Physics-informed neural networks for transformed geometries and manifolds

• URL: http://arxiv.org/abs/2311.15940v2
• Date: Wed, 29 Nov 2023 15:46:23 GMT
• Title: Physics-informed neural networks for transformed geometries and manifolds
• Authors: Samuel Burbulla
• Abstract summary: We propose a novel method for integrating geometric transformations within PINNs to robustly accommodate geometric variations. We demonstrate the enhanced flexibility over traditional PINNs, especially under geometric variations. The proposed framework presents an outlook for training deep neural operators over parametrized geometries.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Physics-informed neural networks (PINNs) effectively embed physical principles into machine learning, but often struggle with complex or alternating geometries. We propose a novel method for integrating geometric transformations within PINNs to robustly accommodate geometric variations. Our method incorporates a diffeomorphism as a mapping of a reference domain and adapts the derivative computation of the physics-informed loss function. This generalizes the applicability of PINNs not only to smoothly deformed domains, but also to lower-dimensional manifolds and allows for direct shape optimization while training the network. We demonstrate the effectivity of our approach on several problems: (i) Eikonal equation on Archimedean spiral, (ii) Poisson problem on surface manifold, (iii) Incompressible Stokes flow in deformed tube, and (iv) Shape optimization with Laplace operator. Through these examples, we demonstrate the enhanced flexibility over traditional PINNs, especially under geometric variations. The proposed framework presents an outlook for training deep neural operators over parametrized geometries, paving the way for advanced modeling with PDEs on complex geometries in science and engineering.

Related papers

• Geometry Distributions [51.4061133324376]
  We propose a novel geometric data representation that models geometry as distributions. Our approach uses diffusion models with a novel network architecture to learn surface point distributions. We evaluate our representation qualitatively and quantitatively across various object types, demonstrating its effectiveness in achieving high geometric fidelity.
  arXiv  Detail & Related papers  (2024-11-25T04:06:48Z)
• A hybrid numerical methodology coupling Reduced Order Modeling and Graph Neural Networks for non-parametric geometries: applications to structural dynamics problems [0.0]
  This work introduces a new approach for accelerating the numerical analysis of time-domain partial differential equations (PDEs) governing complex physical systems. The methodology is based on a combination of a classical reduced-order modeling (ROM) framework and recently-parametric Graph Neural Networks (GNNs)
  arXiv  Detail & Related papers  (2024-06-03T08:51:25Z)
• Geometry-aware framework for deep energy method: an application to structural mechanics with hyperelastic materials [2.271910267215261]
  We introduce a physics-informed framework named the Geometry-Aware Deep Energy Method (GADEM) for solving structural mechanics problems. Different ways to represent the geometric information and to encode the geometric latent vectors are investigated in this work. We present some applications of GADEM to solve solid mechanics problems, including a loading simulation of a toy tire.
  arXiv  Detail & Related papers  (2024-05-06T12:47:16Z)
• Transolver: A Fast Transformer Solver for PDEs on General Geometries [66.82060415622871]
  We present Transolver, which learns intrinsic physical states hidden behind discretized geometries. By calculating attention to physics-aware tokens encoded from slices, Transovler can effectively capture intricate physical correlations. Transolver achieves consistent state-of-the-art with 22% relative gain across six standard benchmarks and also excels in large-scale industrial simulations.
  arXiv  Detail & Related papers  (2024-02-04T06:37:38Z)
• Physics-Informed Graph Convolutional Networks: Towards a generalized framework for complex geometries [0.0]
  We justify the use of graph neural networks for solving partial differential equations. An alternative procedure is proposed, by combining classical numerical solvers and the Physics-Informed framework. We propose an implementation of this approach, that we test on a three-dimensional problem on an irregular geometry.
  arXiv  Detail & Related papers  (2023-10-20T09:46:12Z)
• A Theory of Topological Derivatives for Inverse Rendering of Geometry [87.49881303178061]
  We introduce a theoretical framework for differentiable surface evolution that allows discrete topology changes through the use of topological derivatives. We validate the proposed theory with optimization of closed curves in 2D and surfaces in 3D to lend insights into limitations of current methods.
  arXiv  Detail & Related papers  (2023-08-19T00:55:55Z)
• Learning the solution operator of two-dimensional incompressible Navier-Stokes equations using physics-aware convolutional neural networks [68.8204255655161]
  We introduce a technique with which it is possible to learn approximate solutions to the steady-state Navier--Stokes equations in varying geometries without the need of parametrization. The results of our physics-aware CNN are compared to a state-of-the-art data-based approach.
  arXiv  Detail & Related papers  (2023-08-04T05:09:06Z)
• Topology optimization with physics-informed neural networks: application to noninvasive detection of hidden geometries [0.40611352512781856]
  We introduce a topology optimization framework based on PINNs for detecting hidden geometrical structures. We validate our framework by detecting the number, locations, and shapes of hidden voids and inclusions in linear and nonlinear elastic bodies.
  arXiv  Detail & Related papers  (2023-03-13T12:44:32Z)
• Revisiting Transformation Invariant Geometric Deep Learning: Are Initial Representations All You Need? [80.86819657126041]
  We show that transformation-invariant and distance-preserving initial representations are sufficient to achieve transformation invariance. Specifically, we realize transformation-invariant and distance-preserving initial point representations by modifying multi-dimensional scaling. We prove that TinvNN can strictly guarantee transformation invariance, being general and flexible enough to be combined with the existing neural networks.
  arXiv  Detail & Related papers  (2021-12-23T03:52:33Z)
• ResNet-LDDMM: Advancing the LDDMM Framework Using Deep Residual Networks [86.37110868126548]
  In this work, we make use of deep residual neural networks to solve the non-stationary ODE (flow equation) based on a Euler's discretization scheme. We illustrate these ideas on diverse registration problems of 3D shapes under complex topology-preserving transformations.
  arXiv  Detail & Related papers  (2021-02-16T04:07:13Z)
• Physics-informed neural networks with hard constraints for inverse design [3.8191831921441337]
  We propose a new deep learning method -- physics-informed neural networks with hard constraints (hPINNs) -- for solving topology optimization. We demonstrate the effectiveness of hPINN for a holography problem in optics and a fluid problem of Stokes flow.
  arXiv  Detail & Related papers  (2021-02-09T03:18:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.