Klein, Dominik K. ; Roth, Fabian J. ; Valizadeh, Iman ; Weeger, Oliver (2024)
Parametrized polyconvex hyperelasticity with physics-augmented neural networks.
In: Data-Centric Engineering, 2023, 4
doi: 10.26083/tuprints-00026472
Artikel, Zweitveröffentlichung, Verlagsversion
 | Es ist eine neuere Version dieses Eintrags verfügbar. |
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: | 2024 |
| Autor(en): | Klein, Dominik K. ; Roth, Fabian J. ; Valizadeh, Iman ; Weeger, Oliver |
| Art des Eintrags: | Zweitveröffentlichung |
| Titel: | Parametrized polyconvex hyperelasticity with physics-augmented neural networks |
| Sprache: | Englisch |
| Publikationsjahr: | 5 Februar 2024 |
| Ort: | Darmstadt |
| Publikationsdatum der Erstveröffentlichung: | 2023 |
| Ort der Erstveröffentlichung: | Cambridge |
| Verlag: | Cambridge University Press |
| Titel der Zeitschrift, Zeitung oder Schriftenreihe: | Data-Centric Engineering |
| Jahrgang/Volume einer Zeitschrift: | 4 |
| Kollation: | 22 Seiten |
| DOI: | 10.26083/tuprints-00026472 |
| URL / URN: | https://tuprints.ulb.tu-darmstadt.de/26472 |
| Zugehörige Links: | |
| Herkunft: | Zweitveröffentlichungsservice |
| 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. |
| Freie Schlagworte: | constitutive modeling, hyperelasticity, parametrized material, partially input convex neural networks, physicsaugmented neural networks |
| ID-Nummer: | Artikel-ID: e25 |
| Status: | Verlagsversion |
| URN: | urn:nbn:de:tuda-tuprints-264722 |
| Sachgruppe der Dewey Dezimalklassifikatin (DDC): | 000 Allgemeines, Informatik, Informationswissenschaft > 004 Informatik 600 Technik, Medizin, angewandte Wissenschaften > 620 Ingenieurwissenschaften und Maschinenbau |
| Fachbereich(e)/-gebiet(e): | 16 Fachbereich Maschinenbau 16 Fachbereich Maschinenbau > Fachgebiet Cyber-Physische Simulation (CPS) |
| Hinterlegungsdatum: | 05 Feb 2024 11:02 |
| Letzte Änderung: | 06 Feb 2024 07:14 |
| PPN: | |
| Zugehörige Links: | |
| 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) [Gegenwärtig angezeigt]
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum