Show simple item record

dc.contributor.author
Heidenreich, Julian N.
dc.contributor.author
Gorji, Maysam B.
dc.contributor.author
Mohr, Dirk
dc.date.accessioned
2023-03-22T08:29:12Z
dc.date.available
2023-01-16T12:48:54Z
dc.date.available
2023-02-08T16:27:13Z
dc.date.available
2023-03-22T08:29:12Z
dc.date.issued
2023-04
dc.identifier.issn
0749-6419
dc.identifier.issn
1879-2154
dc.identifier.other
10.1016/j.ijplas.2022.103506
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/592684
dc.description.abstract
The use of micromechanics in conjunction with homogenization theory allows for the prediction of the effective mechanical properties of materials based on microstructural information. The geometrical features of microstructures are often summarized in the form of a multi-dimensional image that may contain information such as grain morphology and grain orientations. Here, an attempt is made to encode microstructural information contained in images through convolutional neural networks (CNN). In particular, we pose the problem of predicting the yield surfaces of porous media based on images of their unit cell. It is shown that an encoder composed of two parallel CNN strands is able to reduce the geometrical information stored in 100 × 100 pixel images of perforated microstructures to ten characteristic features. Furthermore, a fully-connected neural network model with multiplicative layers is introduced to predict the effective yield surfaces based on the encoded geometrical information. The result is a computationally-efficient CNN-FCNN model that is able to replicate the effective yield surface predictions of a detailed FE-based unit cell model. Based on this successful proof of concept, it may be envisioned to train CNNs based on the results from crystal plasticity models as well as experimental data on real materials to obtain structure-property models for the design of optimization of polycrystalline materials.
en_US
dc.language.iso
en
en_US
dc.publisher
Elsevier
en_US
dc.subject
Artificial intelligence
en_US
dc.subject
fully connected neural network
en_US
dc.subject
convolutional neural network
en_US
dc.subject
plasticity
en_US
dc.subject
anisotropy
en_US
dc.subject
homogenization
en_US
dc.title
Modeling Structure-Property Relationships with Convolutional Neural Networks: Yield Surface Prediction Based on Microstructure Images
en_US
dc.type
Journal Article
dc.date.published
2022-12-22
ethz.journal.title
International Journal of Plasticity
ethz.journal.volume
163
en_US
ethz.journal.abbreviated
Int. J. Plast.
ethz.pages.start
103506
en_US
ethz.size
25 p.
en_US
ethz.identifier.wos
ethz.identifier.scopus
ethz.publication.place
Amsterdam
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02130 - Dep. Maschinenbau und Verfahrenstechnik / Dep. of Mechanical and Process Eng.::02622 - Institut für virtuelle Produktion / Institute of Virtual Manufacturing::09473 - Mohr, Dirk / Mohr, Dirk
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02130 - Dep. Maschinenbau und Verfahrenstechnik / Dep. of Mechanical and Process Eng.::02622 - Institut für virtuelle Produktion / Institute of Virtual Manufacturing::09473 - Mohr, Dirk / Mohr, Dirk
en_US
ethz.date.deposited
2023-01-16T12:48:54Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2023-03-22T08:29:13Z
ethz.rosetta.lastUpdated
2024-02-02T21:15:31Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Modeling%20Structure-Property%20Relationships%20with%20Convolutional%20Neural%20Networks:%20Yield%20Surface%20Prediction%20Based%20on%20Microstructure%20Images&rft.jtitle=International%20Journal%20of%20Plasticity&rft.date=2023-04&rft.volume=163&rft.spage=103506&rft.issn=0749-6419&1879-2154&rft.au=Heidenreich,%20Julian%20N.&Gorji,%20Maysam%20B.&Mohr,%20Dirk&rft.genre=article&rft_id=info:doi/10.1016/j.ijplas.2022.103506&
 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