Fault detection and diagnosis using Principal Component Analysis of vibration data from a reciprocating compressor

M. Ahmed, M. Baqqar, F. Gu, A. D. Ball

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

23 Citations (Scopus)

Abstract

This paper investigates the use of time domain vibration features for detection and diagnosis of different faults from a multi stage reciprocating compressor. Principal Component Analysis (PCA) is used to develop a detection and diagnosis framework in that the effective diagnostic features are selected from PCA of 14 potential features and a PCA model based detection method using Hotelling's T2 and Q statistics is subsequently developed to detect various faults including suction valve leakage, inter-cooler leakage, loose drive belt, and combinations of discharge valve leakage with suction valve leakage, suction valve leakage with intercooler leakage and discharge valve leakage with intercooler leakage. A study of Q -contributions has found two original features: Histogram Lower Bound and Normal Negative log-likelihood which allow full classification of different simulated faults.

Original languageEnglish
Title of host publicationProceedings of the 2012 UKACC International Conference on Control, CONTROL 2012
PublisherIEEE
Pages461-466
Number of pages6
ISBN (Electronic)9781467315609
ISBN (Print)9781467315593
DOIs
Publication statusPublished - 22 Oct 2012
Event9th United Kingdom Automatic Control Council International Conference on Control - Cardiff, United Kingdom
Duration: 3 Sep 20125 Sep 2012
Conference number: 9
http://wikicfp.com/cfp/servlet/event.showcfp?eventid=22012 (Link to Conference Information)

Conference

Conference9th United Kingdom Automatic Control Council International Conference on Control
Abbreviated titleUKACC CONTROL 2012
CountryUnited Kingdom
CityCardiff
Period3/09/125/09/12
Internet address

Fingerprint

Reciprocating compressors
Fault detection
Principal component analysis
Failure analysis
Belt drives
Statistics

Cite this

Ahmed, M., Baqqar, M., Gu, F., & Ball, A. D. (2012). Fault detection and diagnosis using Principal Component Analysis of vibration data from a reciprocating compressor. In Proceedings of the 2012 UKACC International Conference on Control, CONTROL 2012 (pp. 461-466). [6334674] IEEE. https://doi.org/10.1109/CONTROL.2012.6334674
Ahmed, M. ; Baqqar, M. ; Gu, F. ; Ball, A. D. / Fault detection and diagnosis using Principal Component Analysis of vibration data from a reciprocating compressor. Proceedings of the 2012 UKACC International Conference on Control, CONTROL 2012. IEEE, 2012. pp. 461-466
@inproceedings{4a97763f24d84dffb937f8c5d6446780,
title = "Fault detection and diagnosis using Principal Component Analysis of vibration data from a reciprocating compressor",
abstract = "This paper investigates the use of time domain vibration features for detection and diagnosis of different faults from a multi stage reciprocating compressor. Principal Component Analysis (PCA) is used to develop a detection and diagnosis framework in that the effective diagnostic features are selected from PCA of 14 potential features and a PCA model based detection method using Hotelling's T2 and Q statistics is subsequently developed to detect various faults including suction valve leakage, inter-cooler leakage, loose drive belt, and combinations of discharge valve leakage with suction valve leakage, suction valve leakage with intercooler leakage and discharge valve leakage with intercooler leakage. A study of Q -contributions has found two original features: Histogram Lower Bound and Normal Negative log-likelihood which allow full classification of different simulated faults.",
keywords = "contribution plots, Fault detection, Principles component analysis, Reciprocating compressor, Vibration",
author = "M. Ahmed and M. Baqqar and F. Gu and Ball, {A. D.}",
year = "2012",
month = "10",
day = "22",
doi = "10.1109/CONTROL.2012.6334674",
language = "English",
isbn = "9781467315593",
pages = "461--466",
booktitle = "Proceedings of the 2012 UKACC International Conference on Control, CONTROL 2012",
publisher = "IEEE",

}

Ahmed, M, Baqqar, M, Gu, F & Ball, AD 2012, Fault detection and diagnosis using Principal Component Analysis of vibration data from a reciprocating compressor. in Proceedings of the 2012 UKACC International Conference on Control, CONTROL 2012., 6334674, IEEE, pp. 461-466, 9th United Kingdom Automatic Control Council International Conference on Control, Cardiff, United Kingdom, 3/09/12. https://doi.org/10.1109/CONTROL.2012.6334674

Fault detection and diagnosis using Principal Component Analysis of vibration data from a reciprocating compressor. / Ahmed, M.; Baqqar, M.; Gu, F.; Ball, A. D.

Proceedings of the 2012 UKACC International Conference on Control, CONTROL 2012. IEEE, 2012. p. 461-466 6334674.

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

TY - GEN

T1 - Fault detection and diagnosis using Principal Component Analysis of vibration data from a reciprocating compressor

AU - Ahmed, M.

AU - Baqqar, M.

AU - Gu, F.

AU - Ball, A. D.

PY - 2012/10/22

Y1 - 2012/10/22

N2 - This paper investigates the use of time domain vibration features for detection and diagnosis of different faults from a multi stage reciprocating compressor. Principal Component Analysis (PCA) is used to develop a detection and diagnosis framework in that the effective diagnostic features are selected from PCA of 14 potential features and a PCA model based detection method using Hotelling's T2 and Q statistics is subsequently developed to detect various faults including suction valve leakage, inter-cooler leakage, loose drive belt, and combinations of discharge valve leakage with suction valve leakage, suction valve leakage with intercooler leakage and discharge valve leakage with intercooler leakage. A study of Q -contributions has found two original features: Histogram Lower Bound and Normal Negative log-likelihood which allow full classification of different simulated faults.

AB - This paper investigates the use of time domain vibration features for detection and diagnosis of different faults from a multi stage reciprocating compressor. Principal Component Analysis (PCA) is used to develop a detection and diagnosis framework in that the effective diagnostic features are selected from PCA of 14 potential features and a PCA model based detection method using Hotelling's T2 and Q statistics is subsequently developed to detect various faults including suction valve leakage, inter-cooler leakage, loose drive belt, and combinations of discharge valve leakage with suction valve leakage, suction valve leakage with intercooler leakage and discharge valve leakage with intercooler leakage. A study of Q -contributions has found two original features: Histogram Lower Bound and Normal Negative log-likelihood which allow full classification of different simulated faults.

KW - contribution plots

KW - Fault detection

KW - Principles component analysis

KW - Reciprocating compressor

KW - Vibration

UR - http://www.scopus.com/inward/record.url?scp=84869479016&partnerID=8YFLogxK

U2 - 10.1109/CONTROL.2012.6334674

DO - 10.1109/CONTROL.2012.6334674

M3 - Conference contribution

SN - 9781467315593

SP - 461

EP - 466

BT - Proceedings of the 2012 UKACC International Conference on Control, CONTROL 2012

PB - IEEE

ER -

Ahmed M, Baqqar M, Gu F, Ball AD. Fault detection and diagnosis using Principal Component Analysis of vibration data from a reciprocating compressor. In Proceedings of the 2012 UKACC International Conference on Control, CONTROL 2012. IEEE. 2012. p. 461-466. 6334674 https://doi.org/10.1109/CONTROL.2012.6334674