A methodology for fault detection in rolling element bearings using singular spectrum analysis

Hussein Al Bugharbee, Irina Trendafilova

Research output: Contribution to conferencePaper

19 Downloads (Pure)

Abstract

This paper proposes a vibration-based methodology for fault detection in rolling element bearings, which is based on pure data analysis via singular spectrum method. The method suggests building a baseline space from feature vectors made of the signals measured in the healthy/baseline bearing condition. The feature vectors are made using the Euclidean norms of the first three principal components found for the signals measured. Then, the lagged version of any new signal corresponding to a new (possibly faulty) condition is projected onto this baseline feature space in order to assess its similarity to the baseline condition. The category of a new signal vector is determined based on the Mahalanobis distance (MD) of its feature vector to the baseline space. A validation of the methodology is suggested based on the results from an experimental test rig. The results obtained confirm the effective performance of the suggested methodology. It is made of simple steps and is easy to apply with a perspective to make it automatic and suitable for commercial applications.
Original languageEnglish
Publication statusAccepted/In press - 29 Nov 2017
EventInternational Conference on Engineering Vibration
2017 (ICoEV 2017)
- Sofia, Bulgaria
Duration: 4 Sep 20177 Sep 2017

Conference

ConferenceInternational Conference on Engineering Vibration
2017 (ICoEV 2017)
CountryBulgaria
CitySofia
Period4/09/177/09/17

Fingerprint

Bearings (structural)
Fault detection
Spectrum analysis

Keywords

  • fault detection and diagnosis (FDD)
  • signal vector
  • Mahalanobis distance

Cite this

Al Bugharbee, H., & Trendafilova, I. (Accepted/In press). A methodology for fault detection in rolling element bearings using singular spectrum analysis. Paper presented at International Conference on Engineering Vibration
2017 (ICoEV 2017), Sofia, Bulgaria.
Al Bugharbee, Hussein ; Trendafilova, Irina. / A methodology for fault detection in rolling element bearings using singular spectrum analysis. Paper presented at International Conference on Engineering Vibration
2017 (ICoEV 2017), Sofia, Bulgaria.
@conference{852b13fb643b405188d8319d5ec8066c,
title = "A methodology for fault detection in rolling element bearings using singular spectrum analysis",
abstract = "This paper proposes a vibration-based methodology for fault detection in rolling element bearings, which is based on pure data analysis via singular spectrum method. The method suggests building a baseline space from feature vectors made of the signals measured in the healthy/baseline bearing condition. The feature vectors are made using the Euclidean norms of the first three principal components found for the signals measured. Then, the lagged version of any new signal corresponding to a new (possibly faulty) condition is projected onto this baseline feature space in order to assess its similarity to the baseline condition. The category of a new signal vector is determined based on the Mahalanobis distance (MD) of its feature vector to the baseline space. A validation of the methodology is suggested based on the results from an experimental test rig. The results obtained confirm the effective performance of the suggested methodology. It is made of simple steps and is easy to apply with a perspective to make it automatic and suitable for commercial applications.",
keywords = "fault detection and diagnosis (FDD) , signal vector, Mahalanobis distance",
author = "{Al Bugharbee}, Hussein and Irina Trendafilova",
year = "2017",
month = "11",
day = "29",
language = "English",
note = "International Conference on Engineering Vibration<br/>2017 (ICoEV 2017) ; Conference date: 04-09-2017 Through 07-09-2017",

}

Al Bugharbee, H & Trendafilova, I 2017, 'A methodology for fault detection in rolling element bearings using singular spectrum analysis' Paper presented at International Conference on Engineering Vibration
2017 (ICoEV 2017), Sofia, Bulgaria, 4/09/17 - 7/09/17, .

A methodology for fault detection in rolling element bearings using singular spectrum analysis. / Al Bugharbee, Hussein; Trendafilova, Irina.

2017. Paper presented at International Conference on Engineering Vibration
2017 (ICoEV 2017), Sofia, Bulgaria.

Research output: Contribution to conferencePaper

TY - CONF

T1 - A methodology for fault detection in rolling element bearings using singular spectrum analysis

AU - Al Bugharbee, Hussein

AU - Trendafilova, Irina

PY - 2017/11/29

Y1 - 2017/11/29

N2 - This paper proposes a vibration-based methodology for fault detection in rolling element bearings, which is based on pure data analysis via singular spectrum method. The method suggests building a baseline space from feature vectors made of the signals measured in the healthy/baseline bearing condition. The feature vectors are made using the Euclidean norms of the first three principal components found for the signals measured. Then, the lagged version of any new signal corresponding to a new (possibly faulty) condition is projected onto this baseline feature space in order to assess its similarity to the baseline condition. The category of a new signal vector is determined based on the Mahalanobis distance (MD) of its feature vector to the baseline space. A validation of the methodology is suggested based on the results from an experimental test rig. The results obtained confirm the effective performance of the suggested methodology. It is made of simple steps and is easy to apply with a perspective to make it automatic and suitable for commercial applications.

AB - This paper proposes a vibration-based methodology for fault detection in rolling element bearings, which is based on pure data analysis via singular spectrum method. The method suggests building a baseline space from feature vectors made of the signals measured in the healthy/baseline bearing condition. The feature vectors are made using the Euclidean norms of the first three principal components found for the signals measured. Then, the lagged version of any new signal corresponding to a new (possibly faulty) condition is projected onto this baseline feature space in order to assess its similarity to the baseline condition. The category of a new signal vector is determined based on the Mahalanobis distance (MD) of its feature vector to the baseline space. A validation of the methodology is suggested based on the results from an experimental test rig. The results obtained confirm the effective performance of the suggested methodology. It is made of simple steps and is easy to apply with a perspective to make it automatic and suitable for commercial applications.

KW - fault detection and diagnosis (FDD)

KW - signal vector

KW - Mahalanobis distance

M3 - Paper

ER -

Al Bugharbee H, Trendafilova I. A methodology for fault detection in rolling element bearings using singular spectrum analysis. 2017. Paper presented at International Conference on Engineering Vibration
2017 (ICoEV 2017), Sofia, Bulgaria.