Neural networks for the approximation of Euler's elastica

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Celledoni, Elena, Çokaj, Ergys, Leone, Andrea, Leyendecker, Sigrid, Murari, Davide, Owren, Brynjulf, de Almagro, Rodrigo T. Sato Martín, Stavole, Martina
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913375767756800
author Celledoni, Elena
Çokaj, Ergys
Leone, Andrea
Leyendecker, Sigrid
Murari, Davide
Owren, Brynjulf
de Almagro, Rodrigo T. Sato Martín
Stavole, Martina
author_facet Celledoni, Elena
Çokaj, Ergys
Leone, Andrea
Leyendecker, Sigrid
Murari, Davide
Owren, Brynjulf
de Almagro, Rodrigo T. Sato Martín
Stavole, Martina
contents Euler's elastica is a classical model of flexible slender structures, relevant in many industrial applications. Static equilibrium equations can be derived via a variational principle. The accurate approximation of solutions of this problem can be challenging due to nonlinearity and constraints. We here present two neural network based approaches for the simulation of this Euler's elastica. Starting from a data set of solutions of the discretised static equilibria, we train the neural networks to produce solutions for unseen boundary conditions. We present a $\textit{discrete}$ approach learning discrete solutions from the discrete data. We then consider a $\textit{continuous}$ approach using the same training data set, but learning continuous solutions to the problem. We present numerical evidence that the proposed neural networks can effectively approximate configurations of the planar Euler's elastica for a range of different boundary conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2312_00644
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Neural networks for the approximation of Euler's elastica
Celledoni, Elena
Çokaj, Ergys
Leone, Andrea
Leyendecker, Sigrid
Murari, Davide
Owren, Brynjulf
de Almagro, Rodrigo T. Sato Martín
Stavole, Martina
Numerical Analysis
Euler's elastica is a classical model of flexible slender structures, relevant in many industrial applications. Static equilibrium equations can be derived via a variational principle. The accurate approximation of solutions of this problem can be challenging due to nonlinearity and constraints. We here present two neural network based approaches for the simulation of this Euler's elastica. Starting from a data set of solutions of the discretised static equilibria, we train the neural networks to produce solutions for unseen boundary conditions. We present a $\textit{discrete}$ approach learning discrete solutions from the discrete data. We then consider a $\textit{continuous}$ approach using the same training data set, but learning continuous solutions to the problem. We present numerical evidence that the proposed neural networks can effectively approximate configurations of the planar Euler's elastica for a range of different boundary conditions.
title Neural networks for the approximation of Euler's elastica
topic Numerical Analysis
url https://arxiv.org/abs/2312.00644