Multi-patch isogeometric neural solver for partial differential equations on computer-aided design domains

Abstract

This work develops a computational framework that combines physics-informed neural networks with multi-patch isogeometric analysis to solve partial differential equations on complex computer-aided design geometries. The method utilizes patch-local neural networks that operate on the reference domain of isogeometric analysis. A custom output layer enables the strong imposition of Dirichlet boundary conditions. Solution conformity across interfaces between non-uniform rational B-spline patches is enforced using dedicated interface neural networks. Training is performed using the variational framework by minimizing the energy functional derived after the weak form of the partial differential equation. The effectiveness of the suggested method is demonstrated on two highly non-trivial and practically relevant use-cases, namely, a 2D magnetostatics model of a quadrupole magnet and a 3D nonlinear solid and contact mechanics model of a mechanical holder. The results show excellent agreement to reference solutions obtained with high-fidelity finite element solvers, thus highlighting the potential of the suggested neural solver to tackle complex engineering problems given the corresponding computer-aided design models.

33 pages, 15 figures

References in corpus (15)

• DGM: A deep learning algorithm for solving partial differential equations
• An Energy Approach to the Solution of Partial Differential Equations in Computational Mechanics via Machine Learning: Concepts, Implementation and Applications
• B-PINNs: Bayesian Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Noisy Data
• hp-VPINNs: Variational Physics-Informed Neural Networks With Domain Decomposition
• DOLFIN: Automated Finite Element Computing
• Isogeometric analysis: an overview and computer implementation aspects
• Physics-informed neural networks for solving Reynolds-averaged Navier$\unicode{x2013}$Stokes equations
• CAN-PINN: A Fast Physics-Informed Neural Network Based on Coupled-Automatic-Numerical Differentiation Method
• Isogeometric mortar methods
• Neural networks meet hyperelasticity: A guide to enforcing physics
• Physics-informed neural networks for solving parametric magnetostatic problems
• Error Approximation and Bias Correction in Dynamic Problems using a Recurrent Neural Network/Finite Element Hybrid Model
• A Neural Solver for Variational Problems on CAD Geometries with Application to Electric Machine Simulation
• Torque Computation with the Isogeometric Mortar Method for the Simulation of Electric Machines
• Solving Electromagnetic Scattering Problems by Isogeometric Analysis with Deep Operator Learning