A Deep Neural Network/Meshfree Method for Solving Dynamic Two-phase Interface Problems

07/21/2022
by   Xingwen Zhu, et al.
0

In this paper, a meshfree method using the deep neural network (DNN) approach is developed for solving two kinds of dynamic two-phase interface problems governed by different dynamic partial differential equations on either side of the stationary interface with the jump and high-contrast coefficients. The first type of two-phase interface problem to be studied is the fluid-fluid (two-phase flow) interface problem modeled by Navier-Stokes equations with high-contrast physical parameters across the interface. The second one belongs to fluid-structure interaction (FSI) problems modeled by Navier-Stokes equations on one side of the interface and the structural equation on the other side of the interface, both the fluid and the structure interact with each other via the kinematic- and the dynamic interface conditions across the interface. The DNN/meshfree method is respectively developed for the above two-phase interface problems by representing solutions of PDEs using the DNNs' structure and reformulating the dynamic interface problem as a least-squares minimization problem based upon a space-time sampling point set. Approximation error analyses are also carried out for each kind of interface problem, which reveals an intrinsic strategy about how to efficiently build a sampling-point training dataset to obtain a more accurate DNNs' approximation. In addition, compared with traditional discretization approaches, the proposed DNN/meshfree method and its error analysis technique can be smoothly extended to many other dynamic interface problems with fixed interfaces. Numerical experiments are conducted to illustrate the accuracies of the proposed DNN/meshfree method for the presented two-phase interface problems. Theoretical results are validated to some extent through three numerical examples.

READ FULL TEXT

page 25

page 27

page 29

page 32

page 34

research
06/13/2020

A Finite Element Method for Electrowetting on Dielectric

We consider the problem of electrowetting on dielectric (EWoD). The syst...
research
01/11/2020

An energy-based coupling approach to nonlocal interface problems

Nonlocal models provide accurate representations of physical phenomena r...
research
06/26/2021

Physics-Guided Deep Neural Network to Characterize Non-Newtonian Fluid Flow for Optimal Use of Energy Resources

Numerical simulations of non-Newtonian fluids are indispensable for opti...
research
01/15/2020

Robust preconditioning of monolithically coupled multiphysics problems

In many applications, one wants to model physical systems consisting of ...
research
08/06/2023

Local Randomized Neural Networks Methods for Interface Problems

Accurate modeling of complex physical problems, such as fluid-structure ...
research
07/05/2022

Riemann Solvers for Phase Transition in a Compressible Sharp-Interface Method

In this paper, we consider Riemann solvers with phase transition effects...

Please sign up or login with your details

Forgot password? Click here to reset