A new mesh smoothing method based on convolutional neural network

DOI10.1007/S00466-025-02693-3MaRDI QIDQ7286528zbMATH OpenFDO

Authors Zhe Chang, Lufeng Liu, Yibing Chen, Xinlong Feng

Publication date 23 June 2026

Published in Computational Mechanics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S00466-025-02693-3

Mathematics Subject Classification ID

Mechanics of deformable solids (74-XX)

Cites work

• A new mesh smoothing method based on a neural network
• Algebraic mesh quality metrics
• Algebraic mesh quality metrics for unstructured initial meshes.
• An arbitrary Lagrangian-Eulerian computing method for all flow speeds
• Analytic study of 2D and 3D grid motion using modified Laplacian
• Arbitrary Lagrangian-Eulerian methods for modeling high-speed compressible multimaterial flows
• Convolution hierarchical deep-learning neural networks (C-HiDeNN): finite elements, isogeometric analysis, tensor decomposition, and beyond
• HiDeNN-FEM: a seamless machine learning approach to nonlinear finite element analysis
• ICIAM/GAMM 95 Numerical Analysis, Scientific computing Computer ScienceICIAM/GAMM 95 Numerical Analysis, Scientific computing Computer Science
• Laplacian smoothing and Delaunay triangulations
• Learning representations by back-propagating errors
• Mesh quality effects on the accuracy of CFD solutions on unstructured meshes
• Physics-informed PointNet: a deep learning solver for steady-state incompressible flows and thermal fields on multiple sets of irregular geometries
• Unstructured surface mesh smoothing method based on deep reinforcement learning

This page was built for publication: A new mesh smoothing method based on convolutional neural network

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7286528)