Klein, Dominik K. ; Roth, Fabian J. ; Valizadeh, Iman ; Weeger, Oliver (2023)
Parametrized polyconvex hyperelasticity with physics-augmented neural networks.
In: Data-Centric Engineering, 4
doi: 10.1017/dce.2023.21
Artikel, Bibliographie
Dies ist die neueste Version dieses Eintrags.
Kurzbeschreibung (Abstract)
In the present work, neural networks are applied to formulate parametrized hyperelastic constitutive models. The models fulfill all common mechanical conditions of hyperelasticity by construction. In particular, partially input convex neural network (pICNN) architectures are applied based on feed-forward neural networks. Receiving two different sets of input arguments, pICNNs are convex in one of them, while for the other, they represent arbitrary relationships which are not necessarily convex. In this way, the model can fulfill convexity conditions stemming from mechanical considerations without being too restrictive on the functional relationship in additional parameters, which may not necessarily be convex. Two different models are introduced, where one can represent arbitrary functional relationships in the additional parameters, while the other is monotonic in the additional parameters. As a first proof of concept, the model is calibrated to data generated with two differently parametrized analytical potentials, whereby three different pICNN architectures are investigated. In all cases, the proposed model shows excellent performance.
| Typ des Eintrags: | Artikel |
|---|---|
| Erschienen: | 2023 |
| Autor(en): | Klein, Dominik K. ; Roth, Fabian J. ; Valizadeh, Iman ; Weeger, Oliver |
| Art des Eintrags: | Bibliographie |
| Titel: | Parametrized polyconvex hyperelasticity with physics-augmented neural networks |
| Sprache: | Englisch |
| Publikationsjahr: | 3 November 2023 |
| Verlag: | Cambridge University Press |
| Titel der Zeitschrift, Zeitung oder Schriftenreihe: | Data-Centric Engineering |
| Jahrgang/Volume einer Zeitschrift: | 4 |
| DOI: | 10.1017/dce.2023.21 |
| Zugehörige Links: | |
| Kurzbeschreibung (Abstract): | In the present work, neural networks are applied to formulate parametrized hyperelastic constitutive models. The models fulfill all common mechanical conditions of hyperelasticity by construction. In particular, partially input convex neural network (pICNN) architectures are applied based on feed-forward neural networks. Receiving two different sets of input arguments, pICNNs are convex in one of them, while for the other, they represent arbitrary relationships which are not necessarily convex. In this way, the model can fulfill convexity conditions stemming from mechanical considerations without being too restrictive on the functional relationship in additional parameters, which may not necessarily be convex. Two different models are introduced, where one can represent arbitrary functional relationships in the additional parameters, while the other is monotonic in the additional parameters. As a first proof of concept, the model is calibrated to data generated with two differently parametrized analytical potentials, whereby three different pICNN architectures are investigated. In all cases, the proposed model shows excellent performance. |
| Zusätzliche Informationen: | Artikel-ID: e25 |
| Fachbereich(e)/-gebiet(e): | 16 Fachbereich Maschinenbau 16 Fachbereich Maschinenbau > Fachgebiet Cyber-Physische Simulation (CPS) Exzellenzinitiative Exzellenzinitiative > Graduiertenschulen Exzellenzinitiative > Graduiertenschulen > Graduate School of Computational Engineering (CE) |
| Hinterlegungsdatum: | 21 Nov 2023 06:15 |
| Letzte Änderung: | 06 Feb 2024 07:15 |
| PPN: | 513362371 |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
Verfügbare Versionen dieses Eintrags
-
Parametrized polyconvex hyperelasticity with physics-augmented neural networks. (deposited 05 Feb 2024 11:02)
- Parametrized polyconvex hyperelasticity with physics-augmented neural networks. (deposited 21 Nov 2023 06:15) [Gegenwärtig angezeigt]
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum