Remaining Useful Life Prediction of Rolling Element Bearings Using Supervised Machine Learning

Xiaochuan Li, Faris Elasha, Suliman Shanbr, David Mba

Research output: Contribution to journalArticle

1 Citation (Scopus)
4 Downloads (Pure)

Abstract

Components of rotating machines, such as shafts, bearings and gears are subject to performance degradation, which if left unattended could lead to failure or breakdown of the entire system. Analyzing condition monitoring data, implementing diagnostic techniques and using machinery prognostic algorithms will bring about accurate estimation of the remaining life and possible failures that may occur. This paper proposes a combination of two supervised machine learning techniques; namely, the regression model and multilayer artificial neural network model, to predict the remaining useful life of rolling element bearings. Root mean square and Kurtosis were analyzed to define the bearing failure stages. The proposed methodology was validated through two case studies involving vibration measurements of an operational wind turbine gearbox and a split cylindrical roller bearing in a test rig.
Original languageEnglish
Pages (from-to)2705
Number of pages17
JournalEnergies
Volume12
Issue number14
DOIs
Publication statusPublished - 15 Jul 2019

Fingerprint

Bearings (structural)
Life Prediction
Supervised Learning
Learning systems
Machine Learning
Cylindrical roller bearings
Vibration measurement
Condition monitoring
Vibration Measurement
Multilayer Neural Network
Gearbox
Wind turbines
Condition Monitoring
Machinery
Gears
Kurtosis
Wind Turbine
Multilayers
Neural Network Model
Mean Square

Bibliographical note

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Keywords

  • prognostics
  • vibration measurement
  • regression model
  • artificial neural network
  • rolling element bearing
  • remaining useful life

Cite this

Remaining Useful Life Prediction of Rolling Element Bearings Using Supervised Machine Learning. / Li, Xiaochuan; Elasha, Faris; Shanbr, Suliman; Mba, David.

In: Energies, Vol. 12, No. 14, 15.07.2019, p. 2705.

Research output: Contribution to journalArticle

Li, Xiaochuan ; Elasha, Faris ; Shanbr, Suliman ; Mba, David. / Remaining Useful Life Prediction of Rolling Element Bearings Using Supervised Machine Learning. In: Energies. 2019 ; Vol. 12, No. 14. pp. 2705.
@article{bc38452f42db4e9f939f2b4d4e9d47a9,
title = "Remaining Useful Life Prediction of Rolling Element Bearings Using Supervised Machine Learning",
abstract = "Components of rotating machines, such as shafts, bearings and gears are subject to performance degradation, which if left unattended could lead to failure or breakdown of the entire system. Analyzing condition monitoring data, implementing diagnostic techniques and using machinery prognostic algorithms will bring about accurate estimation of the remaining life and possible failures that may occur. This paper proposes a combination of two supervised machine learning techniques; namely, the regression model and multilayer artificial neural network model, to predict the remaining useful life of rolling element bearings. Root mean square and Kurtosis were analyzed to define the bearing failure stages. The proposed methodology was validated through two case studies involving vibration measurements of an operational wind turbine gearbox and a split cylindrical roller bearing in a test rig.",
keywords = "prognostics, vibration measurement, regression model, artificial neural network, rolling element bearing, remaining useful life",
author = "Xiaochuan Li and Faris Elasha and Suliman Shanbr and David Mba",
note = "This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.",
year = "2019",
month = "7",
day = "15",
doi = "10.3390/en12142705",
language = "English",
volume = "12",
pages = "2705",
journal = "Energies",
issn = "1996-1073",
publisher = "MDPI",
number = "14",

}

TY - JOUR

T1 - Remaining Useful Life Prediction of Rolling Element Bearings Using Supervised Machine Learning

AU - Li, Xiaochuan

AU - Elasha, Faris

AU - Shanbr, Suliman

AU - Mba, David

N1 - This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

PY - 2019/7/15

Y1 - 2019/7/15

N2 - Components of rotating machines, such as shafts, bearings and gears are subject to performance degradation, which if left unattended could lead to failure or breakdown of the entire system. Analyzing condition monitoring data, implementing diagnostic techniques and using machinery prognostic algorithms will bring about accurate estimation of the remaining life and possible failures that may occur. This paper proposes a combination of two supervised machine learning techniques; namely, the regression model and multilayer artificial neural network model, to predict the remaining useful life of rolling element bearings. Root mean square and Kurtosis were analyzed to define the bearing failure stages. The proposed methodology was validated through two case studies involving vibration measurements of an operational wind turbine gearbox and a split cylindrical roller bearing in a test rig.

AB - Components of rotating machines, such as shafts, bearings and gears are subject to performance degradation, which if left unattended could lead to failure or breakdown of the entire system. Analyzing condition monitoring data, implementing diagnostic techniques and using machinery prognostic algorithms will bring about accurate estimation of the remaining life and possible failures that may occur. This paper proposes a combination of two supervised machine learning techniques; namely, the regression model and multilayer artificial neural network model, to predict the remaining useful life of rolling element bearings. Root mean square and Kurtosis were analyzed to define the bearing failure stages. The proposed methodology was validated through two case studies involving vibration measurements of an operational wind turbine gearbox and a split cylindrical roller bearing in a test rig.

KW - prognostics

KW - vibration measurement

KW - regression model

KW - artificial neural network

KW - rolling element bearing

KW - remaining useful life

UR - http://www.mendeley.com/research/remaining-useful-life-prediction-rolling-element-bearings-using-supervised-machine-learning

U2 - 10.3390/en12142705

DO - 10.3390/en12142705

M3 - Article

VL - 12

SP - 2705

JO - Energies

JF - Energies

SN - 1996-1073

IS - 14

ER -