (MBSE). Some of the features are then selected as the inputs of the support vector machine (SVM) classifier through the Fisher score (FS) as well as the Mahalanobis distance (MD) evaluations. The vibration signals of bearing test data at Case Western Reserve University (CWRU) are utilized as the illustrated examples. The analysis results demonstrate that an accurate bearing defect diagnosis can be achieved by using the extracted machine features in different scales. It can be also noted that the diagnostic results of bearing faults can be further enhanced through the feature selection procedures of FS and MD evaluations.",
keywords = "Fisher score (FS), Mahalanobis distance (MD), Multi-band spectrum entropy (MBSE), Multi-scale entropy (MSE), Multi-scale permutation entropy (MPE), Multi-scale root-mean-square (MSRMS), Support vector machine (SVM)",
author = "Shuen-De Wu and Wu, {Chiu Wen} and Wu, {Tian Yau} and Wang, {Chun Chieh}",
year = "2013",
month = "2",
day = "1",
doi = "10.3390/e15020416",
language = "English",
volume = "15",
pages = "416--433",
journal = "Entropy",
issn = "1099-4300",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "2",

}

TY - JOUR

T1 - Multi-Scale analysis based ball bearing defect diagnostics using mahalanobis distance and support vector machine

AU - Wu, Shuen-De

AU - Wu, Chiu Wen

AU - Wu, Tian Yau

AU - Wang, Chun Chieh

PY - 2013/2/1

Y1 - 2013/2/1

N2 - The objective of this research is to investigate the feasibility of utilizing the multi-scale analysis and support vector machine (SVM) classification scheme to diagnose the bearing faults in rotating machinery. For complicated signals, the characteristics of dynamic systems may not be apparently observed in a scale, particularly for the fault-related features of rotating machinery. In this research, the multi-scale analysis is employed to extract the possible fault-related features in different scales, such as the multi-scale entropy (MSE), multi-scale permutation entropy (MPE), multi-scale root-mean-square (MSRMS) and multi-band spectrum entropy (MBSE). Some of the features are then selected as the inputs of the support vector machine (SVM) classifier through the Fisher score (FS) as well as the Mahalanobis distance (MD) evaluations. The vibration signals of bearing test data at Case Western Reserve University (CWRU) are utilized as the illustrated examples. The analysis results demonstrate that an accurate bearing defect diagnosis can be achieved by using the extracted machine features in different scales. It can be also noted that the diagnostic results of bearing faults can be further enhanced through the feature selection procedures of FS and MD evaluations.

AB - The objective of this research is to investigate the feasibility of utilizing the multi-scale analysis and support vector machine (SVM) classification scheme to diagnose the bearing faults in rotating machinery. For complicated signals, the characteristics of dynamic systems may not be apparently observed in a scale, particularly for the fault-related features of rotating machinery. In this research, the multi-scale analysis is employed to extract the possible fault-related features in different scales, such as the multi-scale entropy (MSE), multi-scale permutation entropy (MPE), multi-scale root-mean-square (MSRMS) and multi-band spectrum entropy (MBSE). Some of the features are then selected as the inputs of the support vector machine (SVM) classifier through the Fisher score (FS) as well as the Mahalanobis distance (MD) evaluations. The vibration signals of bearing test data at Case Western Reserve University (CWRU) are utilized as the illustrated examples. The analysis results demonstrate that an accurate bearing defect diagnosis can be achieved by using the extracted machine features in different scales. It can be also noted that the diagnostic results of bearing faults can be further enhanced through the feature selection procedures of FS and MD evaluations.

KW - Fisher score (FS)

KW - Mahalanobis distance (MD)

KW - Multi-band spectrum entropy (MBSE)

KW - Multi-scale entropy (MSE)

KW - Multi-scale permutation entropy (MPE)

KW - Multi-scale root-mean-square (MSRMS)

KW - Support vector machine (SVM)

UR - http://www.scopus.com/inward/record.url?scp=84874788954&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874788954&partnerID=8YFLogxK

U2 - 10.3390/e15020416

DO - 10.3390/e15020416

M3 - Article

VL - 15

SP - 416

EP - 433

JO - Entropy

JF - Entropy

SN - 1099-4300

IS - 2

ER -