A physics-informed deep learning framework for inversion and surrogate modeling in solid mechanics

We present the application of a class of deep learning, known as Physics Informed Neural Networks (PINN), to inversion and surrogate modeling in solid mechanics. We explain how to incorporate the momentum balance and constitutive relations into PINN, and explore in detail the application to linear e...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Computer methods in applied mechanics and engineering Jg. 379; S. 113741
Hauptverfasser:	Haghighat, Ehsan, Raissi, Maziar, Moure, Adrian, Gomez, Hector, Juanes, Ruben
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Amsterdam Elsevier B.V 01.06.2021 Elsevier BV
Schlagworte:	Algorithms Artificial neural network Artificial neural networks Constitutive relationships Convergence Deep learning Elastoplasticity Finite element method Inversion Linear elasticity Machine learning Mathematical models Model testing Neural networks Parameters Physics Physics-informed deep learning Robustness (mathematics) Sensitivity analysis Solid mechanics Training Transfer learning Inversion Artificial neural network Physics-informed deep learning Elastoplasticity Transfer learning Linear elasticity
ISSN:	0045-7825, 1879-2138
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!