Deep Learning Nonhomogeneous Elliptic Interface Problems by Soft Constraint Physics-Informed Neural Networks
Open Access
- 13 April 2023
- journal article
- research article
- Published by MDPI AG in Mathematics
- Vol. 11 (8) , 1843
Abstract
It is a great challenge to solve nonhomogeneous elliptic interface problems, because the interface divides the computational domain into two disjoint parts, and the solution may change dramatically across the interface. A soft constraint physics-informed neural network with dual neural networks is proposed, which is composed of two separate neural networks for each subdomain, which are coupled by the connecting conditions on the interface. It is beneficial to capture the singularity of the solution across the interface. We formulate the PDEs, boundary conditions, and jump conditions on the interface into the loss function by means of the physics-informed neural network (PINN), and the different terms in the loss function are balanced by optimized penalty weights. To enhance computing efficiency for increasingly difficult issues, adaptive activation functions and the adaptive sampled method are used, which may be improved to produce the optimal network performance, as the topology of the loss function involved in the optimization process changes dynamically. Lastly, we present many numerical experiments, in both 2D and 3D, to demonstrate the proposed method’s flexibility, efficacy, and accuracy in tackling nonhomogeneous interface issues.Keywords
Funding Information
- National Natural Science Foundation of China (12261067, 12161067, 62201298, 12001015, 51961031, NJYT20B15, 2020MS06010, 2021LHMS01006, 2022MS01008, 2019YQL02)
- Inner Mongolia Autonomous Region “Youth Science and Technology Talents” Support Program (12261067, 12161067, 62201298, 12001015, 51961031, NJYT20B15, 2020MS06010, 2021LHMS01006, 2022MS01008, 2019YQL02)
- Inner Mongolia Scientific Fund Project (12261067, 12161067, 62201298, 12001015, 51961031, NJYT20B15, 2020MS06010, 2021LHMS01006, 2022MS01008, 2019YQL02)
- Innovation Fund Project of Inner Mongolia University of Science and Technology-Excellent Youth Science Fund Project (12261067, 12161067, 62201298, 12001015, 51961031, NJYT20B15, 2020MS06010, 2021LHMS01006, 2022MS01008, 2019YQL02)
This publication has 40 references indexed in Scilit:
- An unfitted interface penalty finite element method for elliptic interface problemsComputer Methods in Applied Mechanics and Engineering, 2017
- An interface-fitted adaptive mesh method for elliptic problems and its application in free interface problems with surface tensionAdvances in Computational Mathematics, 2016
- Variational bounds in composites with nonuniform interfacial thermal resistanceApplied Mathematical Modelling, 2015
- Optimal a priori estimates for higher order finite elements for elliptic interface problemsApplied Numerical Mathematics, 2010
- A sharp interface finite volume method for elliptic equations on Cartesian gridsJournal of Computational Physics, 2009
- A discontinuous Galerkin method for elliptic interface problems with application to electroporationCommunications in Numerical Methods in Engineering, 2008
- The Immersed Interface Method2006
- COMPUTATION OF THE EFFECTIVE CONDUCTIVITY OF UNIDIRECTIONAL FIBROUS COMPOSITES WITH AN INTERFACIAL THERMAL RESISTANCENumerical Heat Transfer, Part A: Applications, 2001
- Fitted and Unfitted Finite-Element Methods for Elliptic Equations with Smooth InterfacesIMA Journal of Numerical Analysis, 1987
- Numerical analysis of blood flow in the heartJournal of Computational Physics, 1977