A neural network based approach for machine fault diagnosis

Ari Vepsäläinen

Research output: Book/ReportReportProfessional

Abstract

In this paper a novel approach to classify the state of a machine based on vibration measurements and the use of dynamic neural network is presented. Some comparisons are made between the presented method, the linear classifier, the third-order nonlinear classifier, Markov model based classifier and the recurrent backpropagation network. The proposed classifier can be considered as a spatiotemporal neural network. Spatiotemporal neural networks are used to transform input patterns into timevarying class number output codes. Usually, time is assumed to move forward in small discrete steps. The recurrent backpropagation network and the Spatiotemporal Pattern Recognizer Neural Network (SPRAIN) are other examples of spatiotemporal neural networks. The spatiotemporal neural network can effectively store much more information than most other types of neural networks with same number of nodes. The presented approach is suited to machine maintenance for two reasons: Firstly, it can model temporal relations. For example, it can describe the development of the symptoms of faults. Secondly, it can efficiently handle large amounts of data. Because the spectral signatures of faults may change significantly depending on environmental, operating and physical conditions, the amount of training information is very large.
Original languageEnglish
Place of PublicationEspoo
PublisherVTT Technical Research Centre of Finland
Number of pages27
ISBN (Print)951-38-4007-7
Publication statusPublished - 1991
MoE publication typeNot Eligible

Publication series

NameTiedotteita / Valtion teknillinen tutkimuskeskus
PublisherVTT
No.1274
ISSN (Print)0358-5085

Fingerprint

Failure analysis
Neural networks
Classifiers
Backpropagation
Vibration measurement

Keywords

  • fault diagnosis
  • neural nets
  • classification

Cite this

Vepsäläinen, A. (1991). A neural network based approach for machine fault diagnosis. Espoo: VTT Technical Research Centre of Finland. Valtion teknillinen tutkimuskeskus. Tiedotteita, No. 1274
Vepsäläinen, Ari. / A neural network based approach for machine fault diagnosis. Espoo : VTT Technical Research Centre of Finland, 1991. 27 p. (Valtion teknillinen tutkimuskeskus. Tiedotteita; No. 1274).
@book{1554940825cd4a71903fa39264b1ab57,
title = "A neural network based approach for machine fault diagnosis",
abstract = "In this paper a novel approach to classify the state of a machine based on vibration measurements and the use of dynamic neural network is presented. Some comparisons are made between the presented method, the linear classifier, the third-order nonlinear classifier, Markov model based classifier and the recurrent backpropagation network. The proposed classifier can be considered as a spatiotemporal neural network. Spatiotemporal neural networks are used to transform input patterns into timevarying class number output codes. Usually, time is assumed to move forward in small discrete steps. The recurrent backpropagation network and the Spatiotemporal Pattern Recognizer Neural Network (SPRAIN) are other examples of spatiotemporal neural networks. The spatiotemporal neural network can effectively store much more information than most other types of neural networks with same number of nodes. The presented approach is suited to machine maintenance for two reasons: Firstly, it can model temporal relations. For example, it can describe the development of the symptoms of faults. Secondly, it can efficiently handle large amounts of data. Because the spectral signatures of faults may change significantly depending on environmental, operating and physical conditions, the amount of training information is very large.",
keywords = "fault diagnosis, neural nets, classification",
author = "Ari Veps{\"a}l{\"a}inen",
year = "1991",
language = "English",
isbn = "951-38-4007-7",
series = "Tiedotteita / Valtion teknillinen tutkimuskeskus",
publisher = "VTT Technical Research Centre of Finland",
number = "1274",
address = "Finland",

}

Vepsäläinen, A 1991, A neural network based approach for machine fault diagnosis. Valtion teknillinen tutkimuskeskus. Tiedotteita, no. 1274, VTT Technical Research Centre of Finland, Espoo.

A neural network based approach for machine fault diagnosis. / Vepsäläinen, Ari.

Espoo : VTT Technical Research Centre of Finland, 1991. 27 p. (Valtion teknillinen tutkimuskeskus. Tiedotteita; No. 1274).

Research output: Book/ReportReportProfessional

TY - BOOK

T1 - A neural network based approach for machine fault diagnosis

AU - Vepsäläinen, Ari

PY - 1991

Y1 - 1991

N2 - In this paper a novel approach to classify the state of a machine based on vibration measurements and the use of dynamic neural network is presented. Some comparisons are made between the presented method, the linear classifier, the third-order nonlinear classifier, Markov model based classifier and the recurrent backpropagation network. The proposed classifier can be considered as a spatiotemporal neural network. Spatiotemporal neural networks are used to transform input patterns into timevarying class number output codes. Usually, time is assumed to move forward in small discrete steps. The recurrent backpropagation network and the Spatiotemporal Pattern Recognizer Neural Network (SPRAIN) are other examples of spatiotemporal neural networks. The spatiotemporal neural network can effectively store much more information than most other types of neural networks with same number of nodes. The presented approach is suited to machine maintenance for two reasons: Firstly, it can model temporal relations. For example, it can describe the development of the symptoms of faults. Secondly, it can efficiently handle large amounts of data. Because the spectral signatures of faults may change significantly depending on environmental, operating and physical conditions, the amount of training information is very large.

AB - In this paper a novel approach to classify the state of a machine based on vibration measurements and the use of dynamic neural network is presented. Some comparisons are made between the presented method, the linear classifier, the third-order nonlinear classifier, Markov model based classifier and the recurrent backpropagation network. The proposed classifier can be considered as a spatiotemporal neural network. Spatiotemporal neural networks are used to transform input patterns into timevarying class number output codes. Usually, time is assumed to move forward in small discrete steps. The recurrent backpropagation network and the Spatiotemporal Pattern Recognizer Neural Network (SPRAIN) are other examples of spatiotemporal neural networks. The spatiotemporal neural network can effectively store much more information than most other types of neural networks with same number of nodes. The presented approach is suited to machine maintenance for two reasons: Firstly, it can model temporal relations. For example, it can describe the development of the symptoms of faults. Secondly, it can efficiently handle large amounts of data. Because the spectral signatures of faults may change significantly depending on environmental, operating and physical conditions, the amount of training information is very large.

KW - fault diagnosis

KW - neural nets

KW - classification

M3 - Report

SN - 951-38-4007-7

T3 - Tiedotteita / Valtion teknillinen tutkimuskeskus

BT - A neural network based approach for machine fault diagnosis

PB - VTT Technical Research Centre of Finland

CY - Espoo

ER -

Vepsäläinen A. A neural network based approach for machine fault diagnosis. Espoo: VTT Technical Research Centre of Finland, 1991. 27 p. (Valtion teknillinen tutkimuskeskus. Tiedotteita; No. 1274).