<div class="csl-bib-body">
<div class="csl-entry">Kovacs, A., Exl, L., Kornell, A., Fischbacher, J., Hovorka, M., Gusenbauer, M., Breth, L., Oezelt, H., Praetorius, D., Süss, D., & Schrefl, T. (2022). Magnetostatics and micromagnetics with physics informed neural networks. <i>Journal of Magnetism and Magnetic Materials</i>, <i>548</i>, Article 168951. https://doi.org/10.1016/j.jmmm.2021.168951</div>
</div>
-
dc.identifier.issn
0304-8853
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/136652
-
dc.description.abstract
Partial differential equations and variational problems can be solved with physics informed neural networks (PINNs). The unknown field is approximated with neural networks. Minimizing the residuals of the static Maxwell equation at collocation points or the magnetostatic energy, the weights of the neural network are adjusted so that the neural network solution approximates the magnetic vector potential. This way, the magnetic flux density for a given magnetization distribution can be estimated. With the magnetization as an additional unknown, inverse magnetostatic problems can be solved. Augmenting the magnetostatic energy with additional energy terms, micromagnetic problems can be solved. We demonstrate the use of physics informed neural networks for solving magnetostatic problems, computing the magnetization for inverse problems, and calculating the demagnetization curves for two-dimensional geometries.
en
dc.language.iso
en
-
dc.publisher
ELSEVIER
-
dc.relation.ispartof
Journal of Magnetism and Magnetic Materials
-
dc.subject
Condensed Matter Physics
en
dc.subject
Electronic, Optical and Magnetic Materials
en
dc.title
Magnetostatics and micromagnetics with physics informed neural networks
en
dc.type
Artikel
de
dc.type
Article
en
dc.type.category
Original Research Article
-
tuw.container.volume
548
-
tuw.journal.peerreviewed
true
-
tuw.peerreviewed
true
-
tuw.researchTopic.id
C6
-
tuw.researchTopic.id
C1
-
tuw.researchTopic.name
Modelling and Simulation
-
tuw.researchTopic.name
Computational Materials Science
-
tuw.researchTopic.value
50
-
tuw.researchTopic.value
50
-
dcterms.isPartOf.title
Journal of Magnetism and Magnetic Materials
-
tuw.publication.orgunit
E101-02 - Forschungsbereich Numerik
-
tuw.publisher.doi
10.1016/j.jmmm.2021.168951
-
dc.identifier.articleid
168951
-
dc.identifier.eissn
1873-4766
-
dc.description.numberOfPages
12
-
tuw.author.orcid
0000-0002-5343-6938
-
tuw.author.orcid
0000-0002-0815-5379
-
tuw.author.orcid
0000-0002-3540-3964
-
tuw.author.orcid
0000-0002-1977-9830
-
wb.sci
true
-
wb.sciencebranch
Mathematik
-
wb.sciencebranch.oefos
1010
-
wb.facultyfocus
Analysis und Scientific Computing
de
wb.facultyfocus
Analysis and Scientific Computing
en
wb.facultyfocus.faculty
E100
-
item.fulltext
no Fulltext
-
item.openairecristype
http://purl.org/coar/resource_type/c_2df8fbb1
-
item.languageiso639-1
en
-
item.cerifentitytype
Publications
-
item.openairetype
research article
-
item.grantfulltext
none
-
crisitem.author.dept
TU Wien
-
crisitem.author.dept
E101 - Institut für Analysis und Scientific Computing
-
crisitem.author.dept
E138 - Institut für Festkörperphysik
-
crisitem.author.dept
E101 - Institut für Analysis und Scientific Computing