Preconditioned FEM-based Neural Networks for Solving Incompressible Fluid Flows and Related Inverse Problems

TL;DR

This paper introduces a preconditioned FEM-based neural network approach for efficiently solving incompressible fluid flow problems and related inverse problems, improving training efficiency and accuracy.

Contribution

It extends physically informed neural networks to nonlinear fluid dynamics by incorporating preconditioners, enhancing convergence and generalization.

Findings

Significant reduction in training effort.

Improved accuracy and generalizability.

Effective application to inverse problems.

Abstract

The numerical simulation and optimization of technical systems described by partial differential equations is expensive, especially in multi-query scenarios in which the underlying equations have to be solved for different parameters. A comparatively new approach in this context is to combine the good approximation properties of neural networks (for parameter dependence) with the classical finite element method (for discretization). However, instead of considering the solution mapping of the PDE from the parameter space into the FEM-discretized solution space as a purely data-driven regression problem, so-called physically informed regression problems have proven to be useful. In these, the equation residual is minimized during the training of the neural network, i.e., the neural network "learns" the physics underlying the problem. In this paper, we extend this approach to saddle-point and non-linear fluid dynamics problems, respectively, namely stationary Stokes and stationary Navier-Stokes equations. In particular, we propose a modification of the existing approach: Instead of minimizing the plain vanilla equation residual during training, we minimize the equation residual modified by a preconditioner. By analogy with the linear case, this also improves the condition in the present non-linear case. Our numerical examples demonstrate that this approach significantly reduces the training effort and greatly increases accuracy and generalizability. Finally, we show the application of the resulting parameterized model to a related inverse problem.