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

H Al-Bugharbee, I Trendafilova

Research output: Contribution to journalArticle

Abstract

In this study, a new methodology for fault detection in rolling element bearings is proposed, which is based on singular spectrum analysis (SSA). The main idea of the methodology is to build a baseline space from the feature vectors corresponding to the healthy bearing condition. This baseline space is made from the directions of the first three principal components, which are obtained from the decomposition stage of the singular spectrum analysis. Then, the lagged version of any new signal corresponding to a measured (possibly damaged) condition is projected onto this baseline space in order to assess its similarity to the baseline condition. The Euclidean norms of these projections are used to form three-dimensional feature vectors. The category of a new signal vector is determined on the basis of the Mahalanobis distance (MD) of its feature vector to the baseline ones. The methodology is validated using datasets acquired from two different test-rigs. From the results obtained for the correct classification rate, it is shown that this methodology performs very well. The suggested methodology also has simple steps and is easy to apply.
LanguageEnglish
Pages26-35
Number of pages10
JournalInternational Journal of Condition Monitoring
Volume7
Issue number2
DOIs
Publication statusPublished - 31 May 2017

Fingerprint

Bearings (structural)
Fault detection
Spectrum analysis
Decomposition

Keywords

  • fault detection
  • singular spectrum analysis
  • rolling element bearings

Cite this

@article{585e0101dac24980bbe4b7694b98193c,
title = "A new methodology for fault detection in rolling element bearings using singular spectrum analysis",
abstract = "In this study, a new methodology for fault detection in rolling element bearings is proposed, which is based on singular spectrum analysis (SSA). The main idea of the methodology is to build a baseline space from the feature vectors corresponding to the healthy bearing condition. This baseline space is made from the directions of the first three principal components, which are obtained from the decomposition stage of the singular spectrum analysis. Then, the lagged version of any new signal corresponding to a measured (possibly damaged) condition is projected onto this baseline space in order to assess its similarity to the baseline condition. The Euclidean norms of these projections are used to form three-dimensional feature vectors. The category of a new signal vector is determined on the basis of the Mahalanobis distance (MD) of its feature vector to the baseline ones. The methodology is validated using datasets acquired from two different test-rigs. From the results obtained for the correct classification rate, it is shown that this methodology performs very well. The suggested methodology also has simple steps and is easy to apply.",
keywords = "fault detection, singular spectrum analysis, rolling element bearings",
author = "H Al-Bugharbee and I Trendafilova",
year = "2017",
month = "5",
day = "31",
doi = "10.1784/204764217821144287",
language = "English",
volume = "7",
pages = "26--35",
journal = "International Journal of Condition Monitoring",
issn = "2047-6426",
number = "2",

}

A new methodology for fault detection in rolling element bearings using singular spectrum analysis. / Al-Bugharbee, H; Trendafilova, I.

In: International Journal of Condition Monitoring, Vol. 7, No. 2, 31.05.2017, p. 26-35.

Research output: Contribution to journalArticle

TY - JOUR

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

AU - Al-Bugharbee, H

AU - Trendafilova, I

PY - 2017/5/31

Y1 - 2017/5/31

N2 - In this study, a new methodology for fault detection in rolling element bearings is proposed, which is based on singular spectrum analysis (SSA). The main idea of the methodology is to build a baseline space from the feature vectors corresponding to the healthy bearing condition. This baseline space is made from the directions of the first three principal components, which are obtained from the decomposition stage of the singular spectrum analysis. Then, the lagged version of any new signal corresponding to a measured (possibly damaged) condition is projected onto this baseline space in order to assess its similarity to the baseline condition. The Euclidean norms of these projections are used to form three-dimensional feature vectors. The category of a new signal vector is determined on the basis of the Mahalanobis distance (MD) of its feature vector to the baseline ones. The methodology is validated using datasets acquired from two different test-rigs. From the results obtained for the correct classification rate, it is shown that this methodology performs very well. The suggested methodology also has simple steps and is easy to apply.

AB - In this study, a new methodology for fault detection in rolling element bearings is proposed, which is based on singular spectrum analysis (SSA). The main idea of the methodology is to build a baseline space from the feature vectors corresponding to the healthy bearing condition. This baseline space is made from the directions of the first three principal components, which are obtained from the decomposition stage of the singular spectrum analysis. Then, the lagged version of any new signal corresponding to a measured (possibly damaged) condition is projected onto this baseline space in order to assess its similarity to the baseline condition. The Euclidean norms of these projections are used to form three-dimensional feature vectors. The category of a new signal vector is determined on the basis of the Mahalanobis distance (MD) of its feature vector to the baseline ones. The methodology is validated using datasets acquired from two different test-rigs. From the results obtained for the correct classification rate, it is shown that this methodology performs very well. The suggested methodology also has simple steps and is easy to apply.

KW - fault detection

KW - singular spectrum analysis

KW - rolling element bearings

U2 - 10.1784/204764217821144287

DO - 10.1784/204764217821144287

M3 - Article

VL - 7

SP - 26

EP - 35

JO - International Journal of Condition Monitoring

T2 - International Journal of Condition Monitoring

JF - International Journal of Condition Monitoring

SN - 2047-6426

IS - 2

ER -