The Application of Advanced Signal Processing Techniques to Induction Motor Bearing Condition Diagnosis

D. M. Yang, A. F. Stronach, Peter Frederick Andrew MacConnell

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

Four approaches based on bispectral and wavelet analysis of vibration signals are investigated as signal processing techniques for application in the diagnosis of a number of induction motor rolling element bearing faults. The bearing conditions considered are a normal bearing and bearings with cage and inner and outer race faults. The vibration analysis methods investigated are based on the bispectrum, the bispectrum diagonal slice, the summed bispectrum and wavelets. Singular value decomposition (SVD) is used to extract the most significant features from the vibration signatures and the features are used as inputs to an artificial neural network trained to identify the bearing faults. The results obtained show that the diagnostic system using a supervised multi-layer perceptron type neural network is capable of classifying bearing condition with high success rate, particularly when applied to summed bispectrum signatures.

Original languageEnglish
Pages (from-to)297-308
Number of pages11
JournalMeccanica
Volume38
Issue number2
DOIs
Publication statusPublished - Mar 2003

Keywords

  • artificial neural networks
  • bearing condition monitoring
  • bispectral analysis
  • singular value decomposition and wavelet analysis
  • WAVELET TRANSFORMS
  • BISPECTRUM
  • TURBULENCE
  • VIBRATIONS
  • DEFECTS

Cite this

The Application of Advanced Signal Processing Techniques to Induction Motor Bearing Condition Diagnosis. / Yang, D. M.; Stronach, A. F.; MacConnell, Peter Frederick Andrew.

In: Meccanica, Vol. 38, No. 2, 03.2003, p. 297-308.

Research output: Contribution to journalArticle

Yang, D. M. ; Stronach, A. F. ; MacConnell, Peter Frederick Andrew. / The Application of Advanced Signal Processing Techniques to Induction Motor Bearing Condition Diagnosis. In: Meccanica. 2003 ; Vol. 38, No. 2. pp. 297-308.
@article{713a62bf06be4a46a43d1c2d3458a436,
title = "The Application of Advanced Signal Processing Techniques to Induction Motor Bearing Condition Diagnosis",
abstract = "Four approaches based on bispectral and wavelet analysis of vibration signals are investigated as signal processing techniques for application in the diagnosis of a number of induction motor rolling element bearing faults. The bearing conditions considered are a normal bearing and bearings with cage and inner and outer race faults. The vibration analysis methods investigated are based on the bispectrum, the bispectrum diagonal slice, the summed bispectrum and wavelets. Singular value decomposition (SVD) is used to extract the most significant features from the vibration signatures and the features are used as inputs to an artificial neural network trained to identify the bearing faults. The results obtained show that the diagnostic system using a supervised multi-layer perceptron type neural network is capable of classifying bearing condition with high success rate, particularly when applied to summed bispectrum signatures.",
keywords = "artificial neural networks, bearing condition monitoring, bispectral analysis, singular value decomposition and wavelet analysis, WAVELET TRANSFORMS, BISPECTRUM, TURBULENCE, VIBRATIONS, DEFECTS",
author = "Yang, {D. M.} and Stronach, {A. F.} and MacConnell, {Peter Frederick Andrew}",
year = "2003",
month = "3",
doi = "10.1023/A:1022806705177",
language = "English",
volume = "38",
pages = "297--308",
journal = "Meccanica",
issn = "0025-6455",
publisher = "Springer Netherlands",
number = "2",

}

TY - JOUR

T1 - The Application of Advanced Signal Processing Techniques to Induction Motor Bearing Condition Diagnosis

AU - Yang, D. M.

AU - Stronach, A. F.

AU - MacConnell, Peter Frederick Andrew

PY - 2003/3

Y1 - 2003/3

N2 - Four approaches based on bispectral and wavelet analysis of vibration signals are investigated as signal processing techniques for application in the diagnosis of a number of induction motor rolling element bearing faults. The bearing conditions considered are a normal bearing and bearings with cage and inner and outer race faults. The vibration analysis methods investigated are based on the bispectrum, the bispectrum diagonal slice, the summed bispectrum and wavelets. Singular value decomposition (SVD) is used to extract the most significant features from the vibration signatures and the features are used as inputs to an artificial neural network trained to identify the bearing faults. The results obtained show that the diagnostic system using a supervised multi-layer perceptron type neural network is capable of classifying bearing condition with high success rate, particularly when applied to summed bispectrum signatures.

AB - Four approaches based on bispectral and wavelet analysis of vibration signals are investigated as signal processing techniques for application in the diagnosis of a number of induction motor rolling element bearing faults. The bearing conditions considered are a normal bearing and bearings with cage and inner and outer race faults. The vibration analysis methods investigated are based on the bispectrum, the bispectrum diagonal slice, the summed bispectrum and wavelets. Singular value decomposition (SVD) is used to extract the most significant features from the vibration signatures and the features are used as inputs to an artificial neural network trained to identify the bearing faults. The results obtained show that the diagnostic system using a supervised multi-layer perceptron type neural network is capable of classifying bearing condition with high success rate, particularly when applied to summed bispectrum signatures.

KW - artificial neural networks

KW - bearing condition monitoring

KW - bispectral analysis

KW - singular value decomposition and wavelet analysis

KW - WAVELET TRANSFORMS

KW - BISPECTRUM

KW - TURBULENCE

KW - VIBRATIONS

KW - DEFECTS

U2 - 10.1023/A:1022806705177

DO - 10.1023/A:1022806705177

M3 - Article

VL - 38

SP - 297

EP - 308

JO - Meccanica

JF - Meccanica

SN - 0025-6455

IS - 2

ER -