☆ 4.7 Article

Intelligent mesh generation for crack simulation using graph neural networks

COMPUTERS & STRUCTURES (2024)

Related references

Note: Only part of the references are listed.

Article Computer Science, Artificial Intelligence

Reinforcement learning for automatic quadrilateral mesh generation: A soft actor-critic approach

Jie Pan et al.

Summary: This paper presents, implements, and evaluates a computational framework for automatic mesh generation based on reinforcement learning (RL). Mesh generation is crucial for numerical simulations in computer-aided design and engineering (CAD/E) and is considered a critical issue in the NASA CFD Vision 2030 Study. Existing mesh generation methods face challenges such as high computational complexity, low mesh quality in complex geometries, and limited speed. By formulating mesh generation as a Markov decision process (MDP), the paper applies a state-of-the-art RL algorithm called soft actor-critic to automatically learn the actions for mesh generation. The implementation of this RL algorithm enables the development of a fully automated mesh generation system without human intervention or additional clean-up operations, addressing the gaps in existing mesh generation tools.

NEURAL NETWORKS (2023)

Add to Collection

Article Construction & Building Technology

Exploring graph neural networks for semantic enrichment: Room type classification

Zijian Wang et al.

Summary: This paper introduces a novel approach to semantic enrichment of BIM models by representing models as graphs and applying graph neural networks (GNNs). The experiments demonstrate the feasibility of this approach and show that the developed GNN algorithm achieved higher accuracy and more balanced prediction compared to other machine learning algorithms. The application of GNNs in semantic enrichment opens up possibilities for other potential applications.

AUTOMATION IN CONSTRUCTION (2022)

Add to Collection

Article Engineering, Multidisciplinary

Physics-informed graph neural Galerkin networks: A unified framework for solving PDE-governed forward and inverse problems

Han Gao et al.

Summary: Despite the promise of PINNs in solving forward and inverse problems, there are technical challenges that hinder complex and realistic applications. To address these challenges, a discrete PINN framework based on GCN and PDE is proposed to solve PDEs in both forward and inverse settings, offering improved scalability, boundary enforcement, and handling of irregular geometries.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2022)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Evaluating mesh quality with graph neural networks

Zhichao Wang et al.

Summary: The quality of the finite element mesh has a significant impact on the efficiency and accuracy of computational fluid dynamics simulations. However, there is a lack of justifiable thresholds for determining the quality of the generated mesh. This paper proposes a novel approach to evaluate mesh quality as a graph classification problem using deep graph neural networks.

ENGINEERING WITH COMPUTERS (2022)

Add to Collection

Article Environmental Studies

Hybrid electric buses fuel consumption prediction based on real-world driving data

Ruixiao Sun et al.

Summary: This study empirically compared the fuel consumption of diesel and hybrid buses using long-term monitoring data, and developed high-fidelity microscopic and mesoscopic fuel consumption models based on artificial neural networks. The impacts of different driving speeds, vehicle engine demand, and road grade on prediction performance were investigated by partitioning the data.

TRANSPORTATION RESEARCH PART D-TRANSPORT AND ENVIRONMENT (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

How to teach neural networks to mesh: Application on 2-D simplicial contours

Alexis Papagiannopoulos et al.

Summary: This study introduces a machine learning meshing scheme for 2-D simplicial mesh generation based on predictions made by neural networks. Results show that the scheme is accurate and reliable in producing high-quality meshes, encouraging its adaptation for 3-D mesh generation.

NEURAL NETWORKS (2021)

Add to Collection

Article Computer Science, Software Engineering

Dynamic Graph CNN for Learning on Point Clouds

Yue Wang et al.

ACM TRANSACTIONS ON GRAPHICS (2019)

Add to Collection

Article Ecology

The area under the precision-recall curve as a performance metric for rare binary events

Helen R. Sofaer et al.

METHODS IN ECOLOGY AND EVOLUTION (2019)

Add to Collection

Editorial Material Engineering, Electrical & Electronic

Geometric Deep Learning Going beyond Euclidean data

Michael M. Bronstein et al.

IEEE SIGNAL PROCESSING MAGAZINE (2017)

Add to Collection

Article Computer Science, Interdisciplinary Applications

A new mesh deformation method based on disk relaxation algorithm with pre-displacement and post-smoothing

Xuan Zhou et al.

JOURNAL OF COMPUTATIONAL PHYSICS (2013)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Reduced surface point selection options for efficient mesh deformation using radial basis functions

T. C. S. Rendall et al.

JOURNAL OF COMPUTATIONAL PHYSICS (2010)

Add to Collection

Article Cardiac & Cardiovascular Systems

Receiver-operating characteristic analysis for evaluating diagnostic tests and predictive models

Kelly H. Zou et al.

CIRCULATION (2007)

Add to Collection

Article Computer Science, Artificial Intelligence

An ANN-based element extraction method for automatic mesh generation

S Yao et al.

EXPERT SYSTEMS WITH APPLICATIONS (2005)

Add to Collection

Article Engineering, Multidisciplinary

Isogeometric analysis: CAD, finite elements, NURBS, exact geometry and mesh refinement

TJR Hughes et al.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2005)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Partitioning of tall buildings using bubble graph representation

BHV Topping et al.

JOURNAL OF COMPUTING IN CIVIL ENGINEERING (2001)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Neural network based modelling of environmental variables: A systematic approach

HR Maier et al.

MATHEMATICAL AND COMPUTER MODELLING (2001)

Add to Collection

© Peeref 2019-2024. All rights reserved.