Show simple item record

dc.contributor.author
Arias Chao, Manuel
dc.contributor.author
Kulkarni, Chetan
dc.contributor.author
Goebel, Kai
dc.contributor.author
Fink, Olga
dc.date.accessioned
2021-09-20T06:40:13Z
dc.date.available
2021-09-20T06:37:53Z
dc.date.available
2021-09-20T06:40:13Z
dc.date.issued
2022-01
dc.identifier.issn
0951-8320
dc.identifier.other
10.1016/j.ress.2021.107961
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/506035
dc.identifier.doi
10.3929/ethz-b-000506035
dc.description.abstract
Physics-based and data-driven models for remaining useful lifetime (RUL) prediction typically suffer from two major challenges that limit their applicability to complex real-world domains: (1) the incompleteness of physics-based models and (2) the limited representativeness of the training dataset for data-driven models. Combining the advantages of these two approaches while overcoming some of their limitations, we propose a novel hybrid framework for fusing the information from physics-based performance models with deep learning algorithms for prognostics of complex safety-critical systems. In the proposed framework, we use physicsbased performance models to infer unobservable model parameters related to a system’s components health by solving a calibration problem. These parameters are subsequently combined with sensor readings and used as input to a deep neural network, thereby generating a data-driven prognostics model with physics-augmented features. The performance of the hybrid framework is evaluated on an extensive case study comprising runto-failure degradation trajectories from a fleet of nine turbofan engines under real flight conditions. The experimental results show that the hybrid framework outperforms purely data-driven approaches by extending the prediction horizon by nearly 127%. Furthermore, it requires less training data and is less sensitive to the limited representativeness of the dataset as compared to purely data-driven approaches. Furthermore, we demonstrated the feasibility of the proposed framework on the original CMAPSS dataset, thereby confirming its superior performance.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
Elsevier
dc.rights.uri
http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subject
prognostics
en_US
dc.subject
deep learning
en_US
dc.subject
hybrid model
en_US
dc.subject
CMAPSS
en_US
dc.title
Fusing physics-based and deep learning models for prognostics
en_US
dc.type
Journal Article
dc.rights.license
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
dc.date.published
2021-09-17
ethz.journal.title
Reliability Engineering & System Safety
ethz.journal.volume
217
en_US
ethz.journal.abbreviated
Reliab. eng. syst. saf.
ethz.pages.start
107961
en_US
ethz.size
18 p.
en_US
ethz.version.deposit
publishedVersion
en_US
ethz.grant
Data-Driven Intelligent Predictive Maintenance of Industrial Assets
en_US
ethz.identifier.wos
ethz.identifier.scopus
ethz.publication.place
Amsterdam
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02115 - Dep. Bau, Umwelt und Geomatik / Dep. of Civil, Env. and Geomatic Eng.::02604 - Inst. für Bau- & Infrastrukturmanagement / Inst. Construction&Infrastructure Manag.::09642 - Fink, Olga (ehemalig) / Fink, Olga (former)
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02115 - Dep. Bau, Umwelt und Geomatik / Dep. of Civil, Env. and Geomatic Eng.::02604 - Inst. für Bau- & Infrastrukturmanagement / Inst. Construction&Infrastructure Manag.::09642 - Fink, Olga (ehemalig) / Fink, Olga (former)
en_US
ethz.grant.agreementno
176878
ethz.grant.fundername
SNF
ethz.grant.funderDoi
10.13039/501100001711
ethz.grant.program
SNF-Förderungsprofessuren Stufe 2
ethz.relation.isCompiledBy
10.3929/ethz-b-000517153
ethz.date.deposited
2021-09-20T06:38:02Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2021-09-20T06:40:19Z
ethz.rosetta.lastUpdated
2024-02-02T14:42:11Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Fusing%20physics-based%20and%20deep%20learning%20models%20for%20prognostics&rft.jtitle=Reliability%20Engineering%20&%20System%20Safety&rft.date=2022-01&rft.volume=217&rft.spage=107961&rft.issn=0951-8320&rft.au=Arias%20Chao,%20Manuel&Kulkarni,%20Chetan&Goebel,%20Kai&Fink,%20Olga&rft.genre=article&rft_id=info:doi/10.1016/j.ress.2021.107961&
 Search print copy at ETH Library

Files in this item

Thumbnail

Publication type

Show simple item record