Joint autoencoder-regressor deep neural network for remaining useful life prediction

•We introduce a joint autoencoder and regressor architecture for remaining useful life prediction, and demonstrate the effectiveness of this model on two prognostics benchmarks.•We also propose a new fault detection-based approach to modeling remaining useful life degradation and RUL labeling as an...

Full description

Saved in:
Bibliographic Details
Published in:Engineering science and technology, an international journal Vol. 41; p. 101409
Main Authors: İnce, Kürşat, Genc, Yakup
Format: Journal Article
Language:English
Published: Elsevier B.V 01.05.2023
Elsevier
Subjects:
ISSN:2215-0986, 2215-0986
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract •We introduce a joint autoencoder and regressor architecture for remaining useful life prediction, and demonstrate the effectiveness of this model on two prognostics benchmarks.•We also propose a new fault detection-based approach to modeling remaining useful life degradation and RUL labeling as an alternative to linear and piecewise linear degradation models.•We apply non-linear transformations to raw sensor data, and show that it improves modeling performance on time series data. Ubiquitous availability of IoT technologies allows processing of large amounts of data to improve prognostics tasks in industrial applications. One such important task of prognostics is the prediction of remaining useful life of a system from past performance data. In practice, although failure points are pinpointed, the actual start of degradation is not necessarily available, but usually modeled simply with a linear degradation assumption. In this paper we present a data-driven approach to remaining useful life prediction using joint autoencoder-regression network, a deep neural network model incorporating a convolutional neural network autoencoder and a long-short term memory network regressor trained end-to-end. We also present a new fault detection-based approach to modeling remaining useful life degradation. This model allows a better estimate of the start and progress of equipment degradation ending with a failure. We demonstrate the effectiveness of the proposed algorithms on two datasets. The first one is C-MAPSS frequently used as a benchmark among prognostic researchers. The second one is PHME20, a recent prognostic dataset from a prognostics competition. These experiments show that the proposed algorithms are capable of predicting remaining useful life as good as the state of art methods. The results also show that fault detection-based labeling outperforms linear labeling.
AbstractList Ubiquitous availability of IoT technologies allows processing of large amounts of data to improve prognostics tasks in industrial applications. One such important task of prognostics is the prediction of remaining useful life of a system from past performance data. In practice, although failure points are pinpointed, the actual start of degradation is not necessarily available, but usually modeled simply with a linear degradation assumption. In this paper we present a data-driven approach to remaining useful life prediction using joint autoencoder-regression network, a deep neural network model incorporating a convolutional neural network autoencoder and a long-short term memory network regressor trained end-to-end. We also present a new fault detection-based approach to modeling remaining useful life degradation. This model allows a better estimate of the start and progress of equipment degradation ending with a failure. We demonstrate the effectiveness of the proposed algorithms on two datasets. The first one is C-MAPSS frequently used as a benchmark among prognostic researchers. The second one is PHME20, a recent prognostic dataset from a prognostics competition. These experiments show that the proposed algorithms are capable of predicting remaining useful life as good as the state of art methods. The results also show that fault detection-based labeling outperforms linear labeling.
•We introduce a joint autoencoder and regressor architecture for remaining useful life prediction, and demonstrate the effectiveness of this model on two prognostics benchmarks.•We also propose a new fault detection-based approach to modeling remaining useful life degradation and RUL labeling as an alternative to linear and piecewise linear degradation models.•We apply non-linear transformations to raw sensor data, and show that it improves modeling performance on time series data. Ubiquitous availability of IoT technologies allows processing of large amounts of data to improve prognostics tasks in industrial applications. One such important task of prognostics is the prediction of remaining useful life of a system from past performance data. In practice, although failure points are pinpointed, the actual start of degradation is not necessarily available, but usually modeled simply with a linear degradation assumption. In this paper we present a data-driven approach to remaining useful life prediction using joint autoencoder-regression network, a deep neural network model incorporating a convolutional neural network autoencoder and a long-short term memory network regressor trained end-to-end. We also present a new fault detection-based approach to modeling remaining useful life degradation. This model allows a better estimate of the start and progress of equipment degradation ending with a failure. We demonstrate the effectiveness of the proposed algorithms on two datasets. The first one is C-MAPSS frequently used as a benchmark among prognostic researchers. The second one is PHME20, a recent prognostic dataset from a prognostics competition. These experiments show that the proposed algorithms are capable of predicting remaining useful life as good as the state of art methods. The results also show that fault detection-based labeling outperforms linear labeling.
ArticleNumber 101409
Author Genc, Yakup
İnce, Kürşat
Author_xml – sequence: 1
  givenname: Kürşat
  surname: İnce
  fullname: İnce, Kürşat
  email: kince@havelsan.com.tr, kince@gtu.edu.tr
  organization: Naval Combat Management Technologies Center, HAVELSAN Inc., Pendik/İstanbul, Türkiye
– sequence: 2
  givenname: Yakup
  surname: Genc
  fullname: Genc, Yakup
  email: yakup.genc@gtu.edu.tr
  organization: Computer Engineering Department, Gebze Technical University, Gebze/Kocaeli, Türkiye
BookMark eNqFkc1q3DAURkWYQKZJ3iALv4CnkizLoy4KJbT5YaCbdC1k6Woi12MNV5qGvn01cQghi3R1xQff4ercT2QxxQkIuWJ0xSiTn4fVACnbxxWnvDlGgqoTsuSctTVVa7l48z4jlykNlFKmOGOtXJKH-ximXJlDjjDZ6ABrhC1CShErB7CvJjigGcvITxF_V77kCDsTpjBtq0MCfxirMXio9ggu2BzidEFOvRkTXL7Mc_Lrx_eH69t68_Pm7vrbpraCrXNtedsLV_aF1ishwZU9G6VE70237hw4z_3aMWY6EI2STduAVFL0TQ-NU61tzsndzHXRDHqPYWfwr44m6Ocg4lYbzMGOoBmVXSekZMBAABdKSQN9pzzjvoVWFZaYWRZjSgj-lceoPorWg55F66NoPYsutS_vajZkc5SQ0YTxf-WvcxmKpD8BUCcbyhmKRwSbyy_Cx4B_7iyeTQ
CitedBy_id crossref_primary_10_1007_s10796_024_10558_y
crossref_primary_10_1016_j_engappai_2025_110285
crossref_primary_10_1002_qre_3693
crossref_primary_10_1109_ACCESS_2025_3580267
crossref_primary_10_1002_qre_70057
Cites_doi 10.1016/j.ress.2017.11.021
10.1007/978-1-4899-7488-4_196
10.1007/978-3-030-58452-8_24
10.1109/TII.2021.3121326
10.1023/A:1007379606734
10.23919/FRUCT49677.2020.9211058
10.1016/j.ress.2022.108916
10.1007/s40747-018-0082-z
10.1109/ACCESS.2019.2895394
10.1109/TMECH.2021.3098737
10.36001/phme.2020.v5i1.1317
10.1109/TNNLS.2016.2582798
10.1007/s10916-020-1534-8
10.1016/j.ress.2021.108119
10.1016/j.cja.2016.04.007
10.1016/j.ymssp.2017.11.016
10.1109/BigData50022.2020.9377816
10.1109/ICACI49185.2020.9177774
10.1109/ACCESS.2021.3101284
10.3390/app8122416
10.3934/mbe.2019040
10.1016/j.ymssp.2017.11.024
10.1109/ACCESS.2019.2920297
10.1016/j.compind.2019.02.004
10.36001/phme.2020.v5i1.1318
10.1155/2015/793161
10.1109/TNNLS.2021.3070840
ContentType Journal Article
Copyright 2023 THE AUTHORS
Copyright_xml – notice: 2023 THE AUTHORS
DBID 6I.
AAFTH
AAYXX
CITATION
DOA
DOI 10.1016/j.jestch.2023.101409
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList

Database_xml – sequence: 1
  dbid: DOA
  name: Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2215-0986
ExternalDocumentID oai_doaj_org_article_106774661e1e4e24996aeb79f12f5e59
10_1016_j_jestch_2023_101409
S2215098623000861
GroupedDBID 0R~
0SF
4.4
457
5VS
6I.
AACTN
AAEDT
AAEDW
AAFTH
AAIKJ
AALRI
AAXUO
ABMAC
ACGFS
ADBBV
ADEZE
ADVLN
AEXQZ
AFTJW
AGHFR
AITUG
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
BCNDV
EBS
EJD
FDB
GROUPED_DOAJ
HZ~
IPNFZ
IXB
KQ8
M41
M~E
NCXOZ
O9-
OK1
RIG
ROL
SSZ
AAYWO
AAYXX
AFJKZ
APXCP
CITATION
ID FETCH-LOGICAL-c418t-c25b4d140e5f946ed2213994bfa787dedf2f8d11a7e4396353e6964b3be3d95c3
IEDL.DBID DOA
ISICitedReferencesCount 5
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001026525500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2215-0986
IngestDate Fri Oct 03 12:44:53 EDT 2025
Sat Nov 29 05:06:09 EST 2025
Tue Nov 18 20:24:45 EST 2025
Sat Aug 17 15:42:57 EDT 2024
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Deep learning
Fault detection
Remaining useful life
C-MAPSS
Predictive maintenance
Language English
License This is an open access article under the CC BY-NC-ND license.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c418t-c25b4d140e5f946ed2213994bfa787dedf2f8d11a7e4396353e6964b3be3d95c3
OpenAccessLink https://doaj.org/article/106774661e1e4e24996aeb79f12f5e59
ParticipantIDs doaj_primary_oai_doaj_org_article_106774661e1e4e24996aeb79f12f5e59
crossref_primary_10_1016_j_jestch_2023_101409
crossref_citationtrail_10_1016_j_jestch_2023_101409
elsevier_sciencedirect_doi_10_1016_j_jestch_2023_101409
PublicationCentury 2000
PublicationDate May 2023
2023-05-00
2023-05-01
PublicationDateYYYYMMDD 2023-05-01
PublicationDate_xml – month: 05
  year: 2023
  text: May 2023
PublicationDecade 2020
PublicationTitle Engineering science and technology, an international journal
PublicationYear 2023
Publisher Elsevier B.V
Elsevier
Publisher_xml – name: Elsevier B.V
– name: Elsevier
References Listou Ellefsen, Bjørlykhaug, Æsøy, Ushakov, Zhang (b0125) June 2018; 183
A. Chaoub, A. Voisin, C. Cerisara, B. Iung, Learning representations with end-to-end models for improved remaining useful life prognostics. https://arxiv.org/abs/2104.05049.
Back, Fogel, Michalewicz (b0215) 2000
Li, Gao, Tang, Li (b0230) 2016; 29
Wen, Dong, Gao (b0240) 2019; 16
K. Cho, B. van Merrienboer, Ç. Gülçehre, F. Bougares, H. Schwenk, Y. Bengio, Learning phrase representations using RNN encoder-decoder for statistical machine translation, CoRR abs/1406.1078, http://arxiv.org/abs/1406.1078.
A. Saxena, D. Simon, Turbofan Engine Degradation Simulation Data Set
A. Ellefsen, E. Bjorlykhaug, V. Æsøy, H. Zhang, An unsupervised reconstruction-based fault detection algorithm for maritime components, IEEE Access PP (2019) 1–1. doi: 10.1109/ACCESS.2019.2895394.
Chen, Chen, Liu (b0060) 2021; 3
Tsui, Chen, Zhou, Hai, Wang (b0070) 2015; 2015
K. Ince, E. Sirkeci, Y. Genc, Remaining useful life prediction for experimental filtration system: A data challenge, in: PHM Society European Conference, 2020, pp. 1–6. doi: 10.36001/phme.2020.v5i1.1317.
Al-Dulaimi, Zabihi, Asif, Mohammadi (b0135) 2019; 108
Chen, Qin, Qian, Wang, Liu (b0065) 2023; 230
Zio (b0040) 2022; 218
Zhang, Lim, Qin, Tan (b0225) 2017; 28
Zhao, Bin Liang, Wang (b0180) 2017; 164
D. Giordano, D. Gagar, Fifth european conference of the prognostics and health management society 2020 data challenge
X. Li, Q. Ding, J.Q. Sun, Remaining useful life estimation in prognostics using deep convolution neural networks, Reliability Engineering and System Safety 172 (November 2017) (2018) 1–11. doi: 10.1016/j.ress.2017.11.021.
Li, Zhang, Ma, Luo, Li (b0005) 2022; 33
S.Z. Li, A. Jain (Eds.), Gaussian Mixture Models, Springer US, Boston, MA, 2015, pp. 827–832. doi: 10.1007/978-1-4899-7488-4_196.
(Last accessed: Mar 25, 2023) (February 2016).
Sayyad, Kumar, Bongale, Kamat, Patil, Kotecha (b0035) 2021; 9
Elattar, Elminir, Riad (b0075) 2018; 4
Lei, Li, Guo, Li, Yan, Lin (b0030) 2018; 104
Khan, Yairi (b0080) 2018; 107
Li, Xu, Li, Yang, Lei (b0155) 2022
(Last accessed: Mar 25, 2023) (2008).
Qin, Zhou, Chen (b0110) 2022; 27
P. Malhotra, V. Tv, A. Ramakrishnan, G. Anand, L. Vig, P. Agarwal, G. Shroff, Multi-sensor prognostics using an unsupervised health index based on lstm encoder-decoder, 1st SIGKDD Workshop on Machine Learning for Prognostics and Health Management.
D.P. Kingma, M. Welling, Auto-encoding variational bayes, in: Y. Bengio, Y. LeCun (Eds.), 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14–16, 2014, Conference Track Proceedings, 2014, http://arxiv.org/abs/1312.6114.
H. Mo, F. Lucca, J. Malacarne, G. Iacca, Multi-Head CNN-LSTM with Prediction Error Analysis for Remaining Useful Life Prediction, Conference of Open Innovation Association, FRUCT 2020-September (2020) 164–171. doi: 10.23919/FRUCT49677.2020.9211058.
Shamayleh, Awad, Farhat (b0020) 2020; 44
Hinton (b0130) 2012
J. Rapoza, Maintaining virtual system uptime in today’s transforming it infrastructure, Online
Zhou, Qin, Luo, Wang, Zhu (b0095) 2022
H. Beirami, D. Calzá, A. Cimatti, M. Islam, M. Roveri, P. Svaizer, A data-driven approach for rul prediction of an experimental filtration system, in: PHM Society European Conference, 2020, pp. 1–7. doi: 10.36001/phme.2020.v5i1.1318.
(Last accessed: Mar 25, 2023) (March 2006).
Heimes (b0175) 2008
A. Zhang, H. Wang, S. Li, Y. Cui, Z. Liu, G. Yang, J. Hu, Transfer learning with deep recurrent neural networks for remaining useful life estimation, Applied Sciences (Switzerland) 8 (12). doi: 10.3390/app8122416.
Goodfellow, Bengio, Courville (b0085) 2016
N. Rahaman, A. Baratin, D. Arpit, F. Draxler, M. Lin, F. Hamprecht, Y. Bengio, A. Courville, On the spectral bias of neural networks, in: K. Chaudhuri, R. Salakhutdinov (Eds.), Proceedings of the 36th International Conference on Machine Learning, vol. 97 of Proceedings of Machine Learning Research, PMLR, 2019, pp. 5301–5310. doi: 10.48550/arXiv.1806.08734.
(Last accessed: Feb 28, 2021) (2020).
Bengtsson, Lundström (b0025) 2018; 25
B. Mildenhall, P.P. Srinivasan, M. Tancik, J.T. Barron, R. Ramamoorthi, R. Ng, Nerf: Representing scenes as neural radiance fields for view synthesis, in: A. Vedaldi, H. Bischof, T. Brox, J.M. Frahm (Eds.), Computer Vision – ECCV 2020, Springer International Publishing, Cham, 2020, pp. 405–421. doi: 10.1007/978-3-030-58452-8_24.
E. Vadala, C. Graham, Downtime costs auto industry $22k/minute – survey, Online
Sohn, Lee, Yan (b0105) 2015; vol. 28
Melendez-Vazquez, Doelling, Bringmann (b0220) 2020
Matthews (b0195) 1975; 405
Y. Jiang, Y. Lyu, Y. Wang, P. Wan, Fusion network combined with bidirectional LSTM network and multiscale CNN for useful life estimation LSTM network and multiscale CNN for useful life estimation, 12th International Conference on Advanced Computational Intelligence, ICACI 2020 (2020) 620–627. doi: 10.1109/ICACI49185.2020.9177774.
R. Caruana, Multitask Learning, Machine Learningdoi: 10.1023/A:1007379606734.
Xiang, Qin, Luo, Pu (b0160) 2022; 18
Ellefsen, Ushakov, Aesoy, Zhang (b0115) 2019; 7
Xiang (10.1016/j.jestch.2023.101409_b0160) 2022; 18
Zhang (10.1016/j.jestch.2023.101409_b0225) 2017; 28
10.1016/j.jestch.2023.101409_b0205
10.1016/j.jestch.2023.101409_b0165
10.1016/j.jestch.2023.101409_b0045
10.1016/j.jestch.2023.101409_b0100
Heimes (10.1016/j.jestch.2023.101409_b0175) 2008
Al-Dulaimi (10.1016/j.jestch.2023.101409_b0135) 2019; 108
10.1016/j.jestch.2023.101409_b0145
10.1016/j.jestch.2023.101409_b0200
Wen (10.1016/j.jestch.2023.101409_b0240) 2019; 16
Zhao (10.1016/j.jestch.2023.101409_b0180) 2017; 164
Sohn (10.1016/j.jestch.2023.101409_b0105) 2015; vol. 28
Listou Ellefsen (10.1016/j.jestch.2023.101409_b0125) 2018; 183
Goodfellow (10.1016/j.jestch.2023.101409_b0085) 2016
Shamayleh (10.1016/j.jestch.2023.101409_b0020) 2020; 44
Bengtsson (10.1016/j.jestch.2023.101409_b0025) 2018; 25
Zhou (10.1016/j.jestch.2023.101409_b0095) 2022
Matthews (10.1016/j.jestch.2023.101409_b0195) 1975; 405
Melendez-Vazquez (10.1016/j.jestch.2023.101409_b0220) 2020
10.1016/j.jestch.2023.101409_b0140
10.1016/j.jestch.2023.101409_b0185
10.1016/j.jestch.2023.101409_b0120
Tsui (10.1016/j.jestch.2023.101409_b0070) 2015; 2015
Li (10.1016/j.jestch.2023.101409_b0155) 2022
Ellefsen (10.1016/j.jestch.2023.101409_b0115) 2019; 7
10.1016/j.jestch.2023.101409_b0015
10.1016/j.jestch.2023.101409_b0235
10.1016/j.jestch.2023.101409_b0055
Elattar (10.1016/j.jestch.2023.101409_b0075) 2018; 4
10.1016/j.jestch.2023.101409_b0210
Chen (10.1016/j.jestch.2023.101409_b0065) 2023; 230
Sayyad (10.1016/j.jestch.2023.101409_b0035) 2021; 9
Hinton (10.1016/j.jestch.2023.101409_b0130) 2012
Qin (10.1016/j.jestch.2023.101409_b0110) 2022; 27
Back (10.1016/j.jestch.2023.101409_b0215) 2000
Lei (10.1016/j.jestch.2023.101409_b0030) 2018; 104
10.1016/j.jestch.2023.101409_b0090
Li (10.1016/j.jestch.2023.101409_b0230) 2016; 29
Khan (10.1016/j.jestch.2023.101409_b0080) 2018; 107
10.1016/j.jestch.2023.101409_b0150
10.1016/j.jestch.2023.101409_b0010
Li (10.1016/j.jestch.2023.101409_b0005) 2022; 33
Zio (10.1016/j.jestch.2023.101409_b0040) 2022; 218
10.1016/j.jestch.2023.101409_b0190
Chen (10.1016/j.jestch.2023.101409_b0060) 2021; 3
10.1016/j.jestch.2023.101409_b0170
10.1016/j.jestch.2023.101409_b0050
References_xml – volume: 7
  start-page: 71563
  year: 2019
  end-page: 71575
  ident: b0115
  article-title: Validation of Data-Driven Labeling Approaches Using a Novel Deep Network Structure for Remaining Useful Life Predictions
  publication-title: IEEE Access
– volume: 218
  year: 2022
  ident: b0040
  article-title: Prognostics and health management (phm): Where are we and where do we (need to) go in theory and practice
  publication-title: Reliab. Eng. Syst. Safety
– reference: D.P. Kingma, M. Welling, Auto-encoding variational bayes, in: Y. Bengio, Y. LeCun (Eds.), 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14–16, 2014, Conference Track Proceedings, 2014, http://arxiv.org/abs/1312.6114.
– reference: J. Rapoza, Maintaining virtual system uptime in today’s transforming it infrastructure, Online,
– volume: 107
  start-page: 241
  year: 2018
  end-page: 265
  ident: b0080
  article-title: A review on the application of deep learning in system health management
  publication-title: Mech. Syst. Signal Process.
– volume: 18
  start-page: 7230
  year: 2022
  end-page: 7239
  ident: b0160
  article-title: Spatiotemporally multidifferential processing deep neural network and its application to equipment remaining useful life prediction
  publication-title: IEEE Trans. Industr. Inf.
– reference: N. Rahaman, A. Baratin, D. Arpit, F. Draxler, M. Lin, F. Hamprecht, Y. Bengio, A. Courville, On the spectral bias of neural networks, in: K. Chaudhuri, R. Salakhutdinov (Eds.), Proceedings of the 36th International Conference on Machine Learning, vol. 97 of Proceedings of Machine Learning Research, PMLR, 2019, pp. 5301–5310. doi: 10.48550/arXiv.1806.08734.
– reference: (Last accessed: Feb 28, 2021) (2020).
– reference: R. Caruana, Multitask Learning, Machine Learningdoi: 10.1023/A:1007379606734.
– reference: A. Zhang, H. Wang, S. Li, Y. Cui, Z. Liu, G. Yang, J. Hu, Transfer learning with deep recurrent neural networks for remaining useful life estimation, Applied Sciences (Switzerland) 8 (12). doi: 10.3390/app8122416.
– volume: 25
  start-page: 118
  year: 2018
  end-page: 125
  ident: b0025
  article-title: On the importance of combining “the new with “the old – one important prerequisite for maintenance in industry 4.0
  publication-title: Proc. Manuf.
– reference: B. Mildenhall, P.P. Srinivasan, M. Tancik, J.T. Barron, R. Ramamoorthi, R. Ng, Nerf: Representing scenes as neural radiance fields for view synthesis, in: A. Vedaldi, H. Bischof, T. Brox, J.M. Frahm (Eds.), Computer Vision – ECCV 2020, Springer International Publishing, Cham, 2020, pp. 405–421. doi: 10.1007/978-3-030-58452-8_24.
– start-page: 1
  year: 2022
  end-page: 14
  ident: b0155
  article-title: Remaining useful life prediction with partial sensor malfunctions using deep adversarial networks
  publication-title: IEEE/CAA J. Autom. Sin.
– start-page: 599
  year: 2012
  end-page: 619
  ident: b0130
  article-title: A Practical Guide to Training Restricted Boltzmann Machines
– reference: D. Giordano, D. Gagar, Fifth european conference of the prognostics and health management society 2020 data challenge,
– volume: 104
  start-page: 799
  year: 2018
  end-page: 834
  ident: b0030
  article-title: Machinery health prognostics: A systematic review from data acquisition to RUL prediction
  publication-title: Mech. Syst. Signal Process.
– reference: P. Malhotra, V. Tv, A. Ramakrishnan, G. Anand, L. Vig, P. Agarwal, G. Shroff, Multi-sensor prognostics using an unsupervised health index based on lstm encoder-decoder, 1st SIGKDD Workshop on Machine Learning for Prognostics and Health Management.
– reference: (Last accessed: Mar 25, 2023) (March 2006).
– volume: 230
  year: 2023
  ident: b0065
  article-title: Transfer life prediction of gears by cross-domain health indicator construction and multi-hierarchical long-term memory augmented network
  publication-title: Reliab. Eng. Syst. Safety
– reference: K. Ince, E. Sirkeci, Y. Genc, Remaining useful life prediction for experimental filtration system: A data challenge, in: PHM Society European Conference, 2020, pp. 1–6. doi: 10.36001/phme.2020.v5i1.1317.
– reference: Y. Jiang, Y. Lyu, Y. Wang, P. Wan, Fusion network combined with bidirectional LSTM network and multiscale CNN for useful life estimation LSTM network and multiscale CNN for useful life estimation, 12th International Conference on Advanced Computational Intelligence, ICACI 2020 (2020) 620–627. doi: 10.1109/ICACI49185.2020.9177774.
– year: 2016
  ident: b0085
  article-title: Deep Learning
– volume: 16
  start-page: 862
  year: 2019
  end-page: 880
  ident: b0240
  article-title: A new ensemble residual convolutional neural network for remaining useful life estimation
  publication-title: Math. Biosci. Eng.
– volume: 33
  start-page: 5480
  year: 2022
  end-page: 5491
  ident: b0005
  article-title: Degradation alignment in remaining useful life prediction using deep cycle-consistent learning
  publication-title: IEEE Trans. Neural Networks Learn. Syst.
– reference: K. Cho, B. van Merrienboer, Ç. Gülçehre, F. Bougares, H. Schwenk, Y. Bengio, Learning phrase representations using RNN encoder-decoder for statistical machine translation, CoRR abs/1406.1078, http://arxiv.org/abs/1406.1078.
– reference: X. Li, Q. Ding, J.Q. Sun, Remaining useful life estimation in prognostics using deep convolution neural networks, Reliability Engineering and System Safety 172 (November 2017) (2018) 1–11. doi: 10.1016/j.ress.2017.11.021.
– volume: 183
  start-page: 240
  year: June 2018
  end-page: 251
  ident: b0125
  article-title: Remaining useful life predictions for turbofan engine degradation using semi-supervised deep architecture
  publication-title: Reliab. Eng. Syst. Saf.
– volume: 108
  start-page: 186
  year: 2019
  end-page: 196
  ident: b0135
  article-title: A multimodal and hybrid deep neural network model for Remaining Useful Life estimation
  publication-title: Comput. Ind.
– reference: A. Chaoub, A. Voisin, C. Cerisara, B. Iung, Learning representations with end-to-end models for improved remaining useful life prognostics. https://arxiv.org/abs/2104.05049.
– reference: S.Z. Li, A. Jain (Eds.), Gaussian Mixture Models, Springer US, Boston, MA, 2015, pp. 827–832. doi: 10.1007/978-1-4899-7488-4_196.
– volume: 2015
  start-page: 1
  year: 2015
  end-page: 17
  ident: b0070
  article-title: Prognostics and health management: A review on data driven approaches
  publication-title: Math. Problems Eng.
– volume: 4
  start-page: 1
  year: 2018
  end-page: 12
  ident: b0075
  article-title: Towards online data-driven prognostics system
  publication-title: Complex Intell. Syst.
– year: 2000
  ident: b0215
  article-title: Evolutionary Computation 1: Basic Algorithms and Operators
– volume: 3
  start-page: 1
  year: 2021
  end-page: 17
  ident: b0060
  article-title: Using temporal convolution network for remaining useful lifetime prediction
  publication-title: Eng. Rep.
– reference: A. Ellefsen, E. Bjorlykhaug, V. Æsøy, H. Zhang, An unsupervised reconstruction-based fault detection algorithm for maritime components, IEEE Access PP (2019) 1–1. doi: 10.1109/ACCESS.2019.2895394.
– volume: 44
  start-page: 1
  year: 2020
  end-page: 12
  ident: b0020
  article-title: Iot based predictive maintenance management of medical equipment
  publication-title: J. Med. Syst.
– reference: H. Beirami, D. Calzá, A. Cimatti, M. Islam, M. Roveri, P. Svaizer, A data-driven approach for rul prediction of an experimental filtration system, in: PHM Society European Conference, 2020, pp. 1–7. doi: 10.36001/phme.2020.v5i1.1318.
– volume: 164
  start-page: 74
  year: 2017
  end-page: 83
  ident: b0180
  article-title: Remaining useful life prediction of aircraft engine based on degradation pattern learning
  publication-title: Reliab. Eng. Syst. Safety
– reference: H. Mo, F. Lucca, J. Malacarne, G. Iacca, Multi-Head CNN-LSTM with Prediction Error Analysis for Remaining Useful Life Prediction, Conference of Open Innovation Association, FRUCT 2020-September (2020) 164–171. doi: 10.23919/FRUCT49677.2020.9211058.
– reference: E. Vadala, C. Graham, Downtime costs auto industry $22k/minute – survey, Online,
– reference: A. Saxena, D. Simon, Turbofan Engine Degradation Simulation Data Set,
– start-page: 1
  year: 2022
  end-page: 11
  ident: b0095
  article-title: Dual-thread gated recurrent unit for gear remaining useful life prediction
  publication-title: IEEE Trans. Industr. Inf.
– volume: 9
  start-page: 110255
  year: 2021
  end-page: 110286
  ident: b0035
  article-title: Data-Driven Remaining Useful Life Estimation for Milling Process: Sensors, Algorithms, Datasets, and Future Directions
  publication-title: IEEE Access
– volume: 28
  start-page: 2306
  year: 2017
  end-page: 2318
  ident: b0225
  article-title: Multiobjective Deep Belief Networks Ensemble for Remaining Useful Life Estimation in Prognostics
  publication-title: IEEE Trans. Neural Networks Learn. Syst.
– reference: (Last accessed: Mar 25, 2023) (2008).
– volume: vol. 28
  year: 2015
  ident: b0105
  article-title: Learning structured output representation using deep conditional generative models
  publication-title: Advances in Neural Information Processing Systems
– volume: 27
  start-page: 1447
  year: 2022
  end-page: 1456
  ident: b0110
  article-title: Unsupervised health indicator construction by a novel degradation-trend-constrained variational autoencoder and its applications
  publication-title: IEEE/ASME Trans. Mechatron.
– volume: 29
  start-page: 662
  year: 2016
  end-page: 674
  ident: b0230
  article-title: Remaining useful life estimation for deteriorating systems with time-varying operational conditions and condition-specific failure zones
  publication-title: Chin. J. Aeronaut.
– start-page: 1
  year: 2008
  end-page: 6
  ident: b0175
  article-title: Recurrent neural networks for remaining useful life estimation
  publication-title: 2008 International Conference on Prognostics and Health Management
– volume: 405
  start-page: 442
  year: 1975
  end-page: 451
  ident: b0195
  article-title: Comparison of the predicted and observed secondary structure of t4 phage lysozyme, Biochimica et Biophysica Acta (BBA) - Protein
  publication-title: Structure
– reference: (Last accessed: Mar 25, 2023) (February 2016).
– start-page: 4137
  year: 2020
  end-page: 4146
  ident: b0220
  article-title: Multipath temporal convolutional network for remaining useful life estimation
  publication-title: 2020 IEEE International Conference on Big Data (Big Data)
– start-page: 1
  year: 2022
  ident: 10.1016/j.jestch.2023.101409_b0155
  article-title: Remaining useful life prediction with partial sensor malfunctions using deep adversarial networks
  publication-title: IEEE/CAA J. Autom. Sin.
– ident: 10.1016/j.jestch.2023.101409_b0045
– ident: 10.1016/j.jestch.2023.101409_b0055
  doi: 10.1016/j.ress.2017.11.021
– volume: 25
  start-page: 118
  year: 2018
  ident: 10.1016/j.jestch.2023.101409_b0025
  article-title: On the importance of combining “the new with “the old – one important prerequisite for maintenance in industry 4.0
  publication-title: Proc. Manuf.
– volume: 183
  start-page: 240
  issue: 2019
  year: 2018
  ident: 10.1016/j.jestch.2023.101409_b0125
  article-title: Remaining useful life predictions for turbofan engine degradation using semi-supervised deep architecture
  publication-title: Reliab. Eng. Syst. Saf.
– ident: 10.1016/j.jestch.2023.101409_b0200
  doi: 10.1007/978-1-4899-7488-4_196
– ident: 10.1016/j.jestch.2023.101409_b0210
  doi: 10.1007/978-3-030-58452-8_24
– volume: 18
  start-page: 7230
  issue: 10
  year: 2022
  ident: 10.1016/j.jestch.2023.101409_b0160
  article-title: Spatiotemporally multidifferential processing deep neural network and its application to equipment remaining useful life prediction
  publication-title: IEEE Trans. Industr. Inf.
  doi: 10.1109/TII.2021.3121326
– volume: 164
  start-page: 74
  issue: 457
  year: 2017
  ident: 10.1016/j.jestch.2023.101409_b0180
  article-title: Remaining useful life prediction of aircraft engine based on degradation pattern learning
  publication-title: Reliab. Eng. Syst. Safety
– year: 2016
  ident: 10.1016/j.jestch.2023.101409_b0085
– start-page: 599
  year: 2012
  ident: 10.1016/j.jestch.2023.101409_b0130
– ident: 10.1016/j.jestch.2023.101409_b0165
  doi: 10.1023/A:1007379606734
– ident: 10.1016/j.jestch.2023.101409_b0100
– ident: 10.1016/j.jestch.2023.101409_b0140
  doi: 10.23919/FRUCT49677.2020.9211058
– volume: 230
  year: 2023
  ident: 10.1016/j.jestch.2023.101409_b0065
  article-title: Transfer life prediction of gears by cross-domain health indicator construction and multi-hierarchical long-term memory augmented network
  publication-title: Reliab. Eng. Syst. Safety
  doi: 10.1016/j.ress.2022.108916
– volume: 4
  start-page: 1
  year: 2018
  ident: 10.1016/j.jestch.2023.101409_b0075
  article-title: Towards online data-driven prognostics system
  publication-title: Complex Intell. Syst.
  doi: 10.1007/s40747-018-0082-z
– ident: 10.1016/j.jestch.2023.101409_b0010
– volume: 405
  start-page: 442
  issue: 2
  year: 1975
  ident: 10.1016/j.jestch.2023.101409_b0195
  article-title: Comparison of the predicted and observed secondary structure of t4 phage lysozyme, Biochimica et Biophysica Acta (BBA) - Protein
  publication-title: Structure
– ident: 10.1016/j.jestch.2023.101409_b0120
  doi: 10.1109/ACCESS.2019.2895394
– volume: vol. 28
  year: 2015
  ident: 10.1016/j.jestch.2023.101409_b0105
  article-title: Learning structured output representation using deep conditional generative models
– volume: 27
  start-page: 1447
  issue: 3
  year: 2022
  ident: 10.1016/j.jestch.2023.101409_b0110
  article-title: Unsupervised health indicator construction by a novel degradation-trend-constrained variational autoencoder and its applications
  publication-title: IEEE/ASME Trans. Mechatron.
  doi: 10.1109/TMECH.2021.3098737
– ident: 10.1016/j.jestch.2023.101409_b0235
  doi: 10.36001/phme.2020.v5i1.1317
– start-page: 1
  year: 2008
  ident: 10.1016/j.jestch.2023.101409_b0175
  article-title: Recurrent neural networks for remaining useful life estimation
  publication-title: 2008 International Conference on Prognostics and Health Management
– volume: 28
  start-page: 2306
  issue: 10
  year: 2017
  ident: 10.1016/j.jestch.2023.101409_b0225
  article-title: Multiobjective Deep Belief Networks Ensemble for Remaining Useful Life Estimation in Prognostics
  publication-title: IEEE Trans. Neural Networks Learn. Syst.
  doi: 10.1109/TNNLS.2016.2582798
– ident: 10.1016/j.jestch.2023.101409_b0090
– ident: 10.1016/j.jestch.2023.101409_b0205
– volume: 44
  start-page: 1
  issue: 4
  year: 2020
  ident: 10.1016/j.jestch.2023.101409_b0020
  article-title: Iot based predictive maintenance management of medical equipment
  publication-title: J. Med. Syst.
  doi: 10.1007/s10916-020-1534-8
– volume: 218
  year: 2022
  ident: 10.1016/j.jestch.2023.101409_b0040
  article-title: Prognostics and health management (phm): Where are we and where do we (need to) go in theory and practice
  publication-title: Reliab. Eng. Syst. Safety
  doi: 10.1016/j.ress.2021.108119
– volume: 29
  start-page: 662
  issue: 3
  year: 2016
  ident: 10.1016/j.jestch.2023.101409_b0230
  article-title: Remaining useful life estimation for deteriorating systems with time-varying operational conditions and condition-specific failure zones
  publication-title: Chin. J. Aeronaut.
  doi: 10.1016/j.cja.2016.04.007
– volume: 104
  start-page: 799
  year: 2018
  ident: 10.1016/j.jestch.2023.101409_b0030
  article-title: Machinery health prognostics: A systematic review from data acquisition to RUL prediction
  publication-title: Mech. Syst. Signal Process.
  doi: 10.1016/j.ymssp.2017.11.016
– ident: 10.1016/j.jestch.2023.101409_b0050
– start-page: 4137
  year: 2020
  ident: 10.1016/j.jestch.2023.101409_b0220
  article-title: Multipath temporal convolutional network for remaining useful life estimation
  publication-title: 2020 IEEE International Conference on Big Data (Big Data)
  doi: 10.1109/BigData50022.2020.9377816
– ident: 10.1016/j.jestch.2023.101409_b0145
  doi: 10.1109/ICACI49185.2020.9177774
– volume: 9
  start-page: 110255
  year: 2021
  ident: 10.1016/j.jestch.2023.101409_b0035
  article-title: Data-Driven Remaining Useful Life Estimation for Milling Process: Sensors, Algorithms, Datasets, and Future Directions
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2021.3101284
– ident: 10.1016/j.jestch.2023.101409_b0190
  doi: 10.3390/app8122416
– volume: 3
  start-page: 1
  issue: 3
  year: 2021
  ident: 10.1016/j.jestch.2023.101409_b0060
  article-title: Using temporal convolution network for remaining useful lifetime prediction
  publication-title: Eng. Rep.
– volume: 16
  start-page: 862
  issue: 2
  year: 2019
  ident: 10.1016/j.jestch.2023.101409_b0240
  article-title: A new ensemble residual convolutional neural network for remaining useful life estimation
  publication-title: Math. Biosci. Eng.
  doi: 10.3934/mbe.2019040
– volume: 107
  start-page: 241
  year: 2018
  ident: 10.1016/j.jestch.2023.101409_b0080
  article-title: A review on the application of deep learning in system health management
  publication-title: Mech. Syst. Signal Process.
  doi: 10.1016/j.ymssp.2017.11.024
– ident: 10.1016/j.jestch.2023.101409_b0015
– volume: 7
  start-page: 71563
  year: 2019
  ident: 10.1016/j.jestch.2023.101409_b0115
  article-title: Validation of Data-Driven Labeling Approaches Using a Novel Deep Network Structure for Remaining Useful Life Predictions
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2019.2920297
– volume: 108
  start-page: 186
  year: 2019
  ident: 10.1016/j.jestch.2023.101409_b0135
  article-title: A multimodal and hybrid deep neural network model for Remaining Useful Life estimation
  publication-title: Comput. Ind.
  doi: 10.1016/j.compind.2019.02.004
– start-page: 1
  year: 2022
  ident: 10.1016/j.jestch.2023.101409_b0095
  article-title: Dual-thread gated recurrent unit for gear remaining useful life prediction
  publication-title: IEEE Trans. Industr. Inf.
– ident: 10.1016/j.jestch.2023.101409_b0185
– ident: 10.1016/j.jestch.2023.101409_b0170
  doi: 10.36001/phme.2020.v5i1.1318
– ident: 10.1016/j.jestch.2023.101409_b0150
– year: 2000
  ident: 10.1016/j.jestch.2023.101409_b0215
– volume: 2015
  start-page: 1
  year: 2015
  ident: 10.1016/j.jestch.2023.101409_b0070
  article-title: Prognostics and health management: A review on data driven approaches
  publication-title: Math. Problems Eng.
  doi: 10.1155/2015/793161
– volume: 33
  start-page: 5480
  issue: 10
  year: 2022
  ident: 10.1016/j.jestch.2023.101409_b0005
  article-title: Degradation alignment in remaining useful life prediction using deep cycle-consistent learning
  publication-title: IEEE Trans. Neural Networks Learn. Syst.
  doi: 10.1109/TNNLS.2021.3070840
SSID ssj0001921156
Score 2.2952254
Snippet •We introduce a joint autoencoder and regressor architecture for remaining useful life prediction, and demonstrate the effectiveness of this model on two...
Ubiquitous availability of IoT technologies allows processing of large amounts of data to improve prognostics tasks in industrial applications. One such...
SourceID doaj
crossref
elsevier
SourceType Open Website
Enrichment Source
Index Database
Publisher
StartPage 101409
SubjectTerms C-MAPSS
Deep learning
Fault detection
Predictive maintenance
Remaining useful life
Title Joint autoencoder-regressor deep neural network for remaining useful life prediction
URI https://dx.doi.org/10.1016/j.jestch.2023.101409
https://doaj.org/article/106774661e1e4e24996aeb79f12f5e59
Volume 41
WOSCitedRecordID wos001026525500001&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: PRVAON
  databaseName: Directory of Open Access Journals
  customDbUrl:
  eissn: 2215-0986
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001921156
  issn: 2215-0986
  databaseCode: DOA
  dateStart: 20140101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2215-0986
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001921156
  issn: 2215-0986
  databaseCode: M~E
  dateStart: 20140101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT8QgECbGeNCD8RnXVzh4JbZASzmq0RijxoMabw0tQ7KbtbupXY_-dgfomp704qUHQqEMU-abMPMNIWeCV5k1rmCFkRmTlcVzUCrNlEuKCv0D40J-xeu9enws3t7006DUl48Ji_TAUXDngeJMohWBFCSgs6BzA5XSLuUugyyk7iVKD5ypScQtCHVCZTm0aSzRRb7MmwvBXRM8csNdBBe-Sfp4xIFdCvT9A_M0MDk3W2Szx4r0In7jNlmBZodsDBgEd8nz3WzcdNQsuplnpLTQshaCCz1rqQWYU09YiYM0MdybIkalLbzHuhB08QFuMaXTsQM6b_2djd-nPfJyc_18dcv6QgmslmnRsZpnlbS4CsicljlYXDQCD1k5g_-jBeu4K2yaGgWIPxBiCMh1LitRgbA6q8U-WW1mDRwQKkBmKrHc5bWQVlnDleEOeILAqKi1HRGxFFNZ9yzivpjFtFyGi03KKNzSC7eMwh0R9vPWPLJo_NH_0u_AT1_PgR0aUDPKXjPKvzRjRNRy_8oeTkSYgEONf53-8D-mPyLrfsgYHHlMVrt2ASdkrf7sxh_taVBXfD58XX8DSwTuEg
linkProvider Directory of Open Access Journals
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=Joint+autoencoder-regressor+deep+neural+network+for+remaining+useful+life+prediction&rft.jtitle=Engineering+science+and+technology%2C+an+international+journal&rft.au=%C4%B0nce%2C+K%C3%BCr%C5%9Fat&rft.au=Genc%2C+Yakup&rft.date=2023-05-01&rft.issn=2215-0986&rft.eissn=2215-0986&rft.volume=41&rft.spage=101409&rft_id=info:doi/10.1016%2Fj.jestch.2023.101409&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_jestch_2023_101409
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2215-0986&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2215-0986&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2215-0986&client=summon