Fault diagnosis of reciprocating compressors using revelance vector machines with a genetic algorithm based on vibration data

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

This paper focuses on the development of an advanced fault classifier for monitoring reciprocating compressors (RC) based on vibration signals. Many feature parameters can be used for fault diagnosis, here the classifier is developed based on a relevance vector machine (RVM) which is optimized with genetic algorithms (GA) so determining a more effective subset of the parameters. Both a one-against-one scheme based RVM and a multiclass multi-kernel relevance vector machine (mRVM) have been evaluated to identify a more effective method for implementing the multiclass fault classification for the compressor. The accuracy of both techniques is discussed correspondingly to determine an optimal fault classifier which can correlate with the physical mechanisms underlying the features. The results show that the models perform well, the classification accuracy rate being up to 97% for both algorithms.

Original languageEnglish
Title of host publicationICAC 2014 - Proceedings of the 20th International Conference on Automation and Computing: Future Automation, Computing and Manufacturing
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages164-169
Number of pages6
ISBN (Electronic)9781909522022
DOIs
Publication statusPublished - 24 Oct 2014
Event20th International Conference on Automation and Computing - Cranfield, United Kingdom
Duration: 12 Sep 201413 Sep 2014
Conference number: 20

Conference

Conference20th International Conference on Automation and Computing
Abbreviated titleICAC 2014
CountryUnited Kingdom
CityCranfield
Period12/09/1413/09/14

Fingerprint

Reciprocating compressors
Failure analysis
Classifiers
Genetic algorithms
Compressors
Monitoring

Cite this

Ahmed, M., Smith, A., Gu, F., & Ball, A. D. (2014). Fault diagnosis of reciprocating compressors using revelance vector machines with a genetic algorithm based on vibration data. In ICAC 2014 - Proceedings of the 20th International Conference on Automation and Computing: Future Automation, Computing and Manufacturing (pp. 164-169). [6935480] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IConAC.2014.6935480
Ahmed, M. ; Smith, A. ; Gu, F. ; Ball, A. D. / Fault diagnosis of reciprocating compressors using revelance vector machines with a genetic algorithm based on vibration data. ICAC 2014 - Proceedings of the 20th International Conference on Automation and Computing: Future Automation, Computing and Manufacturing. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 164-169
@inproceedings{e165b715f1e340df87c283e6b02983ba,
title = "Fault diagnosis of reciprocating compressors using revelance vector machines with a genetic algorithm based on vibration data",
abstract = "This paper focuses on the development of an advanced fault classifier for monitoring reciprocating compressors (RC) based on vibration signals. Many feature parameters can be used for fault diagnosis, here the classifier is developed based on a relevance vector machine (RVM) which is optimized with genetic algorithms (GA) so determining a more effective subset of the parameters. Both a one-against-one scheme based RVM and a multiclass multi-kernel relevance vector machine (mRVM) have been evaluated to identify a more effective method for implementing the multiclass fault classification for the compressor. The accuracy of both techniques is discussed correspondingly to determine an optimal fault classifier which can correlate with the physical mechanisms underlying the features. The results show that the models perform well, the classification accuracy rate being up to 97{\%} for both algorithms.",
keywords = "Fault Diagnosis, Genatic Algorithms, multiclass multi-kernel relevance vector machine, Reciprocating Compressor, Relevance Vector Machine",
author = "M. Ahmed and A. Smith and F. Gu and Ball, {A. D.}",
year = "2014",
month = "10",
day = "24",
doi = "10.1109/IConAC.2014.6935480",
language = "English",
pages = "164--169",
booktitle = "ICAC 2014 - Proceedings of the 20th International Conference on Automation and Computing: Future Automation, Computing and Manufacturing",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Ahmed, M, Smith, A, Gu, F & Ball, AD 2014, Fault diagnosis of reciprocating compressors using revelance vector machines with a genetic algorithm based on vibration data. in ICAC 2014 - Proceedings of the 20th International Conference on Automation and Computing: Future Automation, Computing and Manufacturing., 6935480, Institute of Electrical and Electronics Engineers Inc., pp. 164-169, 20th International Conference on Automation and Computing, Cranfield, United Kingdom, 12/09/14. https://doi.org/10.1109/IConAC.2014.6935480

Fault diagnosis of reciprocating compressors using revelance vector machines with a genetic algorithm based on vibration data. / Ahmed, M.; Smith, A.; Gu, F.; Ball, A. D.

ICAC 2014 - Proceedings of the 20th International Conference on Automation and Computing: Future Automation, Computing and Manufacturing. Institute of Electrical and Electronics Engineers Inc., 2014. p. 164-169 6935480.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Fault diagnosis of reciprocating compressors using revelance vector machines with a genetic algorithm based on vibration data

AU - Ahmed, M.

AU - Smith, A.

AU - Gu, F.

AU - Ball, A. D.

PY - 2014/10/24

Y1 - 2014/10/24

N2 - This paper focuses on the development of an advanced fault classifier for monitoring reciprocating compressors (RC) based on vibration signals. Many feature parameters can be used for fault diagnosis, here the classifier is developed based on a relevance vector machine (RVM) which is optimized with genetic algorithms (GA) so determining a more effective subset of the parameters. Both a one-against-one scheme based RVM and a multiclass multi-kernel relevance vector machine (mRVM) have been evaluated to identify a more effective method for implementing the multiclass fault classification for the compressor. The accuracy of both techniques is discussed correspondingly to determine an optimal fault classifier which can correlate with the physical mechanisms underlying the features. The results show that the models perform well, the classification accuracy rate being up to 97% for both algorithms.

AB - This paper focuses on the development of an advanced fault classifier for monitoring reciprocating compressors (RC) based on vibration signals. Many feature parameters can be used for fault diagnosis, here the classifier is developed based on a relevance vector machine (RVM) which is optimized with genetic algorithms (GA) so determining a more effective subset of the parameters. Both a one-against-one scheme based RVM and a multiclass multi-kernel relevance vector machine (mRVM) have been evaluated to identify a more effective method for implementing the multiclass fault classification for the compressor. The accuracy of both techniques is discussed correspondingly to determine an optimal fault classifier which can correlate with the physical mechanisms underlying the features. The results show that the models perform well, the classification accuracy rate being up to 97% for both algorithms.

KW - Fault Diagnosis

KW - Genatic Algorithms

KW - multiclass multi-kernel relevance vector machine

KW - Reciprocating Compressor

KW - Relevance Vector Machine

UR - http://www.scopus.com/inward/record.url?scp=84912065820&partnerID=8YFLogxK

U2 - 10.1109/IConAC.2014.6935480

DO - 10.1109/IConAC.2014.6935480

M3 - Conference contribution

SP - 164

EP - 169

BT - ICAC 2014 - Proceedings of the 20th International Conference on Automation and Computing: Future Automation, Computing and Manufacturing

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Ahmed M, Smith A, Gu F, Ball AD. Fault diagnosis of reciprocating compressors using revelance vector machines with a genetic algorithm based on vibration data. In ICAC 2014 - Proceedings of the 20th International Conference on Automation and Computing: Future Automation, Computing and Manufacturing. Institute of Electrical and Electronics Engineers Inc. 2014. p. 164-169. 6935480 https://doi.org/10.1109/IConAC.2014.6935480