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 …

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 …

DynAMO: Multi-agent reinforcement learning for dynamic anticipatory mesh optimization with applications to hyperbolic conservation laws

T Dzanic, K Mittal, D Kim, J Yang, S Petrides… - Journal of …, 2024 - Elsevier
We introduce DynAMO, a reinforcement learning paradigm for Dynamic Anticipatory Mesh
Optimization. Adaptive mesh refinement is an effective tool for optimizing computational cost …

Quasi-optimal hp-finite element refinements towards singularities via deep neural network prediction

T Służalec, R Grzeszczuk, S Rojas, W Dzwinel… - … & Mathematics with …, 2023 - Elsevier
We show how to construct a deep neural network (DNN) expert to predict quasi-optimal hp-
refinements for a given finite element problem in presence of singularities. The main idea is …

GMR-Net: GCN-based mesh refinement framework for elliptic PDE problems

M Kim, J Lee, J Kim - Engineering with Computers, 2023 - Springer
In this study, we propose a new approach for automatically generating high-quality non-
uniform meshes based on supervised learning. The proposed framework, GMR-Net, is …

[HTML][HTML] A reinforcement learning strategy for p-adaptation in high order solvers

D Huergo, G Rubio, E Ferrer - Results in Engineering, 2024 - Elsevier
Reinforcement learning (RL) has emerged as a promising approach to automating decision
processes. This paper explores the application of RL techniques to optimise the polynomial …

[HTML][HTML] Enhancing data representation in forging processes: Investigating discretization and R-adaptivity strategies with Proper Orthogonal Decomposition reduction

D Uribe, C Durand, C Baudouin, R Bigot - Finite Elements in Analysis and …, 2024 - Elsevier
Effective data reduction techniques are crucial for enhancing computational efficiency in
complex industrial processes such as forging. In this study, we investigate various …

Adaptive Swarm Mesh Refinement using Deep Reinforcement Learning with Local Rewards

N Freymuth, P Dahlinger, T Würth, S Reisch… - arxiv preprint arxiv …, 2024 - arxiv.org
Simulating physical systems is essential in engineering, but analytical solutions are limited
to straightforward problems. Consequently, numerical methods like the Finite Element …

[PDF][PDF] Results in Engineering

D Huergo, G Rubio, E Ferrer - researchgate.net
Reinforcement learning (RL) has emerged as a promising approach to automating decision
processes. This paper explores the application of RL techniques to optimise the polynomial …

DynAMO: Dynamic Anticipatory Mesh Optimization for Hyperbolic PDEs using Reinforcement Learning

K Mittal, T Dzanic, J Yang, S Petrides, D Kim, B Keith… - pdfs.semanticscholar.org
ABSTRACT Adaptive Mesh Refinement (AMR) is a popular technique for improving
efficiency of finite element simulations by selectively modifying resolution in different regions …