A new automatic convolutional neural network based on deep reinforcement learning for fault diagnosis

Convolutional neural network (CNN) has achieved remarkable applications in fault diagnosis. However, the tuning aiming at obtaining the well-trained CNN model is mainly manual search. Tuning requires considerable experiences on the knowledge on CNN training and fault diagnosis, and is always time co...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers of Mechanical Engineering Vol. 17; no. 2; p. 17
Main Authors: WEN, Long, WANG, You, LI, Xinyu
Format: Journal Article
Language:English
Published: Beijing Higher Education Press 01.06.2022
Subjects:
ISSN:2095-0233, 2095-0241
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Convolutional neural network (CNN) has achieved remarkable applications in fault diagnosis. However, the tuning aiming at obtaining the well-trained CNN model is mainly manual search. Tuning requires considerable experiences on the knowledge on CNN training and fault diagnosis, and is always time consuming and labor intensive, making the automatic hyper parameter optimization (HPO) of CNN models essential. To solve this problem, this paper proposes a novel automatic CNN (ACNN) for fault diagnosis, which can automatically tune its three key hyper parameters, namely, learning rate, batch size, and L2-regulation. First, a new deep reinforcement learning (DRL) is developed, and it constructs an agent aiming at controlling these three hyper parameters along with the training of CNN models online. Second, a new structure of DRL is designed by combining deep deterministic policy gradient and long short-term memory, which takes the training loss of CNN models as its input and can output the adjustment on these three hyper parameters. Third, a new training method for ACNN is designed to enhance its stability. Two famous bearing datasets are selected to evaluate the performance of ACNN. It is compared with four commonly used HPO methods, namely, random search, Bayesian optimization, tree Parzen estimator, and sequential model-based algorithm configuration. ACNN is also compared with other published machine learning (ML) and deep learning (DL) methods. The results show that ACNN outperforms these HPO and ML/DL methods, validating its potential in fault diagnosis.
AbstractList Convolutional neural network (CNN) has achieved remarkable applications in fault diagnosis. However, the tuning aiming at obtaining the well-trained CNN model is mainly manual search. Tuning requires considerable experiences on the knowledge on CNN training and fault diagnosis, and is always time consuming and labor intensive, making the automatic hyper parameter optimization (HPO) of CNN models essential. To solve this problem, this paper proposes a novel automatic CNN (ACNN) for fault diagnosis, which can automatically tune its three key hyper parameters, namely, learning rate, batch size, and L2-regulation. First, a new deep reinforcement learning (DRL) is developed, and it constructs an agent aiming at controlling these three hyper parameters along with the training of CNN models online. Second, a new structure of DRL is designed by combining deep deterministic policy gradient and long short-term memory, which takes the training loss of CNN models as its input and can output the adjustment on these three hyper parameters. Third, a new training method for ACNN is designed to enhance its stability. Two famous bearing datasets are selected to evaluate the performance of ACNN. It is compared with four commonly used HPO methods, namely, random search, Bayesian optimization, tree Parzen estimator, and sequential model-based algorithm configuration. ACNN is also compared with other published machine learning (ML) and deep learning (DL) methods. The results show that ACNN outperforms these HPO and ML/DL methods, validating its potential in fault diagnosis.
ArticleNumber 17
Author WANG, You
WEN, Long
LI, Xinyu
Author_xml – sequence: 1
  givenname: Long
  surname: WEN
  fullname: WEN, Long
  organization: School of Mechanical Engineering and Electronic Information, China University of Geosciences, Wuhan 430074, China
– sequence: 2
  givenname: You
  surname: WANG
  fullname: WANG, You
  organization: School of Mechanical Engineering and Electronic Information, China University of Geosciences, Wuhan 430074, China
– sequence: 3
  givenname: Xinyu
  surname: LI
  fullname: LI, Xinyu
  email: Xinyu LI
  organization: State Key Laboratory of Digital Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan 430074, China
BookMark eNp9kLlOAzEQQC0EEgHyAXT-gQVfe6REiEuKRAO1NbHHicPGjmwvEX_PhiAKilQzmtGb412Q0xADEnLN2Q1nrL3NnKumrpgQFWtaWbUnZCLYbF9R_PQvl_KcTHNeM8YEE3Ut5ITgHQ24ozCUuIHiDTUxfMZ-KD4G6MfekH5C2cX0QReQ0dIYqEXc0oQ-uJgMbjAU2iOk4MOSjiXqYOgLtR6WIWafr8iZgz7j9DdekvfHh7f752r--vRyfzevjJRtqaydmVoJ1YBYADgDHVegOtvAzHQtV-PVrhGyEU452drOOcuNsTMJSjhRS3lJ-GGuSTHnhE5vk99A-tKc6b0qfVClR1V6r0q3I9P-Y4wvsP-_JPD9UVIcyDxuCUtMeh2HNGrLR6HuAK38coUJ7TZhztqlcZ_HdAz9Bvw2k6o
CitedBy_id crossref_primary_10_1088_1361_6501_ad356e
crossref_primary_10_1016_j_rcim_2022_102441
crossref_primary_10_1007_s11804_025_00652_1
crossref_primary_10_3390_ma18133001
crossref_primary_10_1016_j_eswa_2024_125594
crossref_primary_10_1177_09544089251324568
crossref_primary_10_1016_j_measurement_2024_114171
Cites_doi 10.1109/TIE.2018.2844805
10.1109/4235.585893
10.3390/s20144017
10.3390/s17020425
10.1007/978-1-4471-0123-9_3
10.1016/j.ymssp.2021.107773
10.1007/s42835-020-00343-7
10.1016/j.measurement.2020.108122
10.1109/TII.2019.2950667
10.1016/j.ymssp.2020.106683
10.1109/TSM.2020.3020985
10.1016/j.measurement.2019.107417
10.1109/TIM.2019.2902003
10.1109/TCYB.2019.2939174
10.1007/s11465-018-0472-3
10.1016/j.engappai.2020.103966
10.3390/s20041233
10.1016/j.neucom.2018.09.050
10.1016/j.neucom.2019.11.006
10.1109/TII.2020.3044106
10.1109/TII.2019.2938884
10.1007/978-3-030-05318-5
10.1109/ACCESS.2019.2936625
10.1109/TIE.2020.3044808
10.1007/s11465-017-0443-0
10.1007/s10462-020-09910-w
10.1177/0020294020932347
10.1016/j.cogsys.2018.03.002
10.1109/TIM.2019.2896370
10.3390/app10103659
10.1016/j.ymssp.2019.106587
10.1007/s11465-021-0629-3
10.1016/j.neucom.2020.07.088
ContentType Journal Article
Copyright Copyright reserved, 2022, Higher Education Press 2022
Higher Education Press 2022
Copyright_xml – notice: Copyright reserved, 2022, Higher Education Press 2022
– notice: Higher Education Press 2022
DBID AAYXX
CITATION
DOI 10.1007/s11465-022-0673-7
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList

DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2095-0241
ExternalDocumentID 10_1007_s11465_022_0673_7
10.1007/s11465-022-0673-7
GroupedDBID 06D
0VY
1-T
29
2J2
2JN
2JY
2KG
2KM
2LR
2~H
30V
4.4
406
40E
5VS
8UJ
95-
95.
96X
A9
AABHQ
AAEIZ
AAFGU
AAIAL
AAJKR
AANZL
AAPBV
AARHV
AARTL
AATLR
AATVU
AAUYE
AAWCG
AAYIU
AAYQN
AAYTO
ABBBX
ABDZT
ABECU
ABFGW
ABFTD
ABFTV
ABHQN
ABJOX
ABKAS
ABKCH
ABKTR
ABMQK
ABNWP
ABQBU
ABSXP
ABTEG
ABTHY
ABTMW
ABXPI
ACBMV
ACBRV
ACBXY
ACGFS
ACHSB
ACHXU
ACIPQ
ACKNC
ACMLO
ACOKC
ACOMO
ACSNA
ACTTH
ACVWB
ACWMK
ADHIR
ADINQ
ADKNI
ADKPE
ADMDM
ADRFC
ADTIX
ADURQ
ADYFF
ADZKW
AEBTG
AEFTE
AEGNC
AEJHL
AEJRE
AEKMD
AEOHA
AEPYU
AESTI
AETLH
AEVTX
AEXYK
AFLOW
AFQWF
AFWTZ
AFZKB
AGAYW
AGDGC
AGGBP
AGJBK
AGQMX
AGWIL
AGWZB
AGYKE
AHAVH
AHBYD
AHKAY
AHSBF
AHYZX
AIAKS
AIIXL
AILAN
AIMYW
AITGF
AJBLW
AJDOV
AJRNO
AJZVZ
ALMA_UNASSIGNED_HOLDINGS
ALWAN
AMKLP
ARMRJ
ASPBG
AVWKF
AXYYD
AZFZN
B-.
BDATZ
BGNMA
C
CSCUP
DNIVK
EBLON
EBS
EIOEI
EJD
EM
ESBYG
FEDTE
FERAY
FFXSO
FIGPU
FINBP
FNLPD
FRRFC
FSGXE
FWDCC
GGCAI
GGRSB
GJIRD
GNWQR
GQ6
GQ7
HF
HG6
HMJXF
HRMNR
HVGLF
IJ-
IPNFZ
IXD
I~Z
J-C
JBSCW
JZLTJ
KOV
M4Y
MA-
N2Q
NQJWS
NU0
O9J
P4S
P9P
PF0
PT4
R89
RIG
ROL
RSV
S16
S3B
SAP
SCL
SEG
SHX
SISQX
SJYHP
SNE
SNX
SOJ
SPISZ
SRMVM
SSLCW
STPWE
SZN
TSG
TUC
U2A
UG4
UNUBA
UOJIU
UTJUX
UZXMN
VC2
VFIZW
VR
W23
W48
WK8
YLTOR
Z7R
Z7S
Z7X
Z7Y
Z7Z
ZMTXR
-EM
.VR
0R~
29~
AACDK
AAJBT
AASML
AATNV
AAYZH
ABAKF
ABJNI
ABQSL
ABTKH
ABWNU
ACAOD
ACDTI
ACMDZ
ACPIV
ACZOJ
ADTPH
AEFQL
AEMSY
AESKC
AEVLU
AFBBN
AGMZJ
AGQEE
AGRTI
AIGIU
AMXSW
AMYLF
AOCGG
BSONS
DDRTE
DPUIP
HF~
IKXTQ
IWAJR
LLZTM
NPVJJ
SNPRN
SOHCF
~A9
AAPKM
AAYXX
ABBRH
ABDBE
ABFSG
ABRTQ
ACSTC
ADHKG
AEZWR
AFDZB
AFHIU
AFOHR
AGQPQ
AHPBZ
AHWEU
AIXLP
ATHPR
AYFIA
CITATION
Q--
ID FETCH-LOGICAL-c337t-dd9c54246a2baafca814a48d6a9c8714202f62362f4f37d8ffd1ccd93a42f2533
IEDL.DBID RSV
ISICitedReferencesCount 7
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000819778900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2095-0233
IngestDate Sat Nov 29 06:19:53 EST 2025
Tue Nov 18 22:01:09 EST 2025
Fri Feb 21 02:46:01 EST 2025
Thu Aug 18 16:19:23 EDT 2022
IsPeerReviewed true
IsScholarly true
Issue 2
Keywords fault diagnosis
deep reinforcement learning
hyper parameter optimization
convolutional neural network
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c337t-dd9c54246a2baafca814a48d6a9c8714202f62362f4f37d8ffd1ccd93a42f2533
Notes Document accepted on :2022-01-10
fault diagnosis
Document received on :2021-09-03
deep reinforcement learning
hyper parameter optimization
convolutional neural network
ParticipantIDs crossref_primary_10_1007_s11465_022_0673_7
crossref_citationtrail_10_1007_s11465_022_0673_7
springer_journals_10_1007_s11465_022_0673_7
higheredpress_frontiers_10_1007_s11465_022_0673_7
PublicationCentury 2000
PublicationDate 2022-06-01
PublicationDateYYYYMMDD 2022-06-01
PublicationDate_xml – month: 06
  year: 2022
  text: 2022-06-01
  day: 01
PublicationDecade 2020
PublicationPlace Beijing
PublicationPlace_xml – name: Beijing
PublicationTitle Frontiers of Mechanical Engineering
PublicationTitleAbbrev Front. Mech. Eng
PublicationYear 2022
Publisher Higher Education Press
Publisher_xml – name: Higher Education Press
References Li, Jamieson, DeSalvo, Rostamizadeh, Talwalkar (CR27) 2018; 18
Wolpert, Macready (CR7) 1997; 1
Xu, Liu, Jiang, Shen, Huang (CR17) 2020; 69
Wei, Huang, Yao, Hu, Fan, Huang (CR31) 2020; 96
Wang, Xu, Dai, Zhang, Zhong (CR5) 2021; 17
CR14
Zhang, Peng, Li, Chen, Zhang (CR37) 2017; 17
Wolpert, Roy, Köppen, Ovaska, Furuhashi, Hoffmann (CR8) 2002
CR13
CR12
Chen, Huang, Zhao, Wang, Liu, Li (CR19) 2021; 70
Li, Wang, Song, Wang, Cui, Lin (CR22) 2020; 165
Hutter, Kotthoff, Vanschoren (CR9) 2019
CR32
Kolar, Lisjak, Pająk, Pavković (CR23) 2020; 20
Wang, Xu, Yang, Zhang, Li (CR16) 2020; 33
Jiao, Zhao, Lin, Liang (CR20) 2020; 417
Wang, Ning, Feng (CR35) 2020; 10
Qiao, Wang, Wang, Zhang, Xu (CR40) 2019; 7
Wen, Li, Gao (CR36) 2020; 69
Li, Zhang, Qin, Sun (CR28) 2020; 234
Wen, Ye, Gao (CR11) 2020; 53
Li, Zheng, Wang, Cao, Guo, Fu (CR18) 2021; 70
Zhang, Chen, Chen, Li (CR33) 2021; 51
Cabrera, Guamán, Zhang, Cerrada, Sánchez, Cevallos, Long, Li (CR26) 2020; 380
Hoang, Kang (CR38) 2019; 53
Chen, Mauricio, Li, Gryllias (CR6) 2020; 140
Wang, Jiang, Li, Liu (CR24) 2020; 154
Zhu, Peng, Chen, Gao (CR34) 2019; 323
Wen, Li, Gao (CR10) 2021; 68
Chen, Wang, Qiao, Chen (CR2) 2018; 13
Nath, Udmale, Singh (CR4) 2021; 54
Song, Li, Jia, Qiu (CR41) 2020; 16
Yao, Zhang, Yang, Gui (CR21) 2020; 20
Jiang, He, Yan, Xie (CR39) 2019; 66
Zhou, Peng, Chen, Yang, Zhang (CR15) 2018; 13
Han, Choi, Park, Hong (CR30) 2020; 15
Long, Zhang, Li (CR29) 2020; 16
Zhang, Huang, Wu, Hu, Huang, Zhou, Zhang (CR1) 2021; 16
Lei, Yang, Jiang, Jia, Li, Nandi (CR3) 2020; 138
Zhang, Chen, He, Xu, Li, Zhou (CR25) 2021; 158
Y G Lei (673_CR3) 2020; 138
Y Yao (673_CR21) 2020; 20
J H Han (673_CR30) 2020; 15
J Y Long (673_CR29) 2020; 16
L Wen (673_CR36) 2020; 69
D H Wolpert (673_CR8) 2002
Y Song (673_CR41) 2020; 16
X F Chen (673_CR2) 2018; 13
673_CR14
673_CR13
P Zhou (673_CR15) 2018; 13
673_CR12
L Wen (673_CR11) 2020; 53
J B Chen (673_CR19) 2021; 70
673_CR32
Z X Li (673_CR18) 2021; 70
D H Wolpert (673_CR7) 1997; 1
Z Y Chen (673_CR6) 2020; 140
R X Wang (673_CR24) 2020; 154
L Wen (673_CR10) 2021; 68
H Li (673_CR28) 2020; 234
G Q Jiang (673_CR39) 2019; 66
S Li (673_CR22) 2020; 165
F Hutter (673_CR9) 2019
K Y Zhang (673_CR25) 2021; 158
J A Wei (673_CR31) 2020; 96
Y Wang (673_CR35) 2020; 10
Z Z Zhang (673_CR33) 2021; 51
W Zhang (673_CR37) 2017; 17
J L Wang (673_CR5) 2021; 17
X Zhang (673_CR1) 2021; 16
G W Xu (673_CR17) 2020; 69
L Li (673_CR27) 2018; 18
Z Y Zhu (673_CR34) 2019; 323
A G Nath (673_CR4) 2021; 54
H H Qiao (673_CR40) 2019; 7
J L Wang (673_CR16) 2020; 33
J Y Jiao (673_CR20) 2020; 417
D Kolar (673_CR23) 2020; 20
D T Hoang (673_CR38) 2019; 53
D Cabrera (673_CR26) 2020; 380
References_xml – volume: 66
  start-page: 3196
  issue: 4
  year: 2019
  end-page: 3207
  ident: CR39
  article-title: Multiscale convolutional neural networks for fault diagnosis of wind turbine gearbox
  publication-title: IEEE Transactions on Industrial Electronics
  doi: 10.1109/TIE.2018.2844805
– volume: 234
  start-page: 343
  issue: 1
  year: 2020
  end-page: 360
  ident: CR28
  article-title: Raw vibration signal pattern recognition with automatic hyper-parameter-optimized convolutional neural network for bearing fault diagnosis
  publication-title: Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science
– volume: 1
  start-page: 67
  issue: 1
  year: 1997
  end-page: 82
  ident: CR7
  article-title: No free lunch theorems for optimization
  publication-title: IEEE Transactions on Evolutionary Computation
  doi: 10.1109/4235.585893
– volume: 20
  start-page: 4017
  issue: 14
  year: 2020
  ident: CR23
  article-title: Fault diagnosis of rotary machines using deep convolutional neural network with wide three axis vibration signal input
  publication-title: Sensors
  doi: 10.3390/s20144017
– ident: CR14
– volume: 17
  start-page: 425
  issue: 2
  year: 2017
  ident: CR37
  article-title: A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals
  publication-title: Sensors
  doi: 10.3390/s17020425
– start-page: 25
  year: 2002
  end-page: 42
  ident: CR8
  article-title: The supervised learning no-free-lunch theorems
  publication-title: Soft Computing and Industry
  doi: 10.1007/978-1-4471-0123-9_3
– volume: 158
  start-page: 107773
  year: 2021
  ident: CR25
  article-title: Differentiable neural architecture search augmented with pruning and multi-objective optimization for time-efficient intelligent fault diagnosis of machinery
  publication-title: Mechanical Systems and Signal Processing
  doi: 10.1016/j.ymssp.2021.107773
– volume: 18
  start-page: 6765
  issue: 1
  year: 2018
  end-page: 6816
  ident: CR27
  article-title: Hyperband: a novel bandit-based approach to hyperparameter optimization
  publication-title: The Journal of Machine Learning Research
– ident: CR12
– volume: 15
  start-page: 721
  issue: 2
  year: 2020
  end-page: 726
  ident: CR30
  article-title: Hyperparameter optimization using a genetic algorithm considering verification time in a convolutional neural network
  publication-title: Journal of Electrical Engineering & Technology
  doi: 10.1007/s42835-020-00343-7
– volume: 165
  start-page: 108122
  year: 2020
  ident: CR22
  article-title: An adaptive data fusion strategy for fault diagnosis based on the convolutional neural network
  publication-title: Measurement
  doi: 10.1016/j.measurement.2020.108122
– volume: 16
  start-page: 6163
  issue: 9
  year: 2020
  end-page: 6171
  ident: CR41
  article-title: Retraining strategy-based domain adaption network for intelligent fault diagnosis
  publication-title: IEEE Transactions on Industrial Informatics
  doi: 10.1109/TII.2019.2950667
– volume: 140
  start-page: 106683
  year: 2020
  ident: CR6
  article-title: A deep learning method for bearing fault diagnosis based on cyclic spectral coherence and convolutional neural networks
  publication-title: Mechanical Systems and Signal Processing
  doi: 10.1016/j.ymssp.2020.106683
– volume: 33
  start-page: 587
  issue: 4
  year: 2020
  end-page: 596
  ident: CR16
  article-title: Deformable convolutional networks for efficient mixed-type wafer defect pattern recognition
  publication-title: IEEE Transactions on Semiconductor Manufacturing
  doi: 10.1109/TSM.2020.3020985
– volume: 154
  start-page: 107417
  year: 2020
  ident: CR24
  article-title: A reinforcement neural architecture search method for rolling bearing fault diagnosis
  publication-title: Measurement
  doi: 10.1016/j.measurement.2019.107417
– volume: 69
  start-page: 509
  issue: 2
  year: 2020
  end-page: 520
  ident: CR17
  article-title: Online fault diagnosis method based on transfer convolutional neural networks
  publication-title: IEEE Transactions on Instrumentation and Measurement
  doi: 10.1109/TIM.2019.2902003
– volume: 70
  start-page: 3500417
  year: 2021
  ident: CR18
  article-title: A novel method for imbalanced fault diagnosis of rotating machinery based on generative adversarial networks
  publication-title: IEEE Transactions on Instrumentation and Measurement
– volume: 51
  start-page: 604
  issue: 2
  year: 2021
  end-page: 613
  ident: CR33
  article-title: Asynchronous episodic deep deterministic policy gradient: toward continuous control in computationally complex environments
  publication-title: IEEE Transactions on Cybernetics
  doi: 10.1109/TCYB.2019.2939174
– volume: 13
  start-page: 264
  issue: 2
  year: 2018
  end-page: 291
  ident: CR2
  article-title: Basic research on machinery fault diagnostics: past, present, and future trends
  publication-title: Frontiers of Mechanical Engineering
  doi: 10.1007/s11465-018-0472-3
– volume: 96
  start-page: 103966
  year: 2020
  ident: CR31
  article-title: New imbalanced fault diagnosis framework based on cluster-MWMOTE and MFO-optimized LS-SVM using limited and complex bearing data
  publication-title: Engineering Applications of Artificial Intelligence
  doi: 10.1016/j.engappai.2020.103966
– volume: 20
  start-page: 1233
  issue: 4
  year: 2020
  ident: CR21
  article-title: Learning attention representation with a multi-scale CNN for gear fault diagnosis under different working conditions
  publication-title: Sensors
  doi: 10.3390/s20041233
– volume: 323
  start-page: 62
  year: 2019
  end-page: 75
  ident: CR34
  article-title: A convolutional neural network based on a capsule network with strong generalization for bearing fault diagnosis
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2018.09.050
– volume: 380
  start-page: 51
  year: 2020
  end-page: 66
  ident: CR26
  article-title: Bayesian approach and time series dimensionality reduction to LSTM-based model-building for fault diagnosis of a reciprocating compressor
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2019.11.006
– volume: 17
  start-page: 7913
  issue: 12
  year: 2021
  end-page: 7922
  ident: CR5
  article-title: An unequal deep learning approach for 3-D point cloud segmentation
  publication-title: IEEE Transactions on Industrial Informatics
  doi: 10.1109/TII.2020.3044106
– volume: 16
  start-page: 4928
  issue: 7
  year: 2020
  end-page: 4937
  ident: CR29
  article-title: Evolving deep echo state networks for intelligent fault diagnosis
  publication-title: IEEE Transactions on Industrial Informatics
  doi: 10.1109/TII.2019.2938884
– year: 2019
  ident: CR9
  publication-title: Automated Machine Learning: Methods, Systems, Challenges
  doi: 10.1007/978-3-030-05318-5
– volume: 7
  start-page: 118954
  year: 2019
  end-page: 118964
  ident: CR40
  article-title: An adaptive weighted multiscale convolutional neural network for rotating machinery fault diagnosis under variable operating conditions
  publication-title: IEEE Access: Practical Innovations, Open Solutions
  doi: 10.1109/ACCESS.2019.2936625
– ident: CR13
– volume: 68
  start-page: 12890
  issue: 12
  year: 2021
  end-page: 12900
  ident: CR10
  article-title: A new reinforcement learning based learning rate scheduler for convolutional neural network in fault classification
  publication-title: IEEE Transactions on Industrial Electronics
  doi: 10.1109/TIE.2020.3044808
– volume: 13
  start-page: 292
  issue: 2
  year: 2018
  end-page: 300
  ident: CR15
  article-title: Non-stationary signal analysis based on general parameterized time-frequency transform and its application in the feature extraction of a rotary machine
  publication-title: Frontiers of Mechanical Engineering
  doi: 10.1007/s11465-017-0443-0
– ident: CR32
– volume: 54
  start-page: 2609
  year: 2021
  end-page: 2668
  ident: CR4
  article-title: Role of artificial intelligence in rotor fault diagnosis: a comprehensive review
  publication-title: Artificial Intelligence Review
  doi: 10.1007/s10462-020-09910-w
– volume: 53
  start-page: 1088
  issue: 7–8
  year: 2020
  end-page: 1098
  ident: CR11
  article-title: A new automatic machine learning based hyperparameter optimization for workpiece quality prediction
  publication-title: Measurement and Control
  doi: 10.1177/0020294020932347
– volume: 53
  start-page: 42
  year: 2019
  end-page: 50
  ident: CR38
  article-title: Rolling element bearing fault diagnosis using convolutional neural network and vibration image
  publication-title: Cognitive Systems Research
  doi: 10.1016/j.cogsys.2018.03.002
– volume: 69
  start-page: 330
  issue: 2
  year: 2020
  end-page: 338
  ident: CR36
  article-title: A new two-level hierarchical diagnosis network based on convolutional neural network
  publication-title: IEEE Transactions on Instrumentation and Measurement
  doi: 10.1109/TIM.2019.2896370
– volume: 10
  start-page: 3659
  issue: 10
  year: 2020
  ident: CR35
  article-title: A novel capsule network based on wide convolution and multi-scale convolution for fault diagnosis
  publication-title: Applied Sciences
  doi: 10.3390/app10103659
– volume: 138
  start-page: 106587
  year: 2020
  ident: CR3
  article-title: Applications of machine learning to machine fault diagnosis: a review and roadmap
  publication-title: Mechanical Systems and Signal Processing
  doi: 10.1016/j.ymssp.2019.106587
– volume: 16
  start-page: 340
  issue: 2
  year: 2021
  end-page: 352
  ident: CR1
  article-title: Multi-model ensemble deep learning method for intelligent fault diagnosis with high-dimensional samples
  publication-title: Frontiers of Mechanical Engineering
  doi: 10.1007/s11465-021-0629-3
– volume: 417
  start-page: 36
  year: 2020
  end-page: 63
  ident: CR20
  article-title: A comprehensive review on convolutional neural network in machine fault diagnosis
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2020.07.088
– volume: 70
  start-page: 3517010
  year: 2021
  ident: CR19
  article-title: Multiscale convolutional neural network with feature alignment for bearing fault diagnosis
  publication-title: IEEE Transactions on Instrumentation and Measurement
– volume: 138
  start-page: 106587
  year: 2020
  ident: 673_CR3
  publication-title: Mechanical Systems and Signal Processing
  doi: 10.1016/j.ymssp.2019.106587
– start-page: 25
  volume-title: Soft Computing and Industry
  year: 2002
  ident: 673_CR8
  doi: 10.1007/978-1-4471-0123-9_3
– volume: 323
  start-page: 62
  year: 2019
  ident: 673_CR34
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2018.09.050
– volume: 33
  start-page: 587
  issue: 4
  year: 2020
  ident: 673_CR16
  publication-title: IEEE Transactions on Semiconductor Manufacturing
  doi: 10.1109/TSM.2020.3020985
– volume: 17
  start-page: 425
  issue: 2
  year: 2017
  ident: 673_CR37
  publication-title: Sensors
  doi: 10.3390/s17020425
– volume: 68
  start-page: 12890
  issue: 12
  year: 2021
  ident: 673_CR10
  publication-title: IEEE Transactions on Industrial Electronics
  doi: 10.1109/TIE.2020.3044808
– volume: 16
  start-page: 340
  issue: 2
  year: 2021
  ident: 673_CR1
  publication-title: Frontiers of Mechanical Engineering
  doi: 10.1007/s11465-021-0629-3
– volume: 20
  start-page: 1233
  issue: 4
  year: 2020
  ident: 673_CR21
  publication-title: Sensors
  doi: 10.3390/s20041233
– volume: 140
  start-page: 106683
  year: 2020
  ident: 673_CR6
  publication-title: Mechanical Systems and Signal Processing
  doi: 10.1016/j.ymssp.2020.106683
– ident: 673_CR12
– volume: 16
  start-page: 6163
  issue: 9
  year: 2020
  ident: 673_CR41
  publication-title: IEEE Transactions on Industrial Informatics
  doi: 10.1109/TII.2019.2950667
– volume: 17
  start-page: 7913
  issue: 12
  year: 2021
  ident: 673_CR5
  publication-title: IEEE Transactions on Industrial Informatics
  doi: 10.1109/TII.2020.3044106
– volume: 16
  start-page: 4928
  issue: 7
  year: 2020
  ident: 673_CR29
  publication-title: IEEE Transactions on Industrial Informatics
  doi: 10.1109/TII.2019.2938884
– volume: 417
  start-page: 36
  year: 2020
  ident: 673_CR20
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2020.07.088
– volume: 53
  start-page: 1088
  issue: 7–8
  year: 2020
  ident: 673_CR11
  publication-title: Measurement and Control
  doi: 10.1177/0020294020932347
– volume: 96
  start-page: 103966
  year: 2020
  ident: 673_CR31
  publication-title: Engineering Applications of Artificial Intelligence
  doi: 10.1016/j.engappai.2020.103966
– volume: 53
  start-page: 42
  year: 2019
  ident: 673_CR38
  publication-title: Cognitive Systems Research
  doi: 10.1016/j.cogsys.2018.03.002
– ident: 673_CR14
– volume: 51
  start-page: 604
  issue: 2
  year: 2021
  ident: 673_CR33
  publication-title: IEEE Transactions on Cybernetics
  doi: 10.1109/TCYB.2019.2939174
– volume: 13
  start-page: 264
  issue: 2
  year: 2018
  ident: 673_CR2
  publication-title: Frontiers of Mechanical Engineering
  doi: 10.1007/s11465-018-0472-3
– volume: 66
  start-page: 3196
  issue: 4
  year: 2019
  ident: 673_CR39
  publication-title: IEEE Transactions on Industrial Electronics
  doi: 10.1109/TIE.2018.2844805
– volume: 70
  start-page: 3500417
  year: 2021
  ident: 673_CR18
  publication-title: IEEE Transactions on Instrumentation and Measurement
– volume: 70
  start-page: 3517010
  year: 2021
  ident: 673_CR19
  publication-title: IEEE Transactions on Instrumentation and Measurement
– volume: 165
  start-page: 108122
  year: 2020
  ident: 673_CR22
  publication-title: Measurement
  doi: 10.1016/j.measurement.2020.108122
– volume: 20
  start-page: 4017
  issue: 14
  year: 2020
  ident: 673_CR23
  publication-title: Sensors
  doi: 10.3390/s20144017
– volume: 7
  start-page: 118954
  year: 2019
  ident: 673_CR40
  publication-title: IEEE Access: Practical Innovations, Open Solutions
  doi: 10.1109/ACCESS.2019.2936625
– volume: 10
  start-page: 3659
  issue: 10
  year: 2020
  ident: 673_CR35
  publication-title: Applied Sciences
  doi: 10.3390/app10103659
– volume: 69
  start-page: 509
  issue: 2
  year: 2020
  ident: 673_CR17
  publication-title: IEEE Transactions on Instrumentation and Measurement
  doi: 10.1109/TIM.2019.2902003
– ident: 673_CR32
– volume: 380
  start-page: 51
  year: 2020
  ident: 673_CR26
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2019.11.006
– volume: 54
  start-page: 2609
  year: 2021
  ident: 673_CR4
  publication-title: Artificial Intelligence Review
  doi: 10.1007/s10462-020-09910-w
– volume: 154
  start-page: 107417
  year: 2020
  ident: 673_CR24
  publication-title: Measurement
  doi: 10.1016/j.measurement.2019.107417
– volume: 18
  start-page: 6765
  issue: 1
  year: 2018
  ident: 673_CR27
  publication-title: The Journal of Machine Learning Research
– volume-title: Automated Machine Learning: Methods, Systems, Challenges
  year: 2019
  ident: 673_CR9
  doi: 10.1007/978-3-030-05318-5
– volume: 158
  start-page: 107773
  year: 2021
  ident: 673_CR25
  publication-title: Mechanical Systems and Signal Processing
  doi: 10.1016/j.ymssp.2021.107773
– ident: 673_CR13
– volume: 13
  start-page: 292
  issue: 2
  year: 2018
  ident: 673_CR15
  publication-title: Frontiers of Mechanical Engineering
  doi: 10.1007/s11465-017-0443-0
– volume: 69
  start-page: 330
  issue: 2
  year: 2020
  ident: 673_CR36
  publication-title: IEEE Transactions on Instrumentation and Measurement
  doi: 10.1109/TIM.2019.2896370
– volume: 15
  start-page: 721
  issue: 2
  year: 2020
  ident: 673_CR30
  publication-title: Journal of Electrical Engineering & Technology
  doi: 10.1007/s42835-020-00343-7
– volume: 234
  start-page: 343
  issue: 1
  year: 2020
  ident: 673_CR28
  publication-title: Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science
– volume: 1
  start-page: 67
  issue: 1
  year: 1997
  ident: 673_CR7
  publication-title: IEEE Transactions on Evolutionary Computation
  doi: 10.1109/4235.585893
SSID ssj0002025523
Score 2.2655103
Snippet Convolutional neural network (CNN) has achieved remarkable applications in fault diagnosis. However, the tuning aiming at obtaining the well-trained CNN model...
SourceID crossref
springer
higheredpress
SourceType Enrichment Source
Index Database
Publisher
StartPage 17
SubjectTerms convolutional neural network
deep reinforcement learning
Engineering
fault diagnosis
hyper parameter optimization
Intelligent Diagnosis and Maintenance
Mechanical Engineering
Research Article
Title A new automatic convolutional neural network based on deep reinforcement learning for fault diagnosis
URI https://journal.hep.com.cn/fme/EN/10.1007/s11465-022-0673-7
https://link.springer.com/article/10.1007/s11465-022-0673-7
Volume 17
WOSCitedRecordID wos000819778900001&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: PRVAVX
  databaseName: SpringerLINK Contemporary 1997-Present
  customDbUrl:
  eissn: 2095-0241
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002025523
  issn: 2095-0233
  databaseCode: RSV
  dateStart: 20060101
  isFulltext: true
  titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22
  providerName: Springer Nature
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3dS8MwED90-qCI3-L8Ig8-KYE2SZv2cYjDpyF-sbeS5UMHox1b599vkrabQxnoUyEkoVwuuUvu7vcDuDaS8pAQjXk64JiJgOFUhxQ775THwSCQQnqyCd7rJf1--ljXcU-bbPcmJOlP6kWxm93UrpqYYEeugvk6bFhrl7jd-PT8Nn9YIc5L9rRuJPDVx5Q20czfZlmyRzsfPrlCK5-E-iM46m1Od-9ff7sPu7WLiTqVThzAms4PYfsb8OAR6A6y7jQSs7LwkK3IJZ_XSmiHOpBL__Ep4shZOoWKHCmtx2iiPdiq9O-KqGadeEe2CRkxG5VIVdl7w-kxvHbvX-4ecE24gCWlvMRKpTJihMWCDIQwUiQhEyxRsUilvVgxK1pj3aWYGGYoV4kxKpRSpVQwYoh1HE-glRe5PgVEI2GsBBTlEbeXqiiRiT1ODNdcMmmnb0PQiD2TNRq5I8UYZQscZSfBzEowcxLMeBtu5kPGFRTHqs7h0lpmxuFBOHbxVWNum7XM6p28ovfZn3qfwxaplAEH4QW0yslMX8Km_CyH08mV1-Av99vp8A
linkProvider Springer Nature
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1bS8MwFA46BRXxLs5rHnxSAm2SNu3jEIfiHKJT9hayXHQwtrF1_n6TtN0cykCfCiUJ5eQk56T5zvcBcGkkYSHGGrG0wxAVAUWpDgly2SmLg04ghfRiE6zZTNrt9Kmo4x6XaPfyStLv1LNiN7uoXTUxRk5cBbFlsEJtwHI4vueXt-mPFeyyZC_rhgNffUxIeZv52yhz8Wjzw4MrtPIg1B-Xoz7m1Lf_9bU7YKtIMWEt94ldsKT7e2DjG_HgPtA1aNNpKCbZwFO2Qgc-L5zQdnUkl_7hIeLQRToFB32otB7CkfZkq9L_V4SF6sQ7tK-gEZNeBlWO3uuOD8Br_bZ1c4cKwQUkCWEZUiqVEcU0FrgjhJEiCamgiYpFKu3BilrTGpsuxdhQQ5hKjFGhlColgmKDbeJ4CCr9QV8fAUgiYawFFGERs4eqKJGJ3U4M00xSaYevgqA0O5cFG7kTxejxGY-ysyC3FuTOgpxVwdW0yzCn4ljUOJybS24cH4RTF1_U57qcS16s5AWtj__U-gKs3bUeG7xx33w4Aes4dwwUhKegko0m-gysys-sOx6de2_-AvcN7NQ
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3dS8MwEA86RRTxW5yfefBJCWuTdGkfhzoUZQz8YG8hy4cORje2zr_fJG03hzIQnwrlEsrl0rvk7n4_AC6NJCzEWCOWdBmiIqAo0SFBLjpl9aAbSCE92QRrteJOJ2kXPKfjstq9TEnmPQ0OpSnNakNlarPGN7vBXWcxRo5oBbFlsEIdZ5A7rj-_TS9ZsIuYPcUbDnwnMiFlZvO3WeZ80-aHL7TQyhek_kiUev_T3P73l--ArSL0hI3cVnbBkk73wMY3QMJ9oBvQhtlQTLKBh3KFrii9ME471IFf-ocvHYfOAyo4SKHSeghH2oOwSn_fCAs2indoX0EjJv0Mqryqrzc-AK_Nu5ebe1QQMSBJCMuQUomMKKZ1gbtCGCnikAoaq7pIpD1wUatmY8OoOjbUEKZiY1QopUqIoNhgG1Aegko6SPURgCQSxmpAERYxe9iKYhnb34xhmkkq7fRVEJRLwGWBUu7IMvp8hq_sNMitBrnTIGdVcDUdMswhOhYJh3Pryo3DiXCs44vGXJfryosdvkD6-E_SF2CtfdvkTw-txxOwjnO7QEF4CirZaKLPwKr8zHrj0bk37C-nb_W4
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=A+new+automatic+convolutional+neural+network+based+on+deep+reinforcement+learning+for+fault+diagnosis&rft.jtitle=Frontiers+of+Mechanical+Engineering&rft.au=Wen%2C+Long&rft.au=Wang%2C+You&rft.au=Li%2C+Xinyu&rft.date=2022-06-01&rft.issn=2095-0233&rft.eissn=2095-0241&rft.volume=17&rft.issue=2&rft_id=info:doi/10.1007%2Fs11465-022-0673-7&rft.externalDBID=n%2Fa&rft.externalDocID=10_1007_s11465_022_0673_7
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2095-0233&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2095-0233&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2095-0233&client=summon