Remaining Useful Life Estimation for Engineered Systems Operating under Uncertainty with Causal GraphNets
dc.contributor.author
Mylonas, Charilaos
dc.contributor.author
Chatzi, Eleni
dc.date.accessioned
2022-02-07T13:51:12Z
dc.date.available
2022-01-31T15:51:42Z
dc.date.available
2022-02-07T09:03:59Z
dc.date.available
2022-02-07T13:51:12Z
dc.date.issued
2021-09-22
dc.identifier.issn
1424-8220
dc.identifier.other
10.3390/s21196325
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/530182
dc.identifier.doi
10.3929/ethz-b-000530182
dc.description.abstract
In this work, a novel approach, termed GNN-tCNN, is presented for the construction and training of Remaining Useful Life (RUL) models. The method exploits Graph Neural Networks (GNNs) and deals with the problem of efficiently learning from time series with non-equidistant observations, which may span multiple temporal scales. The efficacy of the method is demonstrated on a simulated stochastic degradation dataset and on a real-world accelerated life testing dataset for ball-bearings. The proposed method learns a model that describes the evolution of the system implicitly rather than at the raw observation level and is based on message-passing neural networks, which encode the irregularly sampled causal structure. The proposed approach is compared to a recurrent network with a temporal convolutional feature extractor head (LSTM-tCNN), which forms a viable alternative for the problem considered. Finally, by taking advantage of recent advances in the computation of reparametrization gradients for learning probability distributions, a simple, yet efficient, technique is employed for representing prediction uncertainty as a gamma distribution over RUL predictions.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
MDPI
en_US
dc.rights.uri
http://creativecommons.org/licenses/by/4.0/
dc.title
Remaining Useful Life Estimation for Engineered Systems Operating under Uncertainty with Causal GraphNets
en_US
dc.type
Journal Article
dc.rights.license
Creative Commons Attribution 4.0 International
ethz.journal.title
Sensors
ethz.journal.volume
21
en_US
ethz.journal.issue
19
en_US
ethz.pages.start
6325
en_US
ethz.size
23 p.
en_US
ethz.version.deposit
publishedVersion
en_US
ethz.grant
Smart Monitoring, Inspection and Life-Cycle Assessment of Wind Turbines
en_US
ethz.identifier.scopus
ethz.publication.place
Basel
en_US
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.::02605 - Institut für Baustatik u. Konstruktion / Institute of Structural Engineering::03890 - Chatzi, Eleni / Chatzi, Eleni
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.::02605 - Institut für Baustatik u. Konstruktion / Institute of Structural Engineering::03890 - Chatzi, Eleni / Chatzi, Eleni
en_US
ethz.grant.agreementno
679843
ethz.grant.fundername
EC
ethz.grant.funderDoi
10.13039/501100000780
ethz.grant.program
H2020
ethz.date.deposited
2022-01-31T15:51:52Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2022-02-07T13:51:20Z
ethz.rosetta.lastUpdated
2024-02-02T16:17:17Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Remaining%20Useful%20Life%20Estimation%20for%20Engineered%20Systems%20Operating%20under%20Uncertainty%20with%20Causal%20GraphNets&rft.jtitle=Sensors&rft.date=2021-09-22&rft.volume=21&rft.issue=19&rft.spage=6325&rft.issn=1424-8220&rft.au=Mylonas,%20Charilaos&Chatzi,%20Eleni&rft.genre=article&rft_id=info:doi/10.3390/s21196325&
Files in this item
Publication type
-
Journal Article [130870]