Cargando…

A Transfer Learning Framework with a One-Dimensional Deep Subdomain Adaptation Network for Bearing Fault Diagnosis under Different Working Conditions

Accurate and fast rolling bearing fault diagnosis is required for the normal operation of rotating machinery and equipment. Although deep learning methods have achieved excellent results for rolling bearing fault diagnosis, the performance of most methods declines sharply when the working conditions...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Ruixin, Gu, Yu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8876626/
https://www.ncbi.nlm.nih.gov/pubmed/35214528
http://dx.doi.org/10.3390/s22041624
_version_ 1784658218170974208
author Zhang, Ruixin
Gu, Yu
author_facet Zhang, Ruixin
Gu, Yu
author_sort Zhang, Ruixin
collection PubMed
description Accurate and fast rolling bearing fault diagnosis is required for the normal operation of rotating machinery and equipment. Although deep learning methods have achieved excellent results for rolling bearing fault diagnosis, the performance of most methods declines sharply when the working conditions change. To address this issue, we propose a one-dimensional lightweight deep subdomain adaptation network (1D-LDSAN) for faster and more accurate rolling bearing fault diagnosis. The framework uses a one-dimensional lightweight convolutional neural network backbone for the rapid extraction of advanced features from raw vibration signals. The local maximum mean discrepancy (LMMD) is employed to match the probability distribution between the source domain and the target domain data, and a fully connected neural network is used to identify the fault classes. Bearing data from the Case Western Reserve University (CWRU) datasets were used to validate the performance of the proposed framework under different working conditions. The experimental results show that the classification accuracy for 12 tasks was higher for the 1D-LDSAN than for mainstream transfer learning methods. Moreover, the proposed framework provides satisfactory results when a small proportion of the unlabeled target domain data is used for training.
format Online
Article
Text
id pubmed-8876626
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-88766262022-02-26 A Transfer Learning Framework with a One-Dimensional Deep Subdomain Adaptation Network for Bearing Fault Diagnosis under Different Working Conditions Zhang, Ruixin Gu, Yu Sensors (Basel) Article Accurate and fast rolling bearing fault diagnosis is required for the normal operation of rotating machinery and equipment. Although deep learning methods have achieved excellent results for rolling bearing fault diagnosis, the performance of most methods declines sharply when the working conditions change. To address this issue, we propose a one-dimensional lightweight deep subdomain adaptation network (1D-LDSAN) for faster and more accurate rolling bearing fault diagnosis. The framework uses a one-dimensional lightweight convolutional neural network backbone for the rapid extraction of advanced features from raw vibration signals. The local maximum mean discrepancy (LMMD) is employed to match the probability distribution between the source domain and the target domain data, and a fully connected neural network is used to identify the fault classes. Bearing data from the Case Western Reserve University (CWRU) datasets were used to validate the performance of the proposed framework under different working conditions. The experimental results show that the classification accuracy for 12 tasks was higher for the 1D-LDSAN than for mainstream transfer learning methods. Moreover, the proposed framework provides satisfactory results when a small proportion of the unlabeled target domain data is used for training. MDPI 2022-02-18 /pmc/articles/PMC8876626/ /pubmed/35214528 http://dx.doi.org/10.3390/s22041624 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Zhang, Ruixin
Gu, Yu
A Transfer Learning Framework with a One-Dimensional Deep Subdomain Adaptation Network for Bearing Fault Diagnosis under Different Working Conditions
title A Transfer Learning Framework with a One-Dimensional Deep Subdomain Adaptation Network for Bearing Fault Diagnosis under Different Working Conditions
title_full A Transfer Learning Framework with a One-Dimensional Deep Subdomain Adaptation Network for Bearing Fault Diagnosis under Different Working Conditions
title_fullStr A Transfer Learning Framework with a One-Dimensional Deep Subdomain Adaptation Network for Bearing Fault Diagnosis under Different Working Conditions
title_full_unstemmed A Transfer Learning Framework with a One-Dimensional Deep Subdomain Adaptation Network for Bearing Fault Diagnosis under Different Working Conditions
title_short A Transfer Learning Framework with a One-Dimensional Deep Subdomain Adaptation Network for Bearing Fault Diagnosis under Different Working Conditions
title_sort transfer learning framework with a one-dimensional deep subdomain adaptation network for bearing fault diagnosis under different working conditions
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8876626/
https://www.ncbi.nlm.nih.gov/pubmed/35214528
http://dx.doi.org/10.3390/s22041624
work_keys_str_mv AT zhangruixin atransferlearningframeworkwithaonedimensionaldeepsubdomainadaptationnetworkforbearingfaultdiagnosisunderdifferentworkingconditions
AT guyu atransferlearningframeworkwithaonedimensionaldeepsubdomainadaptationnetworkforbearingfaultdiagnosisunderdifferentworkingconditions
AT zhangruixin transferlearningframeworkwithaonedimensionaldeepsubdomainadaptationnetworkforbearingfaultdiagnosisunderdifferentworkingconditions
AT guyu transferlearningframeworkwithaonedimensionaldeepsubdomainadaptationnetworkforbearingfaultdiagnosisunderdifferentworkingconditions