Single and combined fault diagnosis of reciprocating compressor valves using a hybrid deep belief network

Van Tung Tran, Faisal AlThobiani, Tiedo Tinga, Andrew Ball, Gang Niu

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

In this paper, a hybrid deep belief network is proposed to diagnose single and combined faults of suction and discharge valves in a reciprocating compressor. This hybrid integrates the deep belief network structured by multiple stacked restricted Boltzmann machines for pre-training and simplified fuzzy ARTMAP (SFAM) for fault classification. In the pre-training procedure, an algorithm for selecting local receptive fields is used to group the most similar features into the receptive fields of which top values are the units of each layer, and then restricted Boltzmann machine is applied to these units to construct a network. Unsupervised learning is also carried out for each restricted Boltzmann machine layer in this procedure to compute the network weights and biases. Finally, the network output is fed into SFAM to perform fault classification. In order to diagnose the valve faults, three signal types of vibration, pressure, and current are acquired from a two-stage reciprocating air compressor under different valve conditions such as suction leakages, discharge leakages, spring deterioration, and their combination. These signals are subsequently processed so that the useful fault information from the signals can be revealed; next, statistical features in the time and frequency domains are extracted from the signals and used as the inputs for hybrid deep belief network. Performance of hybrid deep belief network in fault classification is compared with that of the original deep belief network and the deep belief network combined with generalized discriminant analysis, where softmax regression is used as a classifier for the latter two models. The results indicate that hybrid deep belief network is more capable of improving the diagnosis accuracy and is feasible in industrial applications.

LanguageEnglish
Pages3767-3780
Number of pages14
JournalProceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science
Volume232
Issue number20
DOIs
Publication statusPublished - 1 Oct 2018

Fingerprint

Reciprocating compressors
Bayesian networks
Failure analysis
Unsupervised learning
Discriminant analysis
Industrial applications
Deterioration
Compressors
Classifiers

Cite this

@article{2134332c44054bdab83d362ec25a5433,
title = "Single and combined fault diagnosis of reciprocating compressor valves using a hybrid deep belief network",
abstract = "In this paper, a hybrid deep belief network is proposed to diagnose single and combined faults of suction and discharge valves in a reciprocating compressor. This hybrid integrates the deep belief network structured by multiple stacked restricted Boltzmann machines for pre-training and simplified fuzzy ARTMAP (SFAM) for fault classification. In the pre-training procedure, an algorithm for selecting local receptive fields is used to group the most similar features into the receptive fields of which top values are the units of each layer, and then restricted Boltzmann machine is applied to these units to construct a network. Unsupervised learning is also carried out for each restricted Boltzmann machine layer in this procedure to compute the network weights and biases. Finally, the network output is fed into SFAM to perform fault classification. In order to diagnose the valve faults, three signal types of vibration, pressure, and current are acquired from a two-stage reciprocating air compressor under different valve conditions such as suction leakages, discharge leakages, spring deterioration, and their combination. These signals are subsequently processed so that the useful fault information from the signals can be revealed; next, statistical features in the time and frequency domains are extracted from the signals and used as the inputs for hybrid deep belief network. Performance of hybrid deep belief network in fault classification is compared with that of the original deep belief network and the deep belief network combined with generalized discriminant analysis, where softmax regression is used as a classifier for the latter two models. The results indicate that hybrid deep belief network is more capable of improving the diagnosis accuracy and is feasible in industrial applications.",
keywords = "Fault diagnosis, hybrid deep belief networks, local receptive fields, reciprocating compressor, simplified fuzzy ARTMAP",
author = "Tran, {Van Tung} and Faisal AlThobiani and Tiedo Tinga and Andrew Ball and Gang Niu",
year = "2018",
month = "10",
day = "1",
doi = "10.1177/0954406217740929",
language = "English",
volume = "232",
pages = "3767--3780",
journal = "Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science",
issn = "0954-4062",
publisher = "SAGE Publications Ltd",
number = "20",

}

Single and combined fault diagnosis of reciprocating compressor valves using a hybrid deep belief network. / Tran, Van Tung; AlThobiani, Faisal; Tinga, Tiedo; Ball, Andrew; Niu, Gang.

In: Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, Vol. 232, No. 20, 01.10.2018, p. 3767-3780.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Single and combined fault diagnosis of reciprocating compressor valves using a hybrid deep belief network

AU - Tran, Van Tung

AU - AlThobiani, Faisal

AU - Tinga, Tiedo

AU - Ball, Andrew

AU - Niu, Gang

PY - 2018/10/1

Y1 - 2018/10/1

N2 - In this paper, a hybrid deep belief network is proposed to diagnose single and combined faults of suction and discharge valves in a reciprocating compressor. This hybrid integrates the deep belief network structured by multiple stacked restricted Boltzmann machines for pre-training and simplified fuzzy ARTMAP (SFAM) for fault classification. In the pre-training procedure, an algorithm for selecting local receptive fields is used to group the most similar features into the receptive fields of which top values are the units of each layer, and then restricted Boltzmann machine is applied to these units to construct a network. Unsupervised learning is also carried out for each restricted Boltzmann machine layer in this procedure to compute the network weights and biases. Finally, the network output is fed into SFAM to perform fault classification. In order to diagnose the valve faults, three signal types of vibration, pressure, and current are acquired from a two-stage reciprocating air compressor under different valve conditions such as suction leakages, discharge leakages, spring deterioration, and their combination. These signals are subsequently processed so that the useful fault information from the signals can be revealed; next, statistical features in the time and frequency domains are extracted from the signals and used as the inputs for hybrid deep belief network. Performance of hybrid deep belief network in fault classification is compared with that of the original deep belief network and the deep belief network combined with generalized discriminant analysis, where softmax regression is used as a classifier for the latter two models. The results indicate that hybrid deep belief network is more capable of improving the diagnosis accuracy and is feasible in industrial applications.

AB - In this paper, a hybrid deep belief network is proposed to diagnose single and combined faults of suction and discharge valves in a reciprocating compressor. This hybrid integrates the deep belief network structured by multiple stacked restricted Boltzmann machines for pre-training and simplified fuzzy ARTMAP (SFAM) for fault classification. In the pre-training procedure, an algorithm for selecting local receptive fields is used to group the most similar features into the receptive fields of which top values are the units of each layer, and then restricted Boltzmann machine is applied to these units to construct a network. Unsupervised learning is also carried out for each restricted Boltzmann machine layer in this procedure to compute the network weights and biases. Finally, the network output is fed into SFAM to perform fault classification. In order to diagnose the valve faults, three signal types of vibration, pressure, and current are acquired from a two-stage reciprocating air compressor under different valve conditions such as suction leakages, discharge leakages, spring deterioration, and their combination. These signals are subsequently processed so that the useful fault information from the signals can be revealed; next, statistical features in the time and frequency domains are extracted from the signals and used as the inputs for hybrid deep belief network. Performance of hybrid deep belief network in fault classification is compared with that of the original deep belief network and the deep belief network combined with generalized discriminant analysis, where softmax regression is used as a classifier for the latter two models. The results indicate that hybrid deep belief network is more capable of improving the diagnosis accuracy and is feasible in industrial applications.

KW - Fault diagnosis

KW - hybrid deep belief networks

KW - local receptive fields

KW - reciprocating compressor

KW - simplified fuzzy ARTMAP

UR - http://www.scopus.com/inward/record.url?scp=85045428927&partnerID=8YFLogxK

U2 - 10.1177/0954406217740929

DO - 10.1177/0954406217740929

M3 - Article

VL - 232

SP - 3767

EP - 3780

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

T2 - 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 - 20

ER -