Automatic feature extraction of time-series applied to fault severity assessment of helical gearbox in stationary and non-stationary speed operation

Signals captured in rotating machines to obtain the status of their components can be considered as a source of massive information. In current methods based on artificial intelligence to fault severity assessment, features are first generated by advanced signal processing techniques. Then feature s...

Full description

Bibliographic Details
Authors: Cabrera, Diego, Sancho Caparrini, Fernando, Li, Chuan, Cerrada, Mariela, Sánchez, René-Vinicio, Pacheco, Fannia, Oliveira, José Valente de
Format: article
Status:Versión enviada para evaluación y publicación
Publication Date:2017
Country:España
Institution:Universidad de Sevilla (US)
Repository:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/107111
Online Access:https://hdl.handle.net/11441/107111
https://doi.org/10.1016/j.asoc.2017.04.016
Access Level:Open access
Keyword:Deep learning
Convolution
Auto-encoder
Wavelet packets
Helical gearbox
id ES_0fceba2f2fd32e965d6d9ccae7d5506f
oai_identifier_str oai:idus.us.es:11441/107111
network_acronym_str ES
network_name_str España
repository_id_str
spelling Automatic feature extraction of time-series applied to fault severity assessment of helical gearbox in stationary and non-stationary speed operationCabrera, DiegoSancho Caparrini, FernandoLi, ChuanCerrada, MarielaSánchez, René-VinicioPacheco, FanniaOliveira, José Valente deDeep learningConvolutionAuto-encoderWavelet packetsHelical gearboxSignals captured in rotating machines to obtain the status of their components can be considered as a source of massive information. In current methods based on artificial intelligence to fault severity assessment, features are first generated by advanced signal processing techniques. Then feature selection takes place, often requiring human expertise. This approach, besides time-consuming, is highly dependent on the machinery configuration as in general the results obtained for a mechanical system cannot be reused by other systems. Moreover, the information about time events is often lost along the process, preventing the discovery of faulty state patterns in machines operating under time-varying conditions. In this paper a novel method for automatic feature extraction and estimation of fault severity is proposed to overcome the drawbacks of classical techniques. The proposed method employs a Deep Convolutional Neural Network pre-trained by a Stacked Convolutional Autoencoder. The robustness and accuracy of this new method are validated using a dataset with different severity conditions on failure mode in a helical gearbox, working in both constant and variable speed of operation. The results show that the proposed unsupervised feature extraction method is effective for the estimation of fault severity in helical gearbox, and it has a consistently better performance in comparison with other reported feature extraction methods.Ministerio de Economía y Competitividad TIN2012-37434Ministerio de Economía y Competitividad TIN2013-41086-PUniversidad Politécnica Salesiana (Ecuador) No.002-002-2016-03-03ElsevierCiencias de la Computación e Inteligencia ArtificialMinisterio de Economía y Competitividad (MINECO). EspañaUniversidad Politécnica Salesiana (Ecuador)2017info:eu-repo/semantics/articleinfo:eu-repo/semantics/submittedVersionapplication/pdfapplication/pdfhttps://hdl.handle.net/11441/107111https://doi.org/10.1016/j.asoc.2017.04.016reponame:idUS. Depósito de Investigación de la Universidad de Sevillainstname:Universidad de Sevilla (US)InglésApplied Soft Computing, 58 (September 2017), 53-64.TIN2012-37434TIN2013-41086-PNo.002-002-2016-03-03https://www.sciencedirect.com/science/article/pii/S1568494617301886info:eu-repo/semantics/openAccessoai:idus.us.es:11441/1071112026-06-17T12:51:07Z
dc.title.none.fl_str_mv Automatic feature extraction of time-series applied to fault severity assessment of helical gearbox in stationary and non-stationary speed operation
title Automatic feature extraction of time-series applied to fault severity assessment of helical gearbox in stationary and non-stationary speed operation
spellingShingle Automatic feature extraction of time-series applied to fault severity assessment of helical gearbox in stationary and non-stationary speed operation
Cabrera, Diego
Deep learning
Convolution
Auto-encoder
Wavelet packets
Helical gearbox
title_short Automatic feature extraction of time-series applied to fault severity assessment of helical gearbox in stationary and non-stationary speed operation
title_full Automatic feature extraction of time-series applied to fault severity assessment of helical gearbox in stationary and non-stationary speed operation
title_fullStr Automatic feature extraction of time-series applied to fault severity assessment of helical gearbox in stationary and non-stationary speed operation
title_full_unstemmed Automatic feature extraction of time-series applied to fault severity assessment of helical gearbox in stationary and non-stationary speed operation
title_sort Automatic feature extraction of time-series applied to fault severity assessment of helical gearbox in stationary and non-stationary speed operation
dc.creator.none.fl_str_mv Cabrera, Diego
Sancho Caparrini, Fernando
Li, Chuan
Cerrada, Mariela
Sánchez, René-Vinicio
Pacheco, Fannia
Oliveira, José Valente de
author Cabrera, Diego
author_facet Cabrera, Diego
Sancho Caparrini, Fernando
Li, Chuan
Cerrada, Mariela
Sánchez, René-Vinicio
Pacheco, Fannia
Oliveira, José Valente de
author_role author
author2 Sancho Caparrini, Fernando
Li, Chuan
Cerrada, Mariela
Sánchez, René-Vinicio
Pacheco, Fannia
Oliveira, José Valente de
author2_role author
author
author
author
author
author
dc.contributor.none.fl_str_mv Ciencias de la Computación e Inteligencia Artificial
Ministerio de Economía y Competitividad (MINECO). España
Universidad Politécnica Salesiana (Ecuador)
dc.subject.none.fl_str_mv Deep learning
Convolution
Auto-encoder
Wavelet packets
Helical gearbox
topic Deep learning
Convolution
Auto-encoder
Wavelet packets
Helical gearbox
description Signals captured in rotating machines to obtain the status of their components can be considered as a source of massive information. In current methods based on artificial intelligence to fault severity assessment, features are first generated by advanced signal processing techniques. Then feature selection takes place, often requiring human expertise. This approach, besides time-consuming, is highly dependent on the machinery configuration as in general the results obtained for a mechanical system cannot be reused by other systems. Moreover, the information about time events is often lost along the process, preventing the discovery of faulty state patterns in machines operating under time-varying conditions. In this paper a novel method for automatic feature extraction and estimation of fault severity is proposed to overcome the drawbacks of classical techniques. The proposed method employs a Deep Convolutional Neural Network pre-trained by a Stacked Convolutional Autoencoder. The robustness and accuracy of this new method are validated using a dataset with different severity conditions on failure mode in a helical gearbox, working in both constant and variable speed of operation. The results show that the proposed unsupervised feature extraction method is effective for the estimation of fault severity in helical gearbox, and it has a consistently better performance in comparison with other reported feature extraction methods.
publishDate 2017
dc.date.none.fl_str_mv 2017
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/submittedVersion
format article
status_str submittedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/11441/107111
https://doi.org/10.1016/j.asoc.2017.04.016
url https://hdl.handle.net/11441/107111
https://doi.org/10.1016/j.asoc.2017.04.016
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Applied Soft Computing, 58 (September 2017), 53-64.
TIN2012-37434
TIN2013-41086-P
No.002-002-2016-03-03
https://www.sciencedirect.com/science/article/pii/S1568494617301886
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:idUS. Depósito de Investigación de la Universidad de Sevilla
instname:Universidad de Sevilla (US)
instname_str Universidad de Sevilla (US)
reponame_str idUS. Depósito de Investigación de la Universidad de Sevilla
collection idUS. Depósito de Investigación de la Universidad de Sevilla
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869403474921259009
score 15.301629

Similar Items