Artificial neural networks for solving elliptic differential equations with boundary layer
Authors:
- 14 March 2022
- journal article
- research article
- Published by Wiley in Mathematical Methods in the Applied Sciences
- Vol. 45 (11) , 6583-6598
Abstract
In this paper, we consider the artificial neural networks for solving the elliptic differential equation with boundary layer, in which the gradient of the solution changes sharply near the boundary layer. The solution of the boundary layer problems poses a huge challenge to both traditional numerical methods and artificial neural network methods. By theoretically analyzing the changing rate of the weights of the first hidden layer near the boundary layer, a mapping strategy is added in traditional neural network to improve the convergence of the loss function. Numerical examples are carried out for the 1D and 2D convection–diffusion equation with boundary layer. The results demonstrate that the modified neural networks significantly improve the ability in approximating the solutions with sharp gradient.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (12161067, 51961031, 61763039, 11772165, 11801287)
This publication has 20 references indexed in Scilit:
- Deep Learning-Based Numerical Methods for High-Dimensional Parabolic Partial Differential Equations and Backward Stochastic Differential EquationsCommunications in Mathematics and Statistics, 2017
- Single Layer Chebyshev Neural Network Model for Solving Elliptic Partial Differential EquationsNeural Processing Letters, 2016
- Application of Legendre Neural Network for solving ordinary differential equationsApplied Soft Computing, 2016
- Multigrid method based on the transformation-free HOC scheme on nonuniform grids for 2D convection diffusion problemsJournal of Computational Physics, 2011
- Feedforward Neural Network for Solving Partial Differential EquationsJournal of Applied Sciences, 2007
- Nonlinear dynamic system identification using Chebyshev functional link artificial neural networksIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2002
- Multilayer neural networks for solving a class of partial differential equationsNeural Networks, 2000
- Artificial neural networks for solving ordinary and partial differential equationsIEEE Transactions on Neural Networks, 1998
- The functional link net and learning optimal controlNeurocomputing, 1995
- Approximation capabilities of multilayer feedforward networksNeural Networks, 1991