A feed-forward neural network for solving Stokes problem

DOI10.1007/S10440-011-9627-5MaRDI QIDQ645014zbMATH OpenOpenAlexFDO

Authors M. Baymani, Sohrab Effati, A. Kerayechian

Publication date 8 November 2011

Published in Acta Applicandae Mathematicae (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10440-011-9627-5

zbMATH Keywords

artificial neural networksPoisson equationStokes problem

Mathematics Subject Classification ID

Laplace operator, Helmholtz equation (reduced wave equation), Poisson equation (35J05) Variational methods for second-order elliptic equations (35J20) Neural networks for/in biological studies, artificial life and related topics (92B20)

Review text

The authors build trial solutions for a particular boundary value problem associated to the Poisson equation, by means of a multilayer perceptron technique. The boundary conditions are included in the trial solution. Two examples are shown.

Recommendations

• Neural‐network‐based approximations for solving partial differential equations
• scientific article; zbMATH DE number 5026478
• Multi-Scale Deep Neural Network (MscaleDNN) Methods for Oscillatory Stokes Flows in Complex Domains
• Design feed forward neural network to solve singular boundary value problems
• A new approach for solving the Stokes problem

Cites work

• A discontinuous Galerkin method with nonoverlapping domain decomposition for the Stokes and Navier-Stokes problems
• A discrete divergence-free basis for finite element methods
• A locally conservative LDG method for the incompressible Navier-Stokes equations
• A Rapidly Convergent Descent Method for Minimization
• Analysis and convergence of the MAC scheme. II. Navier-Stokes equations
• Discontinuous stable elements for the incompressible flow
• Finite Element Methods for Navier-Stokes Equations
• Finite elements for incompressible flow
• scientific article; zbMATH DE number 5524473 (Why is no real title available?)
• scientific article; zbMATH DE number 3906935 (Why is no real title available?)
• scientific article; zbMATH DE number 3912096 (Why is no real title available?)
• scientific article; zbMATH DE number 3746666 (Why is no real title available?)
• scientific article; zbMATH DE number 2110700 (Why is no real title available?)
• Local Discontinuous Galerkin Methods for the Stokes System
• New Finite Element Methods in Computational Fluid Dynamics by H(div) Elements
• Solving the Stokes problem by linear programming methods.
• The construction of a null basis for a discrete divergence operator
• Variance algorithm for minimization

Cited in

(7)

• PFNN: a penalty-free neural network method for solving a class of second-order boundary-value problems on complex geometries
• Polynomial neural forms using feedforward neural networks for solving differential equations
• Solving liner boundary problems with multigrid iterative neural networks
• Application of multigrid iterative neural network method to stationary problems of advection-diffusion
• A hybrid neural-network and MAC scheme for Stokes interface problems
• Can neural networks learn finite elements?
• Multilayer perceptron artificial neural network approach to solve sixth-order two-point boundary value problems

This page was built for publication: A feed-forward neural network for solving Stokes problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q645014)