Multi-layer convolutional dictionary learning network for signal denoising and its application to explainable rolling bearing fault diagnosis

As a vital mechanical sub-component, the health monitoring of rolling bearings is important. Vibration signal analysis is a commonly used approach for fault diagnosis of bearings. Nevertheless, the collected vibration signals cannot avoid interference from noises which has a negative influence on fa...

Full description

Saved in:
Bibliographic Details
Published in:ISA transactions Vol. 147; pp. 55 - 70
Main Authors: Qin, Yi, Yang, Rui, He, Biao, Chen, Dingliang, Mao, Yongfang
Format: Journal Article
Language:English
Published: United States Elsevier Ltd 01.04.2024
Subjects:
ISSN:0019-0578, 1879-2022, 1879-2022
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract As a vital mechanical sub-component, the health monitoring of rolling bearings is important. Vibration signal analysis is a commonly used approach for fault diagnosis of bearings. Nevertheless, the collected vibration signals cannot avoid interference from noises which has a negative influence on fault diagnosis. Thus, denoising needs to be utilized as an essential step of vibration signal processing. Traditional denoising methods need expert knowledge to select hyperparameters. And data-driven methods based on deep learning lack interpretability and a clear justification for the design of architecture in a “black-box” deep neural network. An approach to systematically design neural networks is by unrolling algorithms, such as learned iterative soft-thresholding (LISTA). In this paper, the multi-layer convolutional LISTA (ML-CLISTA) algorithm is derived by embedding a designed multi-layer sparse coder to the convolutional extension of LISTA. Then the multi-layer convolutional dictionary learning (ML-CDL) network for mechanical vibration signal denoising is proposed by unrolling ML-CLISTA. By combining ML-CDL network with a classifier, the proposed denoising method is applied to the explainable rolling bearing fault diagnosis. The experiments on two bearing datasets show the superiority of the ML-CDL network over other typical denoising methods. •The multi-layer convolutional LISTA (ML-CLISTA) algorithm is derived.•The multi-layer convolutional dictionary learning network is proposed.•The proposed method is applied to the explainable rolling bearing fault diagnosis.
AbstractList As a vital mechanical sub-component, the health monitoring of rolling bearings is important. Vibration signal analysis is a commonly used approach for fault diagnosis of bearings. Nevertheless, the collected vibration signals cannot avoid interference from noises which has a negative influence on fault diagnosis. Thus, denoising needs to be utilized as an essential step of vibration signal processing. Traditional denoising methods need expert knowledge to select hyperparameters. And data-driven methods based on deep learning lack interpretability and a clear justification for the design of architecture in a "black-box" deep neural network. An approach to systematically design neural networks is by unrolling algorithms, such as learned iterative soft-thresholding (LISTA). In this paper, the multi-layer convolutional LISTA (ML-CLISTA) algorithm is derived by embedding a designed multi-layer sparse coder to the convolutional extension of LISTA. Then the multi-layer convolutional dictionary learning (ML-CDL) network for mechanical vibration signal denoising is proposed by unrolling ML-CLISTA. By combining ML-CDL network with a classifier, the proposed denoising method is applied to the explainable rolling bearing fault diagnosis. The experiments on two bearing datasets show the superiority of the ML-CDL network over other typical denoising methods.As a vital mechanical sub-component, the health monitoring of rolling bearings is important. Vibration signal analysis is a commonly used approach for fault diagnosis of bearings. Nevertheless, the collected vibration signals cannot avoid interference from noises which has a negative influence on fault diagnosis. Thus, denoising needs to be utilized as an essential step of vibration signal processing. Traditional denoising methods need expert knowledge to select hyperparameters. And data-driven methods based on deep learning lack interpretability and a clear justification for the design of architecture in a "black-box" deep neural network. An approach to systematically design neural networks is by unrolling algorithms, such as learned iterative soft-thresholding (LISTA). In this paper, the multi-layer convolutional LISTA (ML-CLISTA) algorithm is derived by embedding a designed multi-layer sparse coder to the convolutional extension of LISTA. Then the multi-layer convolutional dictionary learning (ML-CDL) network for mechanical vibration signal denoising is proposed by unrolling ML-CLISTA. By combining ML-CDL network with a classifier, the proposed denoising method is applied to the explainable rolling bearing fault diagnosis. The experiments on two bearing datasets show the superiority of the ML-CDL network over other typical denoising methods.
As a vital mechanical sub-component, the health monitoring of rolling bearings is important. Vibration signal analysis is a commonly used approach for fault diagnosis of bearings. Nevertheless, the collected vibration signals cannot avoid interference from noises which has a negative influence on fault diagnosis. Thus, denoising needs to be utilized as an essential step of vibration signal processing. Traditional denoising methods need expert knowledge to select hyperparameters. And data-driven methods based on deep learning lack interpretability and a clear justification for the design of architecture in a “black-box” deep neural network. An approach to systematically design neural networks is by unrolling algorithms, such as learned iterative soft-thresholding (LISTA). In this paper, the multi-layer convolutional LISTA (ML-CLISTA) algorithm is derived by embedding a designed multi-layer sparse coder to the convolutional extension of LISTA. Then the multi-layer convolutional dictionary learning (ML-CDL) network for mechanical vibration signal denoising is proposed by unrolling ML-CLISTA. By combining ML-CDL network with a classifier, the proposed denoising method is applied to the explainable rolling bearing fault diagnosis. The experiments on two bearing datasets show the superiority of the ML-CDL network over other typical denoising methods. •The multi-layer convolutional LISTA (ML-CLISTA) algorithm is derived.•The multi-layer convolutional dictionary learning network is proposed.•The proposed method is applied to the explainable rolling bearing fault diagnosis.
As a vital mechanical sub-component, the health monitoring of rolling bearings is important. Vibration signal analysis is a commonly used approach for fault diagnosis of bearings. Nevertheless, the collected vibration signals cannot avoid interference from noises which has a negative influence on fault diagnosis. Thus, denoising needs to be utilized as an essential step of vibration signal processing. Traditional denoising methods need expert knowledge to select hyperparameters. And data-driven methods based on deep learning lack interpretability and a clear justification for the design of architecture in a "black-box" deep neural network. An approach to systematically design neural networks is by unrolling algorithms, such as learned iterative soft-thresholding (LISTA). In this paper, the multi-layer convolutional LISTA (ML-CLISTA) algorithm is derived by embedding a designed multi-layer sparse coder to the convolutional extension of LISTA. Then the multi-layer convolutional dictionary learning (ML-CDL) network for mechanical vibration signal denoising is proposed by unrolling ML-CLISTA. By combining ML-CDL network with a classifier, the proposed denoising method is applied to the explainable rolling bearing fault diagnosis. The experiments on two bearing datasets show the superiority of the ML-CDL network over other typical denoising methods.
Author Yang, Rui
Qin, Yi
Chen, Dingliang
Mao, Yongfang
He, Biao
Author_xml – sequence: 1
  givenname: Yi
  surname: Qin
  fullname: Qin, Yi
  organization: State Key Laboratory of Mechanical Transmission for Advanced Equipment, Chongqing University, Chongqing 400044, China
– sequence: 2
  givenname: Rui
  surname: Yang
  fullname: Yang, Rui
  organization: State Key Laboratory of Mechanical Transmission for Advanced Equipment, Chongqing University, Chongqing 400044, China
– sequence: 3
  givenname: Biao
  surname: He
  fullname: He, Biao
  organization: State Key Laboratory of Mechanical Transmission for Advanced Equipment, Chongqing University, Chongqing 400044, China
– sequence: 4
  givenname: Dingliang
  orcidid: 0000-0001-7338-2407
  surname: Chen
  fullname: Chen, Dingliang
  organization: State Key Laboratory of Mechanical Transmission for Advanced Equipment, Chongqing University, Chongqing 400044, China
– sequence: 5
  givenname: Yongfang
  orcidid: 0000-0003-3567-1886
  surname: Mao
  fullname: Mao, Yongfang
  email: yfm@cqu.edu.cn
  organization: School of Automation, Chongqing University, Chongqing 400044, China
BackLink https://www.ncbi.nlm.nih.gov/pubmed/38309975$$D View this record in MEDLINE/PubMed
BookMark eNqFkc1u1DAUhS1URKeFN0DISzYJ_smPzQIJVUArFbGBteW5uRl58NjBTgp9CN4ZZ6bdsIDVtezvnCufc0HOQgxIyEvOas5492Zfu2znZGvBRFMzXjPRPyEbrnpdlStxRjaMcV2xtlfn5CLnPWNMtFo9I-dSSaZ1327I78-Ln13l7T0mCjHcRb_MLgbr6eDgeEr31KNNwYUdDTj_jOk7HWOi2e2OGIbo8vpow0DdnKmdJu_ArmI6R4q_Jm9dsFuPNEXvV3RbDNc52rK-bLK7ELPLz8nT0fqMLx7mJfn28cPXq-vq9sunm6v3txXITsyVBBybHgR0je2gG1sFnVSNbcTQq6FBUMPYbVXfguRSw4gMlVYMwWrJOs3lJXl98p1S_LFgns3BZUDvbcC4ZCO0KBTv5Yq-ekCX7QEHMyV3KJGYxwgL8PYEQIo5JxwNuPn4-VKO84Yzs_Zl9ubUl1n7Moyb0lcRN3-JH_3_I3t3kmEJ6c5hMhkcBsDBJYTZDNH92-APAVC1gA
CitedBy_id crossref_primary_10_1016_j_ymssp_2025_112370
crossref_primary_10_1063_5_0225222
crossref_primary_10_1177_14759217251364718
crossref_primary_10_1016_j_measurement_2025_118647
crossref_primary_10_1109_JIOT_2024_3520804
crossref_primary_10_1016_j_aei_2025_103434
crossref_primary_10_1016_j_ress_2025_111371
crossref_primary_10_1016_j_apacoust_2024_110301
crossref_primary_10_1063_5_0234838
crossref_primary_10_1109_TIM_2025_3527598
crossref_primary_10_12677_jisp_2024_132013
crossref_primary_10_1007_s11668_025_02225_4
crossref_primary_10_1088_2631_8695_adee7a
crossref_primary_10_1016_j_neucom_2025_129996
crossref_primary_10_1016_j_measurement_2024_116332
crossref_primary_10_1109_TIM_2025_3595254
crossref_primary_10_1007_s10921_025_01212_x
Cites_doi 10.1109/TIP.2018.2839891
10.1109/TPAMI.2019.2904255
10.3389/fenrg.2022.837823
10.1016/j.jvcir.2021.103095
10.1063/1.4887720
10.1109/PHM-Nanjing52125.2021.9612783
10.1109/ACCESS.2021.3086537
10.1177/1475921720970856
10.3390/math11194117
10.1016/j.jelekin.2023.102834
10.1109/ICSMD53520.2021.9670855
10.3390/app11041591
10.1109/TMM.2021.3094058
10.1016/j.ymssp.2022.110030
10.1109/TII.2019.2909305
10.1109/TIP.2017.2662206
10.3390/electronics12061461
10.1016/j.isatra.2022.05.005
10.1109/OJSP.2022.3172842
10.1007/s10845-021-01861-5
10.3390/s130608013
10.1016/j.isatra.2021.04.022
10.1109/ICASSP.2018.8462313
10.1109/CADIAG.2017.8075624
10.3390/make3040048
ContentType Journal Article
Copyright 2024 ISA
Copyright © 2024 ISA. Published by Elsevier Ltd. All rights reserved.
Copyright_xml – notice: 2024 ISA
– notice: Copyright © 2024 ISA. Published by Elsevier Ltd. All rights reserved.
DBID AAYXX
CITATION
NPM
7X8
DOI 10.1016/j.isatra.2024.01.027
DatabaseName CrossRef
PubMed
MEDLINE - Academic
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic

PubMed
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Sciences (General)
EISSN 1879-2022
EndPage 70
ExternalDocumentID 38309975
10_1016_j_isatra_2024_01_027
S0019057824000363
Genre Journal Article
GroupedDBID ---
--K
--M
-~X
.DC
.~1
0R~
1B1
1~.
1~5
29J
4.4
457
4G.
53G
5GY
5VS
6P2
7-5
71M
8P~
9JN
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
ABFNM
ABFRF
ABJNI
ABMAC
ABNEU
ABTAH
ABXDB
ABYKQ
ACDAQ
ACFVG
ACGFO
ACNNM
ACRLP
ADBBV
ADEZE
ADMUD
ADTZH
AEBSH
AECPX
AEFWE
AEKER
AENEX
AFDAS
AFFNX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AIEXJ
AIKHN
AITUG
AIVDX
AJBFU
AJOXV
AKRWK
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
GBLVA
HVGLF
HZ~
IHE
J1W
JJJVA
KOM
LY7
M41
MO0
N9A
O-L
O9-
OAUVE
OGIMB
OZT
P-8
P-9
P2P
PC.
Q38
R2-
ROL
RPZ
SDF
SDG
SES
SET
SEW
SPC
SPCBC
SPD
SSQ
SST
SSZ
T5K
T9H
TAE
TN5
UHS
UNMZH
WUQ
XPP
ZMT
ZY4
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKYEP
ANKPU
APXCP
CITATION
EFKBS
EFLBG
~HD
AFXIZ
AGCQF
AGRNS
BNPGV
NPM
SSH
7X8
ID FETCH-LOGICAL-c362t-3cef47c2c64a6c6f58c6384a42d78d4ec8df6b875c3139cfe0e8980eca9306913
ISICitedReferencesCount 15
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001235953600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0019-0578
1879-2022
IngestDate Sat Sep 27 20:58:08 EDT 2025
Mon Jul 21 05:57:01 EDT 2025
Tue Nov 18 21:05:40 EST 2025
Sat Nov 29 06:47:03 EST 2025
Sat Apr 20 15:59:35 EDT 2024
IsPeerReviewed true
IsScholarly true
Keywords Multi-layer sparse coding
Sparse representation
Unrolling
Signal denoising
Dictionary learning
Language English
License Copyright © 2024 ISA. Published by Elsevier Ltd. All rights reserved.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c362t-3cef47c2c64a6c6f58c6384a42d78d4ec8df6b875c3139cfe0e8980eca9306913
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0001-7338-2407
0000-0003-3567-1886
PMID 38309975
PQID 2929131731
PQPubID 23479
PageCount 16
ParticipantIDs proquest_miscellaneous_2929131731
pubmed_primary_38309975
crossref_citationtrail_10_1016_j_isatra_2024_01_027
crossref_primary_10_1016_j_isatra_2024_01_027
elsevier_sciencedirect_doi_10_1016_j_isatra_2024_01_027
PublicationCentury 2000
PublicationDate 2024-04-01
PublicationDateYYYYMMDD 2024-04-01
PublicationDate_xml – month: 04
  year: 2024
  text: 2024-04-01
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle ISA transactions
PublicationTitleAlternate ISA Trans
PublicationYear 2024
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Mohguen W, Bekka RE. EMD-based denoising by customized thresholding. In: Proceedings of the 2017 international conference on control, automation and diagnosis (ICCAD); 2017, 19–21 Jan. 2017. p. 019–23.
Jiang, Wang, Shen, Shi, Huang, Zhu, Wang (bib11) 2021; 20
Qin, Zou, Tang, Wang, Chen (bib23) 2020; 16
Sreter H, Giryes R, IEEE. Learned convolutional sparse coding [Proceedings Paper]. In: Proceedings of the 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP); 2018. p. 2191–5.
Liu, Shu, Chen (bib16) 2021; 11
Ai T, Liu Z, Wang H, Han H. Robust Vibration Signal Denoising and Diagnosis Using Encoder-Decoder Networks with Cross-layer Residual Connection. 2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing); 2021, 15–17 Oct. 2021. p. 1–5.
Wang, Su (bib31) 2022; 131
Koppolu, Chemmangat (bib13) 2023; 73
Ma, Peng, Tian, Jiang (bib18) 2022; 24
Zhang, Zuo, Chen, Meng, Zhang (bib32) 2017; 26
Nigam, Srivastava (bib20) 2023; 11
Singh, Gangsar, Porwal, Atulkar (bib26) 2023; 34
Gregor K, LeCun Y. Learning fast approximations of sparse coding. In: Proceedings of the 27th International Conference on International Conference on Machine Learning, Haifa, Israel; 2010. p. 399–406.
Janjušević, Khalilian-Gourtani, Wang (bib10) 2022; 3
Simon D, Elad M. Rethinking the CSC model for natural images. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems (pp. Article 204). Curran Associates Inc; 2019.
Buhrmester, Munch, Arens (bib2) 2021; 3
Han, Wang, Liu, Wang (bib5) 2022; 122
Zhang, Zuo, Zhang (bib33) 2018; 27
Zhou J, Wang S, Tong C, Zhao Z, Chen X. Weighted Basis Pursuit Denoising Algorithm and Its Application in Gear Fault Diagnosis. 2021 International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD); 2021, 21–23 Oct. 2021. p. 1–5.
Khatib, Simon, Elad (bib12) 2021; 77
Qin, Jin, Zhang, He (bib22) 2021; 70
Papyan, Romano, Elad (bib21) 2017; 18
Liu, Zhang (bib15) 2023; 12
M.Ali, Abdelhafeez (bib17) 2022; 1
.
Sulam, Aberdam, Beck, Elad (bib30) 2020; 42
He, Sun, Su, Chen, Zhao (bib7) 2022; 10
Su, Tan, Qi, Gu, Ji, Wang, Pecht (bib29) 2023; 188
He, Qin, Zhang (bib6) 2021; 70
Ismail MT, Mamat SS, Hamzah FM, Karim SAA. Forecasting Performance of Denoising Signal by Wavelet and Fourier Transforms using SARIMA Model. In: Proceedings of the 21st national symposium on mathematical sciences (SKSM21): germination of mathematical sciences education and research towards global sustainability; 2014. p. 961–6.
Li, Ping, Wang, Chen, Cao (bib14) 2013; 13
School of mechanical engineering. Jiangnan University.
Song, Baek, Kim (bib27) 2021; 9
Case western reserve university (CWRU) bearing data center.
Iunusova E, Gonzalez MK, Szipka K, Archenti A. Early fault diagnosis in rolling element bearings: comparative analysis of a knowledge-based and a data-driven approach. J Intell Manuf; 2021. p. 1–21.
10.1016/j.isatra.2024.01.027_bib8
10.1016/j.isatra.2024.01.027_bib9
Li (10.1016/j.isatra.2024.01.027_bib14) 2013; 13
Wang (10.1016/j.isatra.2024.01.027_bib31) 2022; 131
M.Ali (10.1016/j.isatra.2024.01.027_bib17) 2022; 1
Khatib (10.1016/j.isatra.2024.01.027_bib12) 2021; 77
10.1016/j.isatra.2024.01.027_bib1
Koppolu (10.1016/j.isatra.2024.01.027_bib13) 2023; 73
Su (10.1016/j.isatra.2024.01.027_bib29) 2023; 188
10.1016/j.isatra.2024.01.027_bib3
10.1016/j.isatra.2024.01.027_bib4
Nigam (10.1016/j.isatra.2024.01.027_bib20) 2023; 11
10.1016/j.isatra.2024.01.027_bib19
Janjušević (10.1016/j.isatra.2024.01.027_bib10) 2022; 3
Qin (10.1016/j.isatra.2024.01.027_bib22) 2021; 70
10.1016/j.isatra.2024.01.027_bib34
He (10.1016/j.isatra.2024.01.027_bib7) 2022; 10
He (10.1016/j.isatra.2024.01.027_bib6) 2021; 70
Papyan (10.1016/j.isatra.2024.01.027_bib21) 2017; 18
Qin (10.1016/j.isatra.2024.01.027_bib23) 2020; 16
Buhrmester (10.1016/j.isatra.2024.01.027_bib2) 2021; 3
Liu (10.1016/j.isatra.2024.01.027_bib15) 2023; 12
Song (10.1016/j.isatra.2024.01.027_bib27) 2021; 9
Sulam (10.1016/j.isatra.2024.01.027_bib30) 2020; 42
Ma (10.1016/j.isatra.2024.01.027_bib18) 2022; 24
Singh (10.1016/j.isatra.2024.01.027_bib26) 2023; 34
Jiang (10.1016/j.isatra.2024.01.027_bib11) 2021; 20
Zhang (10.1016/j.isatra.2024.01.027_bib33) 2018; 27
Liu (10.1016/j.isatra.2024.01.027_bib16) 2021; 11
Han (10.1016/j.isatra.2024.01.027_bib5) 2022; 122
Zhang (10.1016/j.isatra.2024.01.027_bib32) 2017; 26
10.1016/j.isatra.2024.01.027_bib24
10.1016/j.isatra.2024.01.027_bib25
10.1016/j.isatra.2024.01.027_bib28
References_xml – volume: 70
  start-page: 1
  year: 2021
  end-page: 9
  ident: bib6
  article-title: Rolling bearing fault diagnosis by using a new index: the compound weighted characteristic energy ratio
  publication-title: IEEE Trans Instrum Meas
– volume: 13
  start-page: 8013
  year: 2013
  end-page: 8041
  ident: bib14
  article-title: Sequential fuzzy diagnosis method for motor roller bearing in variable operating conditions based on vibration analysis
  publication-title: SENSORS
– reference: Zhou J, Wang S, Tong C, Zhao Z, Chen X. Weighted Basis Pursuit Denoising Algorithm and Its Application in Gear Fault Diagnosis. 2021 International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD); 2021, 21–23 Oct. 2021. p. 1–5.
– volume: 20
  start-page: 2708
  year: 2021
  end-page: 2725
  ident: bib11
  article-title: An adaptive and efficient variational mode decomposition and its application for bearing fault diagnosis
  publication-title: Struct Health Monit
– volume: 3
  start-page: 966
  year: 2021
  end-page: 989
  ident: bib2
  article-title: Analysis of explainers of black box deep neural networks for computer vision: a survey
  publication-title: Mach Learn Knowl Extraction
– volume: 11
  start-page: 1591
  year: 2021
  ident: bib16
  article-title: ECG signal denoising and reconstruction based on basis pursuit
  publication-title: Appl Sci
– reference: Sreter H, Giryes R, IEEE. Learned convolutional sparse coding [Proceedings Paper]. In: Proceedings of the 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP); 2018. p. 2191–5.
– volume: 26
  start-page: 3142
  year: 2017
  end-page: 3155
  ident: bib32
  article-title: Beyond a Gaussian Denoiser: residual learning of deep CNN for image denoising
  publication-title: IEEE Trans Image Process
– reference: Simon D, Elad M. Rethinking the CSC model for natural images. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems (pp. Article 204). Curran Associates Inc; 2019.
– reference: Gregor K, LeCun Y. Learning fast approximations of sparse coding. In: Proceedings of the 27th International Conference on International Conference on Machine Learning, Haifa, Israel; 2010. p. 399–406.
– volume: 70
  start-page: 1
  year: 2021
  end-page: 12
  ident: bib22
  article-title: Rolling bearing fault diagnosis with adaptive harmonic kurtosis and improved bat algorithm
  publication-title: IEEE Trans Instrum Meas
– volume: 27
  start-page: 4608
  year: 2018
  end-page: 4622
  ident: bib33
  article-title: FFDNet: toward a fast and flexible solution for CNN-based image denoising
  publication-title: IEEE Trans Image Process
– volume: 12
  start-page: 1461
  year: 2023
  ident: bib15
  article-title: A novel denoising algorithm based on wavelet and non-local moment mean filtering
  publication-title: Electronics
– volume: 122
  start-page: 13
  year: 2022
  end-page: 23
  ident: bib5
  article-title: Intelligent vibration signal denoising method based on non-local fully convolutional neural network for rolling bearings
  publication-title: ISA Trans
– volume: 131
  start-page: 650
  year: 2022
  end-page: 661
  ident: bib31
  article-title: An optimization method for motion blur image restoration and ringing suppression via texture mapping
  publication-title: ISA Trans
– volume: 1
  start-page: 8463
  year: 2022
  ident: bib17
  article-title: DeepHAR-Net: a novel machine intelligence approach for human activity recognition from inertial sensors
  publication-title: Sustain Mach Intell J
– reference: Case western reserve university (CWRU) bearing data center.
– volume: 42
  start-page: 1968
  year: 2020
  end-page: 1980
  ident: bib30
  article-title: On multi-layer basis pursuit, efficient algorithms and convolutional neural networks [Article]
  publication-title: IEEE Trans Pattern Anal Mach Intell
– reference: Iunusova E, Gonzalez MK, Szipka K, Archenti A. Early fault diagnosis in rolling element bearings: comparative analysis of a knowledge-based and a data-driven approach. J Intell Manuf; 2021. p. 1–21.
– volume: 9
  start-page: 83786
  year: 2021
  end-page: 83796
  ident: bib27
  article-title: Forecasting stock market indices using padding-based fourier transform denoising and time series deep learning models
  publication-title: IEEE Access
– reference: Ai T, Liu Z, Wang H, Han H. Robust Vibration Signal Denoising and Diagnosis Using Encoder-Decoder Networks with Cross-layer Residual Connection. 2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing); 2021, 15–17 Oct. 2021. p. 1–5.
– volume: 73
  year: 2023
  ident: bib13
  article-title: Automatic selection of IMFs to denoise the sEMG signals using EMD
  publication-title: J Electromyogr Kinesiol
– volume: 34
  start-page: 931
  year: 2023
  end-page: 960
  ident: bib26
  article-title: Artificial intelligence application in fault diagnostics of rotating industrial machines: a state-of-the-art review
  publication-title: J Intell Manuf
– volume: 188
  year: 2023
  ident: bib29
  article-title: An improved orthogonal matching pursuit method for denoising high-frequency ultrasonic detection signals of flip chips
  publication-title: Mech Syst Signal Process
– reference: School of mechanical engineering. Jiangnan University.
– reference: .
– volume: 3
  start-page: 196
  year: 2022
  end-page: 211
  ident: bib10
  article-title: CDLNet: noise-adaptive convolutional dictionary learning network for blind denoising and demosaicing
  publication-title: IEEE Open J Sign Proc
– volume: 10
  year: 2022
  ident: bib7
  article-title: Denoising method of nuclear signal based on sparse representation
  publication-title: Front Energy Res
– volume: 16
  start-page: 215
  year: 2020
  end-page: 227
  ident: bib23
  article-title: Transient feature extraction by the improved orthogonal matching pursuit and K-SVD algorithm with adaptive transient dictionary
  publication-title: IEEE Trans Ind Inform
– volume: 11
  start-page: 4117
  year: 2023
  ident: bib20
  article-title: Filtering of audio signals using discrete wavelet transforms
  publication-title: Mathematics
– reference: Ismail MT, Mamat SS, Hamzah FM, Karim SAA. Forecasting Performance of Denoising Signal by Wavelet and Fourier Transforms using SARIMA Model. In: Proceedings of the 21st national symposium on mathematical sciences (SKSM21): germination of mathematical sciences education and research towards global sustainability; 2014. p. 961–6.
– volume: 77
  year: 2021
  ident: bib12
  article-title: Learned Greedy Method (LGM): A novel neural architecture for sparse coding and beyond
  publication-title: J Vis Commun Image Represent
– reference: Mohguen W, Bekka RE. EMD-based denoising by customized thresholding. In: Proceedings of the 2017 international conference on control, automation and diagnosis (ICCAD); 2017, 19–21 Jan. 2017. p. 019–23.
– volume: 24
  start-page: 3157
  year: 2022
  end-page: 3168
  ident: bib18
  article-title: DBDnet: a deep boosting strategy for image denoising
  publication-title: IEEE Trans Multimed
– volume: 18
  start-page: 1
  year: 2017
  end-page: 52
  ident: bib21
  article-title: Convolutional neural networks analyzed via convolutional sparse coding [Article]
  publication-title: J Mach Learn Res
– volume: 27
  start-page: 4608
  issue: 9
  year: 2018
  ident: 10.1016/j.isatra.2024.01.027_bib33
  article-title: FFDNet: toward a fast and flexible solution for CNN-based image denoising
  publication-title: IEEE Trans Image Process
  doi: 10.1109/TIP.2018.2839891
– volume: 42
  start-page: 1968
  issue: 8
  year: 2020
  ident: 10.1016/j.isatra.2024.01.027_bib30
  article-title: On multi-layer basis pursuit, efficient algorithms and convolutional neural networks [Article]
  publication-title: IEEE Trans Pattern Anal Mach Intell
  doi: 10.1109/TPAMI.2019.2904255
– ident: 10.1016/j.isatra.2024.01.027_bib25
– volume: 10
  year: 2022
  ident: 10.1016/j.isatra.2024.01.027_bib7
  article-title: Denoising method of nuclear signal based on sparse representation
  publication-title: Front Energy Res
  doi: 10.3389/fenrg.2022.837823
– volume: 77
  year: 2021
  ident: 10.1016/j.isatra.2024.01.027_bib12
  article-title: Learned Greedy Method (LGM): A novel neural architecture for sparse coding and beyond
  publication-title: J Vis Commun Image Represent
  doi: 10.1016/j.jvcir.2021.103095
– ident: 10.1016/j.isatra.2024.01.027_bib8
  doi: 10.1063/1.4887720
– ident: 10.1016/j.isatra.2024.01.027_bib1
  doi: 10.1109/PHM-Nanjing52125.2021.9612783
– volume: 9
  start-page: 83786
  year: 2021
  ident: 10.1016/j.isatra.2024.01.027_bib27
  article-title: Forecasting stock market indices using padding-based fourier transform denoising and time series deep learning models
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2021.3086537
– volume: 20
  start-page: 2708
  issue: 5
  year: 2021
  ident: 10.1016/j.isatra.2024.01.027_bib11
  article-title: An adaptive and efficient variational mode decomposition and its application for bearing fault diagnosis
  publication-title: Struct Health Monit
  doi: 10.1177/1475921720970856
– volume: 11
  start-page: 4117
  issue: 19
  year: 2023
  ident: 10.1016/j.isatra.2024.01.027_bib20
  article-title: Filtering of audio signals using discrete wavelet transforms
  publication-title: Mathematics
  doi: 10.3390/math11194117
– volume: 73
  year: 2023
  ident: 10.1016/j.isatra.2024.01.027_bib13
  article-title: Automatic selection of IMFs to denoise the sEMG signals using EMD
  publication-title: J Electromyogr Kinesiol
  doi: 10.1016/j.jelekin.2023.102834
– ident: 10.1016/j.isatra.2024.01.027_bib34
  doi: 10.1109/ICSMD53520.2021.9670855
– ident: 10.1016/j.isatra.2024.01.027_bib4
– volume: 1
  start-page: 8463
  year: 2022
  ident: 10.1016/j.isatra.2024.01.027_bib17
  article-title: DeepHAR-Net: a novel machine intelligence approach for human activity recognition from inertial sensors
  publication-title: Sustain Mach Intell J
– volume: 11
  start-page: 1591
  issue: 4
  year: 2021
  ident: 10.1016/j.isatra.2024.01.027_bib16
  article-title: ECG signal denoising and reconstruction based on basis pursuit
  publication-title: Appl Sci
  doi: 10.3390/app11041591
– volume: 24
  start-page: 3157
  year: 2022
  ident: 10.1016/j.isatra.2024.01.027_bib18
  article-title: DBDnet: a deep boosting strategy for image denoising
  publication-title: IEEE Trans Multimed
  doi: 10.1109/TMM.2021.3094058
– volume: 188
  year: 2023
  ident: 10.1016/j.isatra.2024.01.027_bib29
  article-title: An improved orthogonal matching pursuit method for denoising high-frequency ultrasonic detection signals of flip chips
  publication-title: Mech Syst Signal Process
  doi: 10.1016/j.ymssp.2022.110030
– ident: 10.1016/j.isatra.2024.01.027_bib24
– volume: 16
  start-page: 215
  issue: 1
  year: 2020
  ident: 10.1016/j.isatra.2024.01.027_bib23
  article-title: Transient feature extraction by the improved orthogonal matching pursuit and K-SVD algorithm with adaptive transient dictionary
  publication-title: IEEE Trans Ind Inform
  doi: 10.1109/TII.2019.2909305
– volume: 26
  start-page: 3142
  issue: 7
  year: 2017
  ident: 10.1016/j.isatra.2024.01.027_bib32
  article-title: Beyond a Gaussian Denoiser: residual learning of deep CNN for image denoising
  publication-title: IEEE Trans Image Process
  doi: 10.1109/TIP.2017.2662206
– volume: 70
  start-page: 1
  year: 2021
  ident: 10.1016/j.isatra.2024.01.027_bib6
  article-title: Rolling bearing fault diagnosis by using a new index: the compound weighted characteristic energy ratio
  publication-title: IEEE Trans Instrum Meas
– volume: 12
  start-page: 1461
  issue: 6
  year: 2023
  ident: 10.1016/j.isatra.2024.01.027_bib15
  article-title: A novel denoising algorithm based on wavelet and non-local moment mean filtering
  publication-title: Electronics
  doi: 10.3390/electronics12061461
– volume: 131
  start-page: 650
  year: 2022
  ident: 10.1016/j.isatra.2024.01.027_bib31
  article-title: An optimization method for motion blur image restoration and ringing suppression via texture mapping
  publication-title: ISA Trans
  doi: 10.1016/j.isatra.2022.05.005
– volume: 3
  start-page: 196
  year: 2022
  ident: 10.1016/j.isatra.2024.01.027_bib10
  article-title: CDLNet: noise-adaptive convolutional dictionary learning network for blind denoising and demosaicing
  publication-title: IEEE Open J Sign Proc
  doi: 10.1109/OJSP.2022.3172842
– volume: 34
  start-page: 931
  issue: 3
  year: 2023
  ident: 10.1016/j.isatra.2024.01.027_bib26
  article-title: Artificial intelligence application in fault diagnostics of rotating industrial machines: a state-of-the-art review
  publication-title: J Intell Manuf
  doi: 10.1007/s10845-021-01861-5
– volume: 13
  start-page: 8013
  issue: 6
  year: 2013
  ident: 10.1016/j.isatra.2024.01.027_bib14
  article-title: Sequential fuzzy diagnosis method for motor roller bearing in variable operating conditions based on vibration analysis
  publication-title: SENSORS
  doi: 10.3390/s130608013
– volume: 122
  start-page: 13
  year: 2022
  ident: 10.1016/j.isatra.2024.01.027_bib5
  article-title: Intelligent vibration signal denoising method based on non-local fully convolutional neural network for rolling bearings
  publication-title: ISA Trans
  doi: 10.1016/j.isatra.2021.04.022
– volume: 18
  start-page: 1
  year: 2017
  ident: 10.1016/j.isatra.2024.01.027_bib21
  article-title: Convolutional neural networks analyzed via convolutional sparse coding [Article]
  publication-title: J Mach Learn Res
– ident: 10.1016/j.isatra.2024.01.027_bib28
  doi: 10.1109/ICASSP.2018.8462313
– volume: 70
  start-page: 1
  year: 2021
  ident: 10.1016/j.isatra.2024.01.027_bib22
  article-title: Rolling bearing fault diagnosis with adaptive harmonic kurtosis and improved bat algorithm
  publication-title: IEEE Trans Instrum Meas
– ident: 10.1016/j.isatra.2024.01.027_bib19
  doi: 10.1109/CADIAG.2017.8075624
– ident: 10.1016/j.isatra.2024.01.027_bib3
– ident: 10.1016/j.isatra.2024.01.027_bib9
– volume: 3
  start-page: 966
  issue: 4
  year: 2021
  ident: 10.1016/j.isatra.2024.01.027_bib2
  article-title: Analysis of explainers of black box deep neural networks for computer vision: a survey
  publication-title: Mach Learn Knowl Extraction
  doi: 10.3390/make3040048
SSID ssj0002598
Score 2.4373548
Snippet As a vital mechanical sub-component, the health monitoring of rolling bearings is important. Vibration signal analysis is a commonly used approach for fault...
SourceID proquest
pubmed
crossref
elsevier
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 55
SubjectTerms Dictionary learning
Multi-layer sparse coding
Signal denoising
Sparse representation
Unrolling
Title Multi-layer convolutional dictionary learning network for signal denoising and its application to explainable rolling bearing fault diagnosis
URI https://dx.doi.org/10.1016/j.isatra.2024.01.027
https://www.ncbi.nlm.nih.gov/pubmed/38309975
https://www.proquest.com/docview/2929131731
Volume 147
WOSCitedRecordID wos001235953600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1879-2022
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002598
  issn: 0019-0578
  databaseCode: AIEXJ
  dateStart: 19950301
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9NAEF6lKQc4IFqghEe1SBzgYOS318eAiloOFdAihZO1Xq8lV5YdxUmVP9H_0Z_JzD5sV1VVQOISRY7tXWm-zGu_mSHkXSxSxnOIVHPphU5Y5NxJY46chpJL-EEkQaGGTSSnp2yxSL9NJte2FuayTpqGbbfp8r-KGq6BsLF09i_E3b8ULsB3EDp8gtjh848Er0pqnZqDL6045WYxdRijihiQJ1fbjEijaeCKbYhcDrxNNm3V2eJFPFgYnXKjryq3y9oWXa1MU-8cXqhImRyWx4wuEviqbuz7npzNcSKFHU_eO_PfdRuDX1WvgUwO-8emv3Ss8q6fKt4OfASjMCssRObGAJv8hT-mvaikmi2sGVhMSlFjbVWkp_t8lFo3syQFSfs3lbfu12nUr-74awy5Hkhyy0TobMWFYkutsPOUH-rGrclgEnui4hluBPeBVFs8894hu34SpWxKducnR4uvvdWHMNJYfb1xW6apuIS317rLDborzFHuzvkT8tjEKXSu8bVHJrLZJ49G3Sv3yZ6xCx19b5qXf3hKrkbwozfgRwf4UQs_auBHAX5Uw4_28KMAPwrwoyP40XVLR_CjBn7UwI8q-NEefs_Izy9H55-PHTPywxHgSa2dQMgyTIQv4pDHIi4jJsBAhDz0i4QVoRSsKOMcYmwRQOgiSulKljJXCp5C7Jt6wXMybdpGviDU94VbcFfmMYTMTMrUlZEbxgWootzluZiRwEogE6YfPo5lqTNLfLzItNwylFvmehnIbUac_qml7gdzz_2JFW5mfFrtq2aAx3uefGuxkIHKx3M83sh202U-hDQe-P2BNyMHGiT9XgIWYC189PKf131FHg5_09dkul5t5BvyQFyuq251SHaSBTs04P8NrDXlhA
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Multi-layer+convolutional+dictionary+learning+network+for+signal+denoising+and+its+application+to+explainable+rolling+bearing+fault+diagnosis&rft.jtitle=ISA+transactions&rft.au=Qin%2C+Yi&rft.au=Yang%2C+Rui&rft.au=He%2C+Biao&rft.au=Chen%2C+Dingliang&rft.date=2024-04-01&rft.pub=Elsevier+Ltd&rft.issn=0019-0578&rft.eissn=1879-2022&rft.volume=147&rft.spage=55&rft.epage=70&rft_id=info:doi/10.1016%2Fj.isatra.2024.01.027&rft.externalDocID=S0019057824000363
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0019-0578&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0019-0578&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0019-0578&client=summon