Exact imposition of boundary conditions with distance functions in physics-informed deep neural networks

In this paper, we introduce a new approach based on distance fields to exactly impose boundary conditions in physics-informed deep neural networks. The challenges in satisfying Dirichlet boundary conditions in meshfree and particle methods are well-known. This issue is also pertinent in the developm...

Full description

Saved in:

Bibliographic Details
Published in:	Computer methods in applied mechanics and engineering Vol. 389; p. 114333
Main Authors:	Sukumar, N., Srivastava, Ankit
Format:	Journal Article
Language:	English
Published:	Amsterdam Elsevier B.V 01.02.2022 Elsevier BV
Subjects:	Artificial neural networks Bending Biharmonic equations Boundary conditions Boundary value problems Collocation methods Constructive solid geometry Deep learning Differential geometry Dirichlet problem Distance function Domains Eikonal equation Exact geometry Geometry Hypercubes Interpolation Laplace equation Machine learning Meshfree method Meshless methods Neural networks Partial differential equations Physics Potential fields R-function Ritz method Thermodynamics Training Transfinite interpolation Deep learning Exact geometry Meshfree method Distance function R-function Transfinite interpolation
ISSN:	0045-7825, 1879-2138
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!