An expert system for fault diagnosis in internal combustion engines using wavelet packet transform and neural network

Jian-Da Wu, Chiu Hong Liu

Research output: Contribution to journalArticle

200 Citations (Scopus)

Abstract

In the present study, a fault diagnosis system is proposed for internal combustion engines using wavelet packet transform (WPT) and artificial neural network (ANN) techniques. In fault diagnosis for mechanical systems, WPT is a well-known signal processing technique for fault detection and identification. The signal processing algorithm of the present system is gained from previous work used for speech recognition. In the preprocessing of sound emission signals, WPT coefficients are used for evaluating their entropy and treated as the features to distinguish the fault conditions. Obviously, WPT can improve the continuous wavelet transform (CWT) used over a longer computing time and huge operand. It can also solve the frequency-band disagreement by discrete wavelet transform (DWT) only breaking up the approximation version. In the experimental work, the wavelets are used as mother wavelets to build and perform the proposed WPT technique. In the classification, to verify the effect of the proposed generalized regression neural network (GRNN) in fault diagnosis, a conventional back-propagation network (BPN) is compared with a GRNN network. The experimental results showed the proposed system achieved an average classification accuracy of over 95% for various engine working conditions.

Original languageEnglish
Pages (from-to)4278-4286
Number of pages9
JournalExpert Systems with Applications
Volume36
Issue number3 PART 1
DOIs
Publication statusPublished - 2009 Jan 1

Fingerprint

Internal combustion engines
Expert systems
Failure analysis
Neural networks
Signal processing
Discrete wavelet transforms
Backpropagation
Speech recognition
Fault detection
Wavelet transforms
Frequency bands
Entropy
Acoustic waves
Engines

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Computer Science Applications
  • Artificial Intelligence

Cite this

@article{87a35a64d3904785a86576fd78e0f8e7,
title = "An expert system for fault diagnosis in internal combustion engines using wavelet packet transform and neural network",
abstract = "In the present study, a fault diagnosis system is proposed for internal combustion engines using wavelet packet transform (WPT) and artificial neural network (ANN) techniques. In fault diagnosis for mechanical systems, WPT is a well-known signal processing technique for fault detection and identification. The signal processing algorithm of the present system is gained from previous work used for speech recognition. In the preprocessing of sound emission signals, WPT coefficients are used for evaluating their entropy and treated as the features to distinguish the fault conditions. Obviously, WPT can improve the continuous wavelet transform (CWT) used over a longer computing time and huge operand. It can also solve the frequency-band disagreement by discrete wavelet transform (DWT) only breaking up the approximation version. In the experimental work, the wavelets are used as mother wavelets to build and perform the proposed WPT technique. In the classification, to verify the effect of the proposed generalized regression neural network (GRNN) in fault diagnosis, a conventional back-propagation network (BPN) is compared with a GRNN network. The experimental results showed the proposed system achieved an average classification accuracy of over 95{\%} for various engine working conditions.",
author = "Jian-Da Wu and Liu, {Chiu Hong}",
year = "2009",
month = "1",
day = "1",
doi = "10.1016/j.eswa.2008.03.008",
language = "English",
volume = "36",
pages = "4278--4286",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "3 PART 1",

}

An expert system for fault diagnosis in internal combustion engines using wavelet packet transform and neural network. / Wu, Jian-Da; Liu, Chiu Hong.

In: Expert Systems with Applications, Vol. 36, No. 3 PART 1, 01.01.2009, p. 4278-4286.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An expert system for fault diagnosis in internal combustion engines using wavelet packet transform and neural network

AU - Wu, Jian-Da

AU - Liu, Chiu Hong

PY - 2009/1/1

Y1 - 2009/1/1

N2 - In the present study, a fault diagnosis system is proposed for internal combustion engines using wavelet packet transform (WPT) and artificial neural network (ANN) techniques. In fault diagnosis for mechanical systems, WPT is a well-known signal processing technique for fault detection and identification. The signal processing algorithm of the present system is gained from previous work used for speech recognition. In the preprocessing of sound emission signals, WPT coefficients are used for evaluating their entropy and treated as the features to distinguish the fault conditions. Obviously, WPT can improve the continuous wavelet transform (CWT) used over a longer computing time and huge operand. It can also solve the frequency-band disagreement by discrete wavelet transform (DWT) only breaking up the approximation version. In the experimental work, the wavelets are used as mother wavelets to build and perform the proposed WPT technique. In the classification, to verify the effect of the proposed generalized regression neural network (GRNN) in fault diagnosis, a conventional back-propagation network (BPN) is compared with a GRNN network. The experimental results showed the proposed system achieved an average classification accuracy of over 95% for various engine working conditions.

AB - In the present study, a fault diagnosis system is proposed for internal combustion engines using wavelet packet transform (WPT) and artificial neural network (ANN) techniques. In fault diagnosis for mechanical systems, WPT is a well-known signal processing technique for fault detection and identification. The signal processing algorithm of the present system is gained from previous work used for speech recognition. In the preprocessing of sound emission signals, WPT coefficients are used for evaluating their entropy and treated as the features to distinguish the fault conditions. Obviously, WPT can improve the continuous wavelet transform (CWT) used over a longer computing time and huge operand. It can also solve the frequency-band disagreement by discrete wavelet transform (DWT) only breaking up the approximation version. In the experimental work, the wavelets are used as mother wavelets to build and perform the proposed WPT technique. In the classification, to verify the effect of the proposed generalized regression neural network (GRNN) in fault diagnosis, a conventional back-propagation network (BPN) is compared with a GRNN network. The experimental results showed the proposed system achieved an average classification accuracy of over 95% for various engine working conditions.

UR - http://www.scopus.com/inward/record.url?scp=58349111323&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=58349111323&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2008.03.008

DO - 10.1016/j.eswa.2008.03.008

M3 - Article

AN - SCOPUS:58349111323

VL - 36

SP - 4278

EP - 4286

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 3 PART 1

ER -