PFNN: A Penalty-Free Neural Network Method for Solving a Class of Second-Order Boundary-Value Problems on Complex Geometries

Abstract

We present PFNN, a penalty-free neural network method, to efficiently solve a class of second-order boundary-value problems on complex geometries. To reduce the smoothness requirement, the original problem is reformulated to a weak form so that the evaluations of high-order derivatives are avoided. Two neural networks, rather than just one, are employed to construct the approximate solution, with one network satisfying the essential boundary conditions and the other handling the rest part of the domain. In this way, an unconstrained optimization problem, instead of a constrained one, is solved without adding any penalty terms. The entanglement of the two networks is eliminated with the help of a length factor function that is scale invariant and can adapt with complex geometries. We prove the convergence of the PFNN method and conduct numerical experiments on a series of linear and nonlinear second-order boundary-value problems to demonstrate that PFNN is superior to several existing approaches in terms of accuracy, flexibility and robustness.

References in corpus (18)

• Deep Learning in Neural Networks: An Overview
• Artificial Neural Networks for Solving Ordinary and Partial Differential Equations
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• DGM: A deep learning algorithm for solving partial differential equations
• Solving high-dimensional partial differential equations using deep learning
• Turbulence Modeling in the Age of Data
• Recent Trends in Deep Learning Based Natural Language Processing
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• A unified deep artificial neural network approach to partial differential equations in complex geometries
• PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network
• Weak Adversarial Networks for High-dimensional Partial Differential Equations
• Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
• Deep Nitsche Method: Deep Ritz Method with Essential Boundary Conditions
• D3M: A deep domain decomposition method for partial differential equations
• MgNet: A Unified Framework of Multigrid and Convolutional Neural Network
• DR-RNN: A deep residual recurrent neural network for model reduction
• BCR-Net: a neural network based on the nonstandard wavelet form
• Forward-Backward Stochastic Neural Networks: Deep Learning of High-dimensional Partial Differential Equations

Cited by in corpus (25)

• Gradient-enhanced physics-informed neural networks for forward and inverse PDE problems
• CENN: Conservative energy method based on neural networks with subdomains for solving variational problems involving heterogeneous and complex geometries
• An overview on deep learning-based approximation methods for partial differential equations
• A Discontinuity Capturing Shallow Neural Network for Elliptic Interface Problems
• BINN: A deep learning approach for computational mechanics problems based on boundary integral equations
• A solver for subsonic flow around airfoils based on physics-informed neural networks and mesh transformation
• Adaptive deep density approximation for Fokker-Planck equations
• DCEM: A deep complementary energy method for solid mechanics
• An augmented Lagrangian deep learning method for variational problems with essential boundary conditions
• Deep unfitted Nitsche method for elliptic interface problems
• Enhancing training of physics-informed neural networks using domain-decomposition based preconditioning strategies
• Exact imposition of boundary conditions with distance functions in physics-informed deep neural networks
• Exponential ReLU Neural Network Approximation Rates for Point and Edge Singularities
• A Shallow Ritz Method for Elliptic Problems with Singular Sources
• Physics-informed machine learning and stray field computation with application to micromagnetic energy minimization
• The Hard-Constraint PINNs for Interface Optimal Control Problems
• Enforcing exact boundary and initial conditions in the deep mixed residual method
• Learning Domain-Independent Green's Function For Elliptic Partial Differential Equations
• Deep adaptive sampling for surrogate modeling without labeled data
• Discovering Physics-Informed Neural Networks Model for Solving Partial Differential Equations through Evolutionary Computation
• Physics-Informed Kolmogorov-Arnold Networks for multi-material elasticity problems in electronic packaging
• A Natural Deep Ritz Method for Essential Boundary Value Problems
• AONN-2: An adjoint-oriented neural network method for PDE-constrained shape optimization
• Unfitted finite element interpolated neural networks
• A pre-training deep learning method for simulating the large bending deformation of bilayer plates