Componential coding in the condition monitoring of electrical machines: Part 1: Principles and illustrations using simulated typical faults

C. J S Webber, B. S. Payne, F. Gu, A. D. Ball

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper (Part 1) describes the principles of a novel unsupervised adaptive neural network anomaly detection technique, called componential coding, in the context of condition monitoring of electrical machines. Numerical examples are given to illustrate the technique's capabilities. The companion paper (Part 2), which follows, assesses componential coding in its application to real data recorded from a known machine and an entirely unseen machine (a conventional induction motor and a novel transverse flux motor respectively). Componential coding is particularly suited to applications in which no machine-specific tailored techniques have been developed or in which no previous monitoring experience is available. This is because componential coding is an unsupervised technique that derives the features of the data during training, and so requires neither labelling of known faults nor pre-processing to enhance known fault characteristics. Componential coding offers advantages over more familiar unsupervised data processing techniques such as principal component analysis. In addition, componential coding may be implemented in a computationally efficient manner by exploiting the periodic convolution theorem. Periodic convolution also gives the algorithm the advantage of time invariance; i.e. it will work equally well even if the input data signal is offset by arbitrary displacements in time. This means that there is no need to synchronize the input data signal with respect to reference points or to determine the absolute angular position of a rotating part.

LanguageEnglish
Pages883-899
Number of pages17
JournalProceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science
Volume217
Issue number8
DOIs
Publication statusPublished - 1 Aug 2003
Externally publishedYes

Fingerprint

Machine components
Condition monitoring
Convolution
Invariance
Induction motors
Principal component analysis
Labeling
Fluxes
Neural networks
Monitoring
Processing

Cite this

@article{bb5916fd47204c99bfdb2cf5fded4d9c,
title = "Componential coding in the condition monitoring of electrical machines: Part 1: Principles and illustrations using simulated typical faults",
abstract = "This paper (Part 1) describes the principles of a novel unsupervised adaptive neural network anomaly detection technique, called componential coding, in the context of condition monitoring of electrical machines. Numerical examples are given to illustrate the technique's capabilities. The companion paper (Part 2), which follows, assesses componential coding in its application to real data recorded from a known machine and an entirely unseen machine (a conventional induction motor and a novel transverse flux motor respectively). Componential coding is particularly suited to applications in which no machine-specific tailored techniques have been developed or in which no previous monitoring experience is available. This is because componential coding is an unsupervised technique that derives the features of the data during training, and so requires neither labelling of known faults nor pre-processing to enhance known fault characteristics. Componential coding offers advantages over more familiar unsupervised data processing techniques such as principal component analysis. In addition, componential coding may be implemented in a computationally efficient manner by exploiting the periodic convolution theorem. Periodic convolution also gives the algorithm the advantage of time invariance; i.e. it will work equally well even if the input data signal is offset by arbitrary displacements in time. This means that there is no need to synchronize the input data signal with respect to reference points or to determine the absolute angular position of a rotating part.",
keywords = "Auto-encoder, Componential coding, Condition monitoring, Neural network",
author = "Webber, {C. J S} and Payne, {B. S.} and F. Gu and Ball, {A. D.}",
year = "2003",
month = "8",
day = "1",
doi = "10.1243/095440603322310431",
language = "English",
volume = "217",
pages = "883--899",
journal = "Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science",
issn = "0954-4062",
publisher = "SAGE Publications Ltd",
number = "8",

}

TY - JOUR

T1 - Componential coding in the condition monitoring of electrical machines

T2 - Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science

AU - Webber, C. J S

AU - Payne, B. S.

AU - Gu, F.

AU - Ball, A. D.

PY - 2003/8/1

Y1 - 2003/8/1

N2 - This paper (Part 1) describes the principles of a novel unsupervised adaptive neural network anomaly detection technique, called componential coding, in the context of condition monitoring of electrical machines. Numerical examples are given to illustrate the technique's capabilities. The companion paper (Part 2), which follows, assesses componential coding in its application to real data recorded from a known machine and an entirely unseen machine (a conventional induction motor and a novel transverse flux motor respectively). Componential coding is particularly suited to applications in which no machine-specific tailored techniques have been developed or in which no previous monitoring experience is available. This is because componential coding is an unsupervised technique that derives the features of the data during training, and so requires neither labelling of known faults nor pre-processing to enhance known fault characteristics. Componential coding offers advantages over more familiar unsupervised data processing techniques such as principal component analysis. In addition, componential coding may be implemented in a computationally efficient manner by exploiting the periodic convolution theorem. Periodic convolution also gives the algorithm the advantage of time invariance; i.e. it will work equally well even if the input data signal is offset by arbitrary displacements in time. This means that there is no need to synchronize the input data signal with respect to reference points or to determine the absolute angular position of a rotating part.

AB - This paper (Part 1) describes the principles of a novel unsupervised adaptive neural network anomaly detection technique, called componential coding, in the context of condition monitoring of electrical machines. Numerical examples are given to illustrate the technique's capabilities. The companion paper (Part 2), which follows, assesses componential coding in its application to real data recorded from a known machine and an entirely unseen machine (a conventional induction motor and a novel transverse flux motor respectively). Componential coding is particularly suited to applications in which no machine-specific tailored techniques have been developed or in which no previous monitoring experience is available. This is because componential coding is an unsupervised technique that derives the features of the data during training, and so requires neither labelling of known faults nor pre-processing to enhance known fault characteristics. Componential coding offers advantages over more familiar unsupervised data processing techniques such as principal component analysis. In addition, componential coding may be implemented in a computationally efficient manner by exploiting the periodic convolution theorem. Periodic convolution also gives the algorithm the advantage of time invariance; i.e. it will work equally well even if the input data signal is offset by arbitrary displacements in time. This means that there is no need to synchronize the input data signal with respect to reference points or to determine the absolute angular position of a rotating part.

KW - Auto-encoder

KW - Componential coding

KW - Condition monitoring

KW - Neural network

UR - http://www.scopus.com/inward/record.url?scp=0141522906&partnerID=8YFLogxK

U2 - 10.1243/095440603322310431

DO - 10.1243/095440603322310431

M3 - Article

VL - 217

SP - 883

EP - 899

JO - Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science

JF - Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science

SN - 0954-4062

IS - 8

ER -