A review and comparison of error estimators for anisotropic mesh adaptation for flow simulations

A Balan, MA Park, SL Wood, WK Anderson… - Computers & …, 2022 - Elsevier
Automated mesh adaptation is known to be an efficient way to control discretization errors in
Computational Fluid Dynamics (CFD) simulations. It offers the added advantage that the …

Swarm reinforcement learning for adaptive mesh refinement

N Freymuth, P Dahlinger, T Würth… - Advances in …, 2024 - proceedings.neurips.cc
Abstract The Finite Element Method, an important technique in engineering, is aided by
Adaptive Mesh Refinement (AMR), which dynamically refines mesh regions to allow for a …

M2N: Mesh movement networks for PDE solvers

W Song, M Zhang, JG Wallwork… - Advances in …, 2022 - proceedings.neurips.cc
Abstract Numerical Partial Differential Equation (PDE) solvers often require discretizing the
physical domain by using a mesh. Mesh movement methods provide the capability to …

[HTML][HTML] Neural control of discrete weak formulations: Galerkin, least squares & minimal-residual methods with quasi-optimal weights

I Brevis, I Muga, KG van der Zee - Computer Methods in Applied Mechanics …, 2022 - Elsevier
There is tremendous potential in using neural networks to optimize numerical methods. In
this paper, we introduce and analyze a framework for the neural optimization of discrete …

Towards a new paradigm in intelligence-driven computational fluid dynamics simulations

X Chen, Z Wang, L Deng, J Yan, C Gong… - Engineering …, 2024 - Taylor & Francis
Computational Fluid Dynamics (CFD) plays a crucial role in investigating new physical
phenomena and exploring the principles of fluid mechanics. However, CFD numerical …

Machine learning mesh-adaptation for laminar and turbulent flows: applications to high-order discontinuous Galerkin solvers

K Tlales, KE Otmani, G Ntoukas, G Rubio… - Engineering with …, 2024 - Springer
We present a machine learning-based mesh refinement technique for steady and unsteady
incompressible flows. The clustering technique proposed by Otmani et al.(Phys Fluids 35 …

E2n: error estimation networks for goal-oriented mesh adaptation

JG Wallwork, J Lu, M Zhang, MD Piggott - arXiv preprint arXiv:2207.11233, 2022 - arxiv.org
Given a partial differential equation (PDE), goal-oriented error estimation allows us to
understand how errors in a diagnostic quantity of interest (QoI), or goal, occur and …

MeshPointNet: 3D Surface Classification Using Graph Neural Networks and Conformal Predictions on Mesh-Based Representations

A Heyrani Nobari, J Rey… - Journal of …, 2024 - asmedigitalcollection.asme.org
In many design automation applications, accurate segmentation and classification of 3D
surfaces and extraction of geometric insight from 3D models can be pivotal. This paper …

Conformal predictions enhanced expert-guided meshing with graph neural networks

AH Nobari, J Rey, S Kodali, M Jones… - arXiv preprint arXiv …, 2023 - arxiv.org
Computational Fluid Dynamics (CFD) is widely used in different engineering fields, but
accurate simulations are dependent upon proper meshing of the simulation domain. While …

Unstructured mesh size control method based on artificial neural network

W Nianhua, L Peng, C Xinghua, Z Laiping… - Chinese Journal of …, 2021 - lxxb.cstam.org.cn
Automatic mesh generation and adaptation are bottleneck problems restricting
computational fluid dynamics (CFD). Grid quality, efficiency, flexibility, automation level, and …