A Neural Solver for Variational Problems on CAD Geometries with Application to Electric Machine Simulation

Abstract

This work presents a deep learning-based framework for the solution of partial differential equations on complex computational domains described with computer-aided design tools. To account for the underlying distribution of the training data caused by spline-based projections from the reference to the physical domain, a variational neural solver equipped with an importance sampling scheme is developed, such that the loss function based on the discretized energy functional obtained after the weak formulation is modified according to the sample distribution. To tackle multi-patch domains possibly leading to solution discontinuities, the variational neural solver is additionally combined with a domain decomposition approach based on the Discontinuous Galerkin formulation. The proposed neural solver is verified on a toy problem and then applied to a real-world engineering test case, namely that of electric machine simulation. The numerical results show clearly that the neural solver produces physics-conforming solutions of significantly improved accuracy.

arXiv comment27 pages, 9 figures

References in corpus (19)

• Adam: A Method for Stochastic Optimization
• TensorFlow: A system for large-scale machine learning
• On the difficulty of training Recurrent Neural Networks
• DeepXDE: A deep learning library for solving differential equations
• DGM: A deep learning algorithm for solving partial differential equations
• Solving high-dimensional partial differential equations using deep learning
• Adaptive activation functions accelerate convergence in deep and physics-informed neural networks
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• hp-VPINNs: Variational Physics-Informed Neural Networks With Domain Decomposition
• 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
• SciANN: A Keras/Tensorflow wrapper for scientific computations and physics-informed deep learning using artificial neural networks
• PDE-Net: Learning PDEs from Data
• Deep Nitsche Method: Deep Ritz Method with Essential Boundary Conditions
• D3M: A deep domain decomposition method for partial differential equations
• Full error analysis for the training of deep neural networks
• VarNet: Variational Neural Networks for the Solution of Partial Differential Equations
• Isogeometric Analysis and Harmonic Stator-Rotor Coupling for Simulating Electric Machines
• Probabilistic partition of unity networks: clustering based deep approximation

Cited by in corpus (1)

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