Show simple item record

dc.contributor.author
Simpson, Thomas
dc.contributor.author
Dervilis, Nikolaos
dc.contributor.author
Chatzi, Eleni
dc.date.accessioned
2021-07-30T08:00:40Z
dc.date.available
2021-07-30T02:43:20Z
dc.date.available
2021-07-30T08:00:40Z
dc.date.issued
2021-10
dc.identifier.other
10.1061/(ASCE)EM.1943-7889.0001971
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/498486
dc.description.abstract
In analyzing and assessing the condition of dynamical systems, it is necessary to account for nonlinearity. Recent advances in computation have rendered previously computationally infeasible analyses readily executable on common computer hardware. However, in certain use cases, such as uncertainty quantification or high precision real-time simulation, the computational cost remains a challenge. This necessitates the adoption of reduced-order modeling methods, which can reduce the computational toll of such nonlinear analyses. In this work, we propose a reduction scheme relying on the exploitation of an autoencoder as means to infer a latent space from output-only response data. This latent space, which in essence approximates the system’s nonlinear normal modes (NNMs), serves as an invertible reduction basis for the nonlinear system. The proposed machine learning framework is then complemented via the use of long short-term memory (LSTM) networks in the reduced space. These are used for creating a nonlinear reduced-order model (ROM) of the system, able to recreate the full system’s dynamic response under a known driving input. © 2021 American Society of Civil Engineers
en_US
dc.language.iso
en
en_US
dc.publisher
American Society of Civil Engineers
en_US
dc.subject
Nonlinear
en_US
dc.subject
Reduced order modeling
en_US
dc.subject
Machine learning
en_US
dc.subject
LSTM
en_US
dc.subject
Autoencoder
en_US
dc.title
Machine Learning Approach to Model Order Reduction of Nonlinear Systems via Autoencoder and LSTM Networks
en_US
dc.type
Journal Article
dc.date.published
2021-07-19
ethz.journal.title
Journal of Engineering Mechanics
ethz.journal.volume
147
en_US
ethz.journal.issue
10
en_US
ethz.pages.start
04021061
en_US
ethz.size
22 p.
en_US
ethz.grant
Dynamic virtualisation: modelling performance of engineering structures
en_US
ethz.identifier.scopus
ethz.publication.place
Reston, VA
en_US
ethz.publication.status
published
en_US
ethz.grant.agreementno
764547
ethz.grant.fundername
EC
ethz.grant.funderDoi
10.13039/501100000780
ethz.grant.program
H2020
ethz.date.deposited
2021-07-30T02:43:23Z
ethz.source
SCOPUS
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2021-07-30T08:00:45Z
ethz.rosetta.lastUpdated
2021-07-30T08:00:45Z
ethz.rosetta.exportRequired
true
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Machine%20Learning%20Approach%20to%20Model%20Order%20Reduction%20of%20Nonlinear%20Systems%20via%20Autoencoder%20and%20LSTM%20Networks&rft.jtitle=Journal%20of%20Engineering%20Mechanics&rft.date=2021-10&rft.volume=147&rft.issue=10&rft.spage=04021061&rft.au=Simpson,%20Thomas&Dervilis,%20Nikolaos&Chatzi,%20Eleni&rft.genre=article&rft_id=info:doi/10.1061/(ASCE)EM.1943-7889.0001971&
 Search print copy at ETH Library

Files in this item

FilesSizeFormatOpen in viewer

There are no files associated with this item.

Publication type

Show simple item record