Machine fault diagnosis using mutual information and informative wavelet

Reza Tafreshi, Farrokh Sassani, Hossein Ahmadi, Guy Dumont

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

This paper deals with an application of wavelets for feature extraction and classification of machine faults. The statistical approach referred to as informative wavelet algorithm is utilized to generate wavelets and subsequent coefficients that are used as feature variables for the classification and diagnosis of machine faults. Informative wavelets are referred to classes of functions generated from elements of a dictionary of orthogonal bases, such as wavelet packet dictionary. Training data are used to construct probability distributions required for the computation of the entropy and mutual information. In our data analysis, we have used machine data acquired from a single cylinder engine under a series of induced faults in a test environment. The objective of the experiment was to evaluate the performance of the informative wavelet algorithm in classifying faults using real-world machine data and to examine the extent to which the results were influenced by different analyzing wavelets chosen for data analysis. The correlation structure of the informative wavelets as well as coefficient matrix are also examined.

Original languageEnglish
Title of host publicationIntegration of Practice-Oriented Knowledge Technology: Trends and Prospectives
PublisherSpringer-Verlag Berlin Heidelberg
Pages183-192
Number of pages10
ISBN (Electronic)9783642344718
ISBN (Print)3642344704, 9783642344701
DOIs
Publication statusPublished - 1 Aug 2013

Fingerprint

Glossaries
Failure analysis
Engine cylinders
Probability distributions
Feature extraction
Entropy
Experiments

Keywords

  • Fault diagnosis
  • informative wavelets
  • wavelet packet analysis

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Tafreshi, R., Sassani, F., Ahmadi, H., & Dumont, G. (2013). Machine fault diagnosis using mutual information and informative wavelet. In Integration of Practice-Oriented Knowledge Technology: Trends and Prospectives (pp. 183-192). Springer-Verlag Berlin Heidelberg. https://doi.org/10.1007/978-3-642-34471-8_15

Machine fault diagnosis using mutual information and informative wavelet. / Tafreshi, Reza; Sassani, Farrokh; Ahmadi, Hossein; Dumont, Guy.

Integration of Practice-Oriented Knowledge Technology: Trends and Prospectives. Springer-Verlag Berlin Heidelberg, 2013. p. 183-192.

Research output: Chapter in Book/Report/Conference proceedingChapter

Tafreshi, R, Sassani, F, Ahmadi, H & Dumont, G 2013, Machine fault diagnosis using mutual information and informative wavelet. in Integration of Practice-Oriented Knowledge Technology: Trends and Prospectives. Springer-Verlag Berlin Heidelberg, pp. 183-192. https://doi.org/10.1007/978-3-642-34471-8_15
Tafreshi R, Sassani F, Ahmadi H, Dumont G. Machine fault diagnosis using mutual information and informative wavelet. In Integration of Practice-Oriented Knowledge Technology: Trends and Prospectives. Springer-Verlag Berlin Heidelberg. 2013. p. 183-192 https://doi.org/10.1007/978-3-642-34471-8_15
Tafreshi, Reza ; Sassani, Farrokh ; Ahmadi, Hossein ; Dumont, Guy. / Machine fault diagnosis using mutual information and informative wavelet. Integration of Practice-Oriented Knowledge Technology: Trends and Prospectives. Springer-Verlag Berlin Heidelberg, 2013. pp. 183-192
@inbook{ba12123ac46d4d198b236ee558dcfae5,
title = "Machine fault diagnosis using mutual information and informative wavelet",
abstract = "This paper deals with an application of wavelets for feature extraction and classification of machine faults. The statistical approach referred to as informative wavelet algorithm is utilized to generate wavelets and subsequent coefficients that are used as feature variables for the classification and diagnosis of machine faults. Informative wavelets are referred to classes of functions generated from elements of a dictionary of orthogonal bases, such as wavelet packet dictionary. Training data are used to construct probability distributions required for the computation of the entropy and mutual information. In our data analysis, we have used machine data acquired from a single cylinder engine under a series of induced faults in a test environment. The objective of the experiment was to evaluate the performance of the informative wavelet algorithm in classifying faults using real-world machine data and to examine the extent to which the results were influenced by different analyzing wavelets chosen for data analysis. The correlation structure of the informative wavelets as well as coefficient matrix are also examined.",
keywords = "Fault diagnosis, informative wavelets, wavelet packet analysis",
author = "Reza Tafreshi and Farrokh Sassani and Hossein Ahmadi and Guy Dumont",
year = "2013",
month = "8",
day = "1",
doi = "10.1007/978-3-642-34471-8_15",
language = "English",
isbn = "3642344704",
pages = "183--192",
booktitle = "Integration of Practice-Oriented Knowledge Technology: Trends and Prospectives",
publisher = "Springer-Verlag Berlin Heidelberg",

}

TY - CHAP

T1 - Machine fault diagnosis using mutual information and informative wavelet

AU - Tafreshi, Reza

AU - Sassani, Farrokh

AU - Ahmadi, Hossein

AU - Dumont, Guy

PY - 2013/8/1

Y1 - 2013/8/1

N2 - This paper deals with an application of wavelets for feature extraction and classification of machine faults. The statistical approach referred to as informative wavelet algorithm is utilized to generate wavelets and subsequent coefficients that are used as feature variables for the classification and diagnosis of machine faults. Informative wavelets are referred to classes of functions generated from elements of a dictionary of orthogonal bases, such as wavelet packet dictionary. Training data are used to construct probability distributions required for the computation of the entropy and mutual information. In our data analysis, we have used machine data acquired from a single cylinder engine under a series of induced faults in a test environment. The objective of the experiment was to evaluate the performance of the informative wavelet algorithm in classifying faults using real-world machine data and to examine the extent to which the results were influenced by different analyzing wavelets chosen for data analysis. The correlation structure of the informative wavelets as well as coefficient matrix are also examined.

AB - This paper deals with an application of wavelets for feature extraction and classification of machine faults. The statistical approach referred to as informative wavelet algorithm is utilized to generate wavelets and subsequent coefficients that are used as feature variables for the classification and diagnosis of machine faults. Informative wavelets are referred to classes of functions generated from elements of a dictionary of orthogonal bases, such as wavelet packet dictionary. Training data are used to construct probability distributions required for the computation of the entropy and mutual information. In our data analysis, we have used machine data acquired from a single cylinder engine under a series of induced faults in a test environment. The objective of the experiment was to evaluate the performance of the informative wavelet algorithm in classifying faults using real-world machine data and to examine the extent to which the results were influenced by different analyzing wavelets chosen for data analysis. The correlation structure of the informative wavelets as well as coefficient matrix are also examined.

KW - Fault diagnosis

KW - informative wavelets

KW - wavelet packet analysis

UR - http://www.scopus.com/inward/record.url?scp=84929526841&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84929526841&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-34471-8_15

DO - 10.1007/978-3-642-34471-8_15

M3 - Chapter

SN - 3642344704

SN - 9783642344701

SP - 183

EP - 192

BT - Integration of Practice-Oriented Knowledge Technology: Trends and Prospectives

PB - Springer-Verlag Berlin Heidelberg

ER -