Fault detection of reciprocating compressors using a model from principles component analysis of vibrations

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

Research output: Contribution to journalConference article

10 Citations (Scopus)

Abstract

Traditional vibration monitoring techniques have found it difficult to determine a set of effective diagnostic features due to the high complexity of the vibration signals originating from the many different impact sources and wide ranges of practical operating conditions. In this paper Principal Component Analysis (PCA) is used for selecting vibration feature and detecting different faults in a reciprocating compressor. Vibration datasets were collected from the compressor under baseline condition and five common faults: valve leakage, inter-cooler leakage, suction valve leakage, loose drive belt combined with intercooler leakage and belt loose drive belt combined with suction valve leakage. A model using five PCs has been developed using the baseline data sets and the presence of faults can be detected by comparing the T2 and Q values from the features of fault vibration signals with corresponding thresholds developed from baseline data. However, the Q-statistic procedure produces a better detection as it can separate the five faults completely.

Original languageEnglish
Article number012133
JournalJournal of Physics: Conference Series
Volume364
Issue number1
DOIs
Publication statusPublished - 28 May 2012
Event25th International Congress on Condition Monitoring and Diagnostic Engineering: Sustained Prosperity through Proactive Monitoring, Diagnosis and Management - University of Huddersfield, Huddersfield, United Kingdom
Duration: 18 Jun 201220 Jun 2012
Conference number: 25
http://compeng.hud.ac.uk/comadem2012/ (Link to Conference Website )

Fingerprint

fault detection
compressors
leakage
vibration
suction
principal components analysis
coolers
statistics
thresholds

Cite this

@article{932686d6153f4249b677d8cecbf94130,
title = "Fault detection of reciprocating compressors using a model from principles component analysis of vibrations",
abstract = "Traditional vibration monitoring techniques have found it difficult to determine a set of effective diagnostic features due to the high complexity of the vibration signals originating from the many different impact sources and wide ranges of practical operating conditions. In this paper Principal Component Analysis (PCA) is used for selecting vibration feature and detecting different faults in a reciprocating compressor. Vibration datasets were collected from the compressor under baseline condition and five common faults: valve leakage, inter-cooler leakage, suction valve leakage, loose drive belt combined with intercooler leakage and belt loose drive belt combined with suction valve leakage. A model using five PCs has been developed using the baseline data sets and the presence of faults can be detected by comparing the T2 and Q values from the features of fault vibration signals with corresponding thresholds developed from baseline data. However, the Q-statistic procedure produces a better detection as it can separate the five faults completely.",
keywords = "Fault detection, Principles component analysis, Reciprocating compressor, Vibration",
author = "M. Ahmed and F. Gu and Ball, {A. D.}",
year = "2012",
month = "5",
day = "28",
doi = "10.1088/1742-6596/364/1/012133",
language = "English",
volume = "364",
journal = "Journal of Physics: Conference Series",
issn = "1742-6588",
publisher = "IOP Publishing Ltd.",
number = "1",

}

Fault detection of reciprocating compressors using a model from principles component analysis of vibrations. / Ahmed, M.; Gu, F.; Ball, A. D.

In: Journal of Physics: Conference Series, Vol. 364, No. 1, 012133, 28.05.2012.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Fault detection of reciprocating compressors using a model from principles component analysis of vibrations

AU - Ahmed, M.

AU - Gu, F.

AU - Ball, A. D.

PY - 2012/5/28

Y1 - 2012/5/28

N2 - Traditional vibration monitoring techniques have found it difficult to determine a set of effective diagnostic features due to the high complexity of the vibration signals originating from the many different impact sources and wide ranges of practical operating conditions. In this paper Principal Component Analysis (PCA) is used for selecting vibration feature and detecting different faults in a reciprocating compressor. Vibration datasets were collected from the compressor under baseline condition and five common faults: valve leakage, inter-cooler leakage, suction valve leakage, loose drive belt combined with intercooler leakage and belt loose drive belt combined with suction valve leakage. A model using five PCs has been developed using the baseline data sets and the presence of faults can be detected by comparing the T2 and Q values from the features of fault vibration signals with corresponding thresholds developed from baseline data. However, the Q-statistic procedure produces a better detection as it can separate the five faults completely.

AB - Traditional vibration monitoring techniques have found it difficult to determine a set of effective diagnostic features due to the high complexity of the vibration signals originating from the many different impact sources and wide ranges of practical operating conditions. In this paper Principal Component Analysis (PCA) is used for selecting vibration feature and detecting different faults in a reciprocating compressor. Vibration datasets were collected from the compressor under baseline condition and five common faults: valve leakage, inter-cooler leakage, suction valve leakage, loose drive belt combined with intercooler leakage and belt loose drive belt combined with suction valve leakage. A model using five PCs has been developed using the baseline data sets and the presence of faults can be detected by comparing the T2 and Q values from the features of fault vibration signals with corresponding thresholds developed from baseline data. However, the Q-statistic procedure produces a better detection as it can separate the five faults completely.

KW - Fault detection

KW - Principles component analysis

KW - Reciprocating compressor

KW - Vibration

UR - http://www.scopus.com/inward/record.url?scp=84862308344&partnerID=8YFLogxK

U2 - 10.1088/1742-6596/364/1/012133

DO - 10.1088/1742-6596/364/1/012133

M3 - Conference article

VL - 364

JO - Journal of Physics: Conference Series

JF - Journal of Physics: Conference Series

SN - 1742-6588

IS - 1

M1 - 012133

ER -