An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks

Van Tung Tran, Faisal Al Thobiani, Andrew Ball

Research output: Contribution to journalArticle

184 Citations (Scopus)

Abstract

This paper presents an approach to implement vibration, pressure, and current signals for fault diagnosis of the valves in reciprocating compressors. Due to the complexity of structure and motion of such compressor, the acquired vibration signal normally involves transient impacts and noise. This causes the useful information to be corrupted and difficulty in accurately diagnosing the faults with traditional methods. To reveal the fault patterns contained in this signal, the Teager-Kaiser energy operation (TKEO) is proposed to estimate the amplitude envelopes. In case of pressure and current, the random noise is removed by using a denoising method based on wavelet transform. Subsequently, statistical measures are extracted from all signals to represent the characteristics of the valve conditions. In order to classify the faults of compressor valves, a new type of learning architecture for deep generative model called deep belief networks (DBNs) is applied. DBN employs a hierarchical structure with multiple stacked restricted Boltzmann machines (RBMs) and works through a greedy layer-by-layer learning algorithm. In pattern recognition research areas, DBN has proved to be very effective and provided with high performance for binary values. However, for implementing DBN to fault diagnosis where most of signals are real-valued, RBM with Bernoulli hidden units and Gaussian visible units is considered in this study. The proposed approach is validated with the signals from a two-stage reciprocating air compressor under different valve conditions. To confirm the superiority of DBN in fault classification, its performance is compared with that of relevant vector machine and back propagation neuron networks. The achieved accuracy indicates that the proposed approach is highly reliable and applicable in fault diagnosis of industrial reciprocating machinery.

LanguageEnglish
Pages4113-4122
Number of pages10
JournalExpert Systems with Applications
Volume41
Issue number9
Early online date29 Dec 2013
DOIs
Publication statusPublished - Jul 2014

Fingerprint

Reciprocating compressors
Bayesian networks
Failure analysis
Compressors
Backpropagation
Wavelet transforms
Learning algorithms
Neurons
Pattern recognition
Machinery

Cite this

@article{b4c4bd3882ba46d29723b6e055599bd0,
title = "An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks",
abstract = "This paper presents an approach to implement vibration, pressure, and current signals for fault diagnosis of the valves in reciprocating compressors. Due to the complexity of structure and motion of such compressor, the acquired vibration signal normally involves transient impacts and noise. This causes the useful information to be corrupted and difficulty in accurately diagnosing the faults with traditional methods. To reveal the fault patterns contained in this signal, the Teager-Kaiser energy operation (TKEO) is proposed to estimate the amplitude envelopes. In case of pressure and current, the random noise is removed by using a denoising method based on wavelet transform. Subsequently, statistical measures are extracted from all signals to represent the characteristics of the valve conditions. In order to classify the faults of compressor valves, a new type of learning architecture for deep generative model called deep belief networks (DBNs) is applied. DBN employs a hierarchical structure with multiple stacked restricted Boltzmann machines (RBMs) and works through a greedy layer-by-layer learning algorithm. In pattern recognition research areas, DBN has proved to be very effective and provided with high performance for binary values. However, for implementing DBN to fault diagnosis where most of signals are real-valued, RBM with Bernoulli hidden units and Gaussian visible units is considered in this study. The proposed approach is validated with the signals from a two-stage reciprocating air compressor under different valve conditions. To confirm the superiority of DBN in fault classification, its performance is compared with that of relevant vector machine and back propagation neuron networks. The achieved accuracy indicates that the proposed approach is highly reliable and applicable in fault diagnosis of industrial reciprocating machinery.",
keywords = "Deep belief networks, Fault diagnosis, Reciprocating compressor, Teager-Kaiser energy operator",
author = "Tran, {Van Tung} and {Al Thobiani}, Faisal and Andrew Ball",
year = "2014",
month = "7",
doi = "10.1016/j.eswa.2013.12.026",
language = "English",
volume = "41",
pages = "4113--4122",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "9",

}

An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks. / Tran, Van Tung; Al Thobiani, Faisal; Ball, Andrew.

In: Expert Systems with Applications, Vol. 41, No. 9, 07.2014, p. 4113-4122.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks

AU - Tran, Van Tung

AU - Al Thobiani, Faisal

AU - Ball, Andrew

PY - 2014/7

Y1 - 2014/7

N2 - This paper presents an approach to implement vibration, pressure, and current signals for fault diagnosis of the valves in reciprocating compressors. Due to the complexity of structure and motion of such compressor, the acquired vibration signal normally involves transient impacts and noise. This causes the useful information to be corrupted and difficulty in accurately diagnosing the faults with traditional methods. To reveal the fault patterns contained in this signal, the Teager-Kaiser energy operation (TKEO) is proposed to estimate the amplitude envelopes. In case of pressure and current, the random noise is removed by using a denoising method based on wavelet transform. Subsequently, statistical measures are extracted from all signals to represent the characteristics of the valve conditions. In order to classify the faults of compressor valves, a new type of learning architecture for deep generative model called deep belief networks (DBNs) is applied. DBN employs a hierarchical structure with multiple stacked restricted Boltzmann machines (RBMs) and works through a greedy layer-by-layer learning algorithm. In pattern recognition research areas, DBN has proved to be very effective and provided with high performance for binary values. However, for implementing DBN to fault diagnosis where most of signals are real-valued, RBM with Bernoulli hidden units and Gaussian visible units is considered in this study. The proposed approach is validated with the signals from a two-stage reciprocating air compressor under different valve conditions. To confirm the superiority of DBN in fault classification, its performance is compared with that of relevant vector machine and back propagation neuron networks. The achieved accuracy indicates that the proposed approach is highly reliable and applicable in fault diagnosis of industrial reciprocating machinery.

AB - This paper presents an approach to implement vibration, pressure, and current signals for fault diagnosis of the valves in reciprocating compressors. Due to the complexity of structure and motion of such compressor, the acquired vibration signal normally involves transient impacts and noise. This causes the useful information to be corrupted and difficulty in accurately diagnosing the faults with traditional methods. To reveal the fault patterns contained in this signal, the Teager-Kaiser energy operation (TKEO) is proposed to estimate the amplitude envelopes. In case of pressure and current, the random noise is removed by using a denoising method based on wavelet transform. Subsequently, statistical measures are extracted from all signals to represent the characteristics of the valve conditions. In order to classify the faults of compressor valves, a new type of learning architecture for deep generative model called deep belief networks (DBNs) is applied. DBN employs a hierarchical structure with multiple stacked restricted Boltzmann machines (RBMs) and works through a greedy layer-by-layer learning algorithm. In pattern recognition research areas, DBN has proved to be very effective and provided with high performance for binary values. However, for implementing DBN to fault diagnosis where most of signals are real-valued, RBM with Bernoulli hidden units and Gaussian visible units is considered in this study. The proposed approach is validated with the signals from a two-stage reciprocating air compressor under different valve conditions. To confirm the superiority of DBN in fault classification, its performance is compared with that of relevant vector machine and back propagation neuron networks. The achieved accuracy indicates that the proposed approach is highly reliable and applicable in fault diagnosis of industrial reciprocating machinery.

KW - Deep belief networks

KW - Fault diagnosis

KW - Reciprocating compressor

KW - Teager-Kaiser energy operator

UR - http://www.scopus.com/inward/record.url?scp=84893464266&partnerID=8YFLogxK

UR - https://www.journals.elsevier.com/expert-systems-with-applications

U2 - 10.1016/j.eswa.2013.12.026

DO - 10.1016/j.eswa.2013.12.026

M3 - Article

VL - 41

SP - 4113

EP - 4122

JO - Expert Systems with Applications

T2 - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 9

ER -