A comparative study of three artificial neural networks for the detection and classification of gear faults

Research output: Contribution to journalReview article

53 Citations (Scopus)

Abstract

Artificial neural networks (ANN) have been recognized as a powerful tool for classification and pattern recognition in various fields of applications. This paper presents an overview of three ANN architectures and the results of applying those ANNs for the detection and classification of malfunction, wear and damage of a gearbox operating under steady state conditions. The ANN models studied are: feed forward back propagation (FFBP), functional link network (FLN) and learning vector quantization (LVQ). Three artificial defects were deliberately introduced to the gearbox and these are: (1) loose key, (2) single tooth flank wear and (3) full tooth breakage (missing tooth). Vibration signals, collected from extensive experimentation, were analyzed using time and frequency domain descriptors that were used as feature vectors to feed the ANNs. The results show that, for this study, the FLN learns more quickly and is more accurate in operation than the FFBP or the LVQ. The LVQ algorithm exhibits faster rate of convergence than the FFBP but suffers more from misclassifications.

Original languageEnglish (US)
Pages (from-to)261-277
Number of pages17
JournalInternational Journal of General Systems
Volume34
Issue number3
DOIs
StatePublished - Jun 1 2005

Fingerprint

Learning Vector Quantization
Vector quantization
Back Propagation
Feedforward
Backpropagation
Comparative Study
Artificial Neural Network
Gears
Gearbox
Fault
Neural networks
Wear of materials
Vibration Signal
Breakage
Misclassification
Network Architecture
Feature Vector
Network architecture
Neural Network Model
Experimentation

All Science Journal Classification (ASJC) codes

  • Computational Theory and Mathematics
  • Theoretical Computer Science

Cite this

@article{3eaef8cfb72c4a3288e624758ab0ac20,
title = "A comparative study of three artificial neural networks for the detection and classification of gear faults",
abstract = "Artificial neural networks (ANN) have been recognized as a powerful tool for classification and pattern recognition in various fields of applications. This paper presents an overview of three ANN architectures and the results of applying those ANNs for the detection and classification of malfunction, wear and damage of a gearbox operating under steady state conditions. The ANN models studied are: feed forward back propagation (FFBP), functional link network (FLN) and learning vector quantization (LVQ). Three artificial defects were deliberately introduced to the gearbox and these are: (1) loose key, (2) single tooth flank wear and (3) full tooth breakage (missing tooth). Vibration signals, collected from extensive experimentation, were analyzed using time and frequency domain descriptors that were used as feature vectors to feed the ANNs. The results show that, for this study, the FLN learns more quickly and is more accurate in operation than the FFBP or the LVQ. The LVQ algorithm exhibits faster rate of convergence than the FFBP but suffers more from misclassifications.",
author = "Issam Abu-Mahfouz",
year = "2005",
month = "6",
day = "1",
doi = "10.1080/03081070500065726",
language = "English (US)",
volume = "34",
pages = "261--277",
journal = "International Journal of General Systems",
issn = "0308-1079",
publisher = "Taylor and Francis Ltd.",
number = "3",

}

TY - JOUR

T1 - A comparative study of three artificial neural networks for the detection and classification of gear faults

AU - Abu-Mahfouz, Issam

PY - 2005/6/1

Y1 - 2005/6/1

N2 - Artificial neural networks (ANN) have been recognized as a powerful tool for classification and pattern recognition in various fields of applications. This paper presents an overview of three ANN architectures and the results of applying those ANNs for the detection and classification of malfunction, wear and damage of a gearbox operating under steady state conditions. The ANN models studied are: feed forward back propagation (FFBP), functional link network (FLN) and learning vector quantization (LVQ). Three artificial defects were deliberately introduced to the gearbox and these are: (1) loose key, (2) single tooth flank wear and (3) full tooth breakage (missing tooth). Vibration signals, collected from extensive experimentation, were analyzed using time and frequency domain descriptors that were used as feature vectors to feed the ANNs. The results show that, for this study, the FLN learns more quickly and is more accurate in operation than the FFBP or the LVQ. The LVQ algorithm exhibits faster rate of convergence than the FFBP but suffers more from misclassifications.

AB - Artificial neural networks (ANN) have been recognized as a powerful tool for classification and pattern recognition in various fields of applications. This paper presents an overview of three ANN architectures and the results of applying those ANNs for the detection and classification of malfunction, wear and damage of a gearbox operating under steady state conditions. The ANN models studied are: feed forward back propagation (FFBP), functional link network (FLN) and learning vector quantization (LVQ). Three artificial defects were deliberately introduced to the gearbox and these are: (1) loose key, (2) single tooth flank wear and (3) full tooth breakage (missing tooth). Vibration signals, collected from extensive experimentation, were analyzed using time and frequency domain descriptors that were used as feature vectors to feed the ANNs. The results show that, for this study, the FLN learns more quickly and is more accurate in operation than the FFBP or the LVQ. The LVQ algorithm exhibits faster rate of convergence than the FFBP but suffers more from misclassifications.

UR - http://www.scopus.com/inward/record.url?scp=27344460283&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=27344460283&partnerID=8YFLogxK

U2 - 10.1080/03081070500065726

DO - 10.1080/03081070500065726

M3 - Review article

VL - 34

SP - 261

EP - 277

JO - International Journal of General Systems

JF - International Journal of General Systems

SN - 0308-1079

IS - 3

ER -