Fuhg, Jan N. ; Jadoon, Asghar ; Weeger, Oliver ; Seidl, D. Thomas ; Jones, Reese E. (2024)
Polyconvex neural network models of thermoelasticity.
In: Journal of the Mechanics and Physics of Solids, 192
doi: 10.1016/j.jmps.2024.105837
Artikel, Bibliographie
Kurzbeschreibung (Abstract)
Machine-learning function representations such as neural networks have proven to be excellent constructs for constitutive modeling due to their flexibility to represent highly nonlinear data and their ability to incorporate constitutive constraints, which also allows them to generalize well to unseen data. In this work, we extend a polyconvex hyperelastic neural network framework to (isotropic) thermo-hyperelasticity by specifying the thermodynamic and material theoretic requirements for an expansion of the Helmholtz free energy expressed in terms of deformation invariants and temperature. Different formulations which a priori ensure polyconvexity with respect to deformation and concavity with respect to temperature are proposed and discussed. The physics-augmented neural networks are furthermore calibrated with a recently proposed sparsification algorithm that not only aims to fit the training data but also penalizes the number of active parameters, which prevents overfitting in the low data regime and promotes generalization. The performance of the proposed framework is demonstrated on synthetic data, which illustrate the expected thermomechanical phenomena, and existing temperature-dependent uniaxial tension and tension-torsion experimental datasets.
Typ des Eintrags: | Artikel |
---|---|
Erschienen: | 2024 |
Autor(en): | Fuhg, Jan N. ; Jadoon, Asghar ; Weeger, Oliver ; Seidl, D. Thomas ; Jones, Reese E. |
Art des Eintrags: | Bibliographie |
Titel: | Polyconvex neural network models of thermoelasticity |
Sprache: | Englisch |
Publikationsjahr: | 28 August 2024 |
Verlag: | Elsevier |
Titel der Zeitschrift, Zeitung oder Schriftenreihe: | Journal of the Mechanics and Physics of Solids |
Jahrgang/Volume einer Zeitschrift: | 192 |
DOI: | 10.1016/j.jmps.2024.105837 |
Kurzbeschreibung (Abstract): | Machine-learning function representations such as neural networks have proven to be excellent constructs for constitutive modeling due to their flexibility to represent highly nonlinear data and their ability to incorporate constitutive constraints, which also allows them to generalize well to unseen data. In this work, we extend a polyconvex hyperelastic neural network framework to (isotropic) thermo-hyperelasticity by specifying the thermodynamic and material theoretic requirements for an expansion of the Helmholtz free energy expressed in terms of deformation invariants and temperature. Different formulations which a priori ensure polyconvexity with respect to deformation and concavity with respect to temperature are proposed and discussed. The physics-augmented neural networks are furthermore calibrated with a recently proposed sparsification algorithm that not only aims to fit the training data but also penalizes the number of active parameters, which prevents overfitting in the low data regime and promotes generalization. The performance of the proposed framework is demonstrated on synthetic data, which illustrate the expected thermomechanical phenomena, and existing temperature-dependent uniaxial tension and tension-torsion experimental datasets. |
ID-Nummer: | Artikel-ID: 105837 |
Fachbereich(e)/-gebiet(e): | 16 Fachbereich Maschinenbau 16 Fachbereich Maschinenbau > Fachgebiet Cyber-Physische Simulation (CPS) |
Hinterlegungsdatum: | 10 Sep 2024 05:48 |
Letzte Änderung: | 10 Sep 2024 06:04 |
PPN: | 521297443 |
Export: | |
Suche nach Titel in: | TUfind oder in Google |
Frage zum Eintrag |
Optionen (nur für Redakteure)
Redaktionelle Details anzeigen |