Physical informed neural networks with soft and hard boundary constraints for solving advection-diffusion equations using Fourier expansions

TL;DR

This paper introduces SFHCPINN, a hybrid physics-informed neural network that combines Fourier features and boundary constraints to solve advection-diffusion equations more accurately and efficiently, especially in complex and high-frequency cases.

Contribution

The paper proposes a novel hybrid neural network architecture, SFHCPINN, integrating Fourier features and boundary constraints for improved PDE solving performance.

Findings

SFHCPINN outperforms standard PINN in accuracy and efficiency.

The method effectively handles complex boundary conditions.

It demonstrates superior performance in high-frequency and high-dimensional ADE scenarios.

Abstract

Deep learning methods have gained considerable interest in the numerical solution of various partial differential equations (PDEs). One particular focus is physics-informed neural networks (PINN), which integrate physical principles into neural networks. This transforms the process of solving PDEs into optimization problems for neural networks. To address a collection of advection-diffusion equations (ADE) in a range of difficult circumstances, this paper proposes a novel network structure. This architecture integrates the solver, a multi-scale deep neural networks (MscaleDNN) utilized in the PINN method, with a hard constraint technique known as HCPINN. This method introduces a revised formulation of the desired solution for ADE by utilizing a loss function that incorporates the residuals of the governing equation and penalizes any deviations from the specified boundary and initial constraints. By surpassing the boundary constraints automatically, this method improves the accuracy and efficiency of the PINN technique. To address the ``spectral bias'' phenomenon in neural networks, a subnetwork structure of MscaleDNN and a Fourier-induced activation function are incorporated into the HCPINN, resulting in a hybrid approach called SFHCPINN. The effectiveness of SFHCPINN is demonstrated through various numerical experiments involving ADE in different dimensions. The numerical results indicate that SFHCPINN outperforms both standard PINN and its subnetwork version with Fourier feature embedding. It achieves remarkable accuracy and efficiency while effectively handling complex boundary conditions and high-frequency scenarios in ADE.