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

References in corpus (10)

• Physics-informed graph neural Galerkin networks: A unified framework for solving PDE-governed forward and inverse problems
• Variational Physics-Informed Neural Networks For Solving Partial Differential Equations
• Physics-Informed Machine Learning: A Survey on Problems, Methods and Applications
• Integrated Finite Element Neural Network (I-FENN) for non-local continuum damage mechanics
• Deep Learning Methods for Partial Differential Equations and Related Parameter Identification Problems
• Enhancing training of physics-informed neural networks using domain-decomposition based preconditioning strategies
• A hybrid finite element/neural network solver and its application to the Poisson problem
• Fusion-DeepONet: A Data-Efficient Neural Operator for Geometry-Dependent Hypersonic and Supersonic Flows
• A hybrid physics-informed neural network based multiscale solver as a partial differential equation constrained optimization problem
• Preconditioning for Physics-Informed Neural Networks

Cited by in corpus (1)

• Spectral Informed Neural Network: An Efficient and Low-Memory PINN