Show simple item record

dc.contributor.author
Moustapha, Maliki
dc.contributor.author
Sudret, Bruno
dc.contributor.editor
Papadrakakis, Manolis
dc.contributor.editor
Papadopoulos, Vissarion
dc.contributor.editor
Stefanou, George
dc.date.accessioned
2020-01-31T12:49:17Z
dc.date.available
2019-11-25T12:57:00Z
dc.date.available
2019-11-25T13:27:20Z
dc.date.available
2020-01-31T12:49:17Z
dc.date.issued
2019-10
dc.identifier.isbn
978‐618‐82844‐9‐4
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/380278
dc.identifier.doi
10.3929/ethz-b-000380278
dc.description.abstract
Surrogate modelling has become an important topic in the field of uncertainty quantification as it allows for the solution of otherwise computationally intractable problems. The basic idea in surrogate modelling consists in replacing an expensive-to-evaluate black-box function by a cheap proxy. Various surrogate modelling techniques have been developed in the past decade. They always assume accommodating properties of the underlying model such as regularity and smoothness. However such assumptions may not hold for some models in civil or mechanical engineering applications, e.g., due to the presence of snap-through instability patterns or bifurcations in the physical behavior of the system under interest. In such cases, building a single surrogate that accounts for all possible model scenarios leads to poor prediction capability. To overcome such a hurdle, this paper investigates an approach where the surrogate model is built in two stages. In the first stage, the different behaviors of the system are identified using either expert knowledge or unsupervised learning, i.e. clustering. Then a classifier of such behaviors is built, using support vector machines. In the second stage, a regression-based surrogate model is built for each of the identified classes of behaviors. For any new point, the prediction is therefore made in two stages: first predicting the class and then estimating the response using an appropriate recombination of the surrogate models. The approach is validated on two examples, showing its effectiveness with respect to using a single surrogate model in the entire space.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
Institute of Structural Analysis and Antiseismic Research, National Technical University of Athens
en_US
dc.rights.uri
http://rightsstatements.org/page/InC-NC/1.0/
dc.subject
Surrogate modelling
en_US
dc.subject
Kriging
en_US
dc.subject
Support Vector Machines
en_US
dc.title
A two-stage surrogate modelling approach for the approximation of models with non-smooth outputs
en_US
dc.type
Conference Paper
dc.rights.license
In Copyright - Non-Commercial Use Permitted
ethz.book.title
UNCECOMP 2019 Proceedings of the 3rd International Conference on Uncertainty Quatification in Computational Sciences and Engineering
en_US
ethz.pages.start
357
en_US
ethz.pages.end
366
en_US
ethz.size
12 p.
en_US
ethz.version.deposit
updatedVersion
en_US
ethz.event
3rd International Conference on Uncertainty Quantification in Computational Sciences and Engineering (UNCECOMP 2019)
en_US
ethz.event.location
Hersonissos, Greece
en_US
ethz.event.date
June 24-26, 2019
en_US
ethz.notes
Conference lecture held on June 26, 2019
en_US
ethz.publication.place
Athens
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::03962 - Sudret, Bruno / Sudret, Bruno
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::03962 - Sudret, Bruno / Sudret, Bruno
en_US
ethz.relation.isSupplementTo
http://hdl.handle.net/20.500.11850/352847
ethz.date.deposited
2019-11-25T12:57:11Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2019-11-25T13:27:36Z
ethz.rosetta.lastUpdated
2020-01-31T12:49:28Z
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=A%20two-stage%20surrogate%20modelling%20approach%20for%20the%20approximation%20of%20models%20with%20non-smooth%20outputs&rft.date=2019-10&rft.spage=357&rft.epage=366&rft.au=Moustapha,%20Maliki&Sudret,%20Bruno&rft.isbn=978%E2%80%90618%E2%80%9082844%E2%80%909%E2%80%904&rft.genre=proceeding&rft_id=info:doi/978%E2%80%90618%E2%80%9082844%E2%80%909%E2%80%904&rft.btitle=UNCECOMP%202019%20Proceedings%20of%20the%203rd%20International%20Conference%20on%20%20Uncertainty%20Quatification%20in%20Computational%20Sciences%20and%20Engineering
 Search via SFX

Files in this item

Thumbnail

Publication type

Show simple item record