An intelligent mesh-smoothing method with graph neural networks

Zhichao WANG; Xinhai CHEN; Junjun YAN; Jie LIU

doi:10.1631/FITEE.2300878

Your Location：

Home >

Browse articles >

An intelligent mesh-smoothing method with graph neural networks

Regular Papers | Updated：2025-04-03

- An intelligent mesh-smoothing method with graph neural networks
  Enhanced Publication
- 基于图神经网络的网格平滑方法研究
- Frontiers of Information Technology & Electronic Engineering Vol. 26, Issue 3, Pages: 367-384(2025)
- Affiliations：
  
  1.Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Changsha 410073, China
  2.Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha 410073, China
- Author bio：
  
  E-mail: wangzhichao@nudt.edu.cn
  ‡Corresponding author
- Funds：
- DOI：10.1631/FITEE.2300878
  CLC： TP391.4
- Received：29 December 2023，
  
  Revised：16 April 2024，
  
  Published：2025-03
- Accepted：
Scan QR Code
Zhichao WANG, Xinhai CHEN, Junjun YAN, et al. An intelligent mesh-smoothing method with graph neural networks[J]. Frontiers of information technology & electronic engineering, 2025, 26(3): 367-384.
DOI：

Zhichao WANG, Xinhai CHEN, Junjun YAN, et al. An intelligent mesh-smoothing method with graph neural networks[J]. Frontiers of information technology & electronic engineering, 2025, 26(3): 367-384. DOI： 10.1631/FITEE.2300878.

摘要

在计算流体力学中，网格平滑方法通常被应用于优化网格质量，以实现高精度的数值模拟。其中，基于优化的平滑方法广泛用于高质量网格平滑，但其计算成本相对较高。一些先驱性研究工作尝试采用监督学习的方法，从高质量网格样本中学习平滑方法，以提高其平滑效率。然而，该方法存在一些限制，例如难以处理不同度节点的问题，并且需要数据增强来解决网格节点输入顺序的问题。此外，对于高质量网格数据的依赖也限制了该方法的适用性。为解决这些问题，本文提出一种轻量级神经网络模型GMSNet，以实现智能化的网格平滑。GMSNet采用图神经网络来提取节点邻居的特征，并输出最优的节点位置。在平滑过程中，本文还引入了一种容错机制，以防止GMSNet生成负体积元素。通过轻量级的模型架构，GMSNet能够有效地平滑不同度的网格节点，并且不受输入数据顺序的影响。此外，本文还提出一种新颖的损失函数MetricLoss，用于消除对高质量网格数据的依赖，并促进训练的稳定、快速收敛。本文在二维非结构网格上将GMSNet与常用的网格平滑方法进行对比。实验结果表明，相较于之前的模型，GMSNet在具有出色的网格平滑性能的同时，仅需要其5%的参数，并且平滑速度是基于优化的方法的13.56倍。

Abstract

In computational fluid dynamics (CFD)

mesh-smoothing methods are widely used to refine the mesh quality for achieving high-precision numerical simulations. Specifically

optimization-based smoothing is used for high-quality mesh smoothing

but it incurs significant computational overhead. Pioneer works have improved its smoothing efficiency by adopting supervised learning to learn smoothing methods from high-quality meshes. However

they pose difficulties in smoothing the mesh nodes with varying degrees and require data augmentation to address the node input sequence problem. Additionally

the required labeled high-quality meshes further limit the applicability of the proposed method. In this paper

we present graph-based smoothing mesh net (GMSNet)

a lightweight neural network model for intelligent mesh smoothing. GMSNet adopts graph neural networks (GNNs) to extract features of the node’s neighbors and outputs the optimal node position. During smoothing

we also introduce a fault-tolerance mechanism to prevent GMSNet from generating negative volume elements. With a lightweight model

GMSNet can effectively smooth mesh nodes with varying degrees and remain unaffected by the order of input data. A novel loss function

MetricLoss

is developed to eliminate the need for high-quality meshes

which provides stable and rapid convergence during training. We compare GMSNet with commonly used mesh-smoothing methods on two-dimensional (2D) triangle meshes. Experimental results show that GMSNet achieves outstanding mesh-smoothing performances with 5% of the model parameters compared to the previous model

but offers a speedup of 13.56 times over the optimization-based smoothing.

关键词

Keywords

references

Baker TJ , 2005 . Mesh generation: art or science ? Prog Aerosp Sci , 41 ( 1 ): 29 - 63 . https://doi.org/10.1016/j.paerosci.2005.02.002 https://doi.org/10.1016/j.paerosci.2005.02.002

Bohn J , Feischl M , 2021 . Recurrent neural networks as optimal mesh refinement strategies . Comput Math Appl , 97 : 61 - 76 . https://doi.org/10.1016/j.camwa.2021.05.018 https://doi.org/10.1016/j.camwa.2021.05.018

Bridgeman J , Jefferson B , Parsons SA , 2010 . The development and application of CFD models for water treatment flocculators . Adv Eng Softw , 41 ( 1 ): 99 - 109 . https://doi.org/10.1016/j.advengsoft.2008.12.007 https://doi.org/10.1016/j.advengsoft.2008.12.007

Cai TL , Luo SJ , Xu KYL , et al. , 2021 . GraphNorm: a principled approach to accelerating graph neural network training . Proc 38 th Int Conf on Machine Learning , p. 1204 - 1215 .

Canann SA , Tristano JR , Staten ML , 1998 . An approach to combined Laplacian and optimization-based smoothing for triangular, quadrilateral, and quad-dominant meshes . Proc 7 th Int Meshing Roundtable , p. 479 - 494 .

Chen L , 2004 . Mesh smoothing schemes based on optimal Delaunay triangulations . Proc IMR , p. 109 - 120 .

Chen XH , Liu J , Pang YF , et al. , 2020 . Developing a new mesh quality evaluation method based on convolutional neural network . Eng Appl Comput Fluid Mech , 14 ( 1 ): 391 - 400 . https://doi.org/10.1080/19942060.2020.1720820 https://doi.org/10.1080/19942060.2020.1720820

Chen XH , Liu J , Gong CY , et al. , 2021 . MVE-Net: an automatic 3-D structured mesh validity evaluation framework using deep neural networks . Comput Aided Des , 141 : 103104 . https://doi.org/10.1016/j.cad.2021.103104 https://doi.org/10.1016/j.cad.2021.103104

Chen XH , Li TJ , Wan Q , et al. , 2022 . MGNet: a novel differential mesh generation method based on unsupervised neural networks . Eng Comput , 38 ( 5 ): 4409 - 4421 . https://doi.org/10.1007/s00366-022-01632-7 https://doi.org/10.1007/s00366-022-01632-7

Chowdhary KR , 2020 . Natural language processing . In: Chowdhary KR (Ed.), Fundamentals of Artificial Intelligence . Springer , New Delhi, India , p. 603 - 649 . https://doi.org/10.1007/978-81-322-3972-7_19 https://doi.org/10.1007/978-81-322-3972-7_19

Damjanović D , Kozak D , Živić M , et al. , 2011 . CFD analysis of concept car in order to improve aerodynamics . A Jövő Járműve , 1 ( 2 ): 67 - 70 .

Daroya R , Atienza R , Cajote R , 2020 . REIN: flexible mesh generation from point clouds . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition Workshops , p. 1444 - 1453 . https://doi.org/10.1109/CVPRW50498.2020.00184 https://doi.org/10.1109/CVPRW50498.2020.00184

Du Q , Gunzburger M , 2002 . Grid generation and optimization based on centroidal Voronoi tessellations . Appl Math Comput , 133 ( 2-3 ): 591 - 607 .

Du Q , Wang DS , 2003 . Tetrahedral mesh generation and optimization based on centroidal Voronoi tessellations . Int J Numer Methods Eng , 56 ( 9 ): 1355 - 1373 . https://doi.org/10.1002/nme.616 https://doi.org/10.1002/nme.616

Du Q , Faber V , Gunzburger M , 1999 . Centroidal Voronoi tessellations: applications and algorithms . SIAM Rev , 41 ( 4 ): 637 - 676 . https://doi.org/10.1137/S0036144599352836 https://doi.org/10.1137/S0036144599352836

Durand R , Pantoja-Rosero BG , Oliveira V , 2019 . A general mesh smoothing method for finite elements . Finite Elem Anal Des , 158 : 17 - 30 . https://doi.org/10.1016/j.finel.2019.01.010 https://doi.org/10.1016/j.finel.2019.01.010

Escobar JM , Montenegro R , Montero G , et al. , 2005 . Smoothing and local refinement techniques for improving tetrahedral mesh quality . Comput Struct , 83 ( 28-30 ): 2423 - 2430 . https://doi.org/10.1016/j.compstruc.2005.03.022 https://doi.org/10.1016/j.compstruc.2005.03.022

Fidkowski KJ , Chen GD , 2021 . Metric-based, goal-oriented mesh adaptation using machine learning . J Comput Phys , 426 : 109957 . https://doi.org/10.1016/j.jcp.2020.109957 https://doi.org/10.1016/j.jcp.2020.109957

Field DA , 1988 . Laplacian smoothing and Delaunay triangulations . Commun Appl Numer Methods , 4 ( 6 ): 709 - 712 . https://doi.org/10.1002/cnm.1630040603 https://doi.org/10.1002/cnm.1630040603

Freitag LA , Knupp PM , 2002 . Tetrahedral mesh improvement via optimization of the element condition number . Int J Numer Methods Eng , 53 ( 6 ): 1377 - 1391 . https://doi.org/10.1002/nme.341 https://doi.org/10.1002/nme.341

Freitag LA , Ollivier-Gooch C , 1997 . Tetrahedral mesh improvement using swapping and smoothing . Int J Numer Methods Eng , 40 ( 21 ): 3979 - 4002 . https://doi.org/10.1002/(SICI)1097-0207(19971115)40:21<3979::AID-NME251>3.0.CO;2-9 https://doi.org/10.1002/(SICI)1097-0207(19971115)40:21<3979::AID-NME251>3.0.CO;2-9 https://doi.org/10.1002/(SICI)1097-0207(19971115)40:21<3979::AID-NME251>3.0.CO;2-9 https://doi.org/10.1002/(SICI)1097-0207(19971115)40:21<3979::AID-NME251>3.0.CO;2-9

Guo YF , Hai YQ , 2021 . Adaptive surface mesh remeshing based on a sphere packing method and a node insertion/deletion method . Appl Math Model , 98 : 1 - 13 . https://doi.org/10.1016/j.apm.2021.05.003 https://doi.org/10.1016/j.apm.2021.05.003

Guo YF , Wang L , Zhao K , et al. , 2020 . An angle-based smoothing method for triangular and tetrahedral meshes . Proc 15 th Chinese Conf on Image and Graphics Technologies and Applications , p. 224 - 234 . https://doi.org/10.1007/978-981-33-6033-4_17 https://doi.org/10.1007/978-981-33-6033-4_17

Guo YF , Wang CR , Ma Z , et al. , 2022 . A new mesh smoothing method based on a neural network . Comput Mech , 69 ( 2 ): 425 - 438 . https://doi.org/10.1007/s00466-021-02097-z https://doi.org/10.1007/s00466-021-02097-z

Hai YQ , Guo YF , Cheng SY , et al. , 2021 . Regular position-oriented method for mesh smoothing . Acta Mech Soli Sin , 34 ( 3 ): 437 - 448 . https://doi.org/10.1007/s10338-020-00201-z https://doi.org/10.1007/s10338-020-00201-z

Han X , Gao H , Pffaf T , et al. , 2022 . Predicting physics in mesh-reduced space with temporal attention . Proc Int Conf on Learning Representations .

Herrmann LR , 1976 . Laplacian-isoparametric grid generation scheme . J Eng Mech Div , 102 ( 5 ): 749 - 756 . https://doi.org/10.1061/JMCEA3.0002158 https://doi.org/10.1061/JMCEA3.0002158

Kingma DP , Ba J , 2015 . Adam: a method for stochastic optimization . Proc 3rd Int Conf on Learning Representations .

Kipf TN , Welling M , 2016 . Semi-supervised classification with graph convolutional networks . https://doi.org/10.48550/arXiv.1609.02907 https://doi.org/10.48550/arXiv.1609.02907

Klingner BM , Shewchuk JR , 2008 . Aggressive tetrahedral mesh improvement . In: Brewer ML , Marcum D (Eds.), Proc 16th International Meshing Roundtable . Springer , Berlin, Germany , p. 3 - 23 . https://doi.org/10.1007/978-3-540-75103-8_1 https://doi.org/10.1007/978-3-540-75103-8_1

Knupp PM , 2001 . Algebraic mesh quality metrics . SIAM J Sci Comput , 23 ( 1 ): 193 - 218 . https://doi.org/10.1137/S1064827500371499 https://doi.org/10.1137/S1064827500371499

LeCun Y , Bengio Y , Hinton G , 2015 . Deep learning . Nature , 521 ( 7553 ): 436 - 444 . https://doi.org/10.1038/nature14539 https://doi.org/10.1038/nature14539

Lee DT , Schachter BJ , 1980 . Two algorithms for constructing a Delaunay triangulation . Int J Comput Inform Sci , 9 ( 3 ): 219 - 242 . https://doi.org/10.1007/BF00977785 https://doi.org/10.1007/BF00977785

Li GH , Müller M , Thabet A , et al. , 2019 . DeepGCNs: can GCNs go as deep as CNNs ? Proc IEEE/CVF Int Conf on Computer Vision , p. 9266 - 9275 . https://doi.org/10.1109/ICCV.2019.00936 https://doi.org/10.1109/ICCV.2019.00936

Liaw R , Liang E , Nishihara R , et al. , 2018 . Tune: a research platform for distributed model selection and training . https://doi.org/10.48550/arXiv.1807.05118 https://doi.org/10.48550/arXiv.1807.05118

Lino M , Cantwell C , Bharath AA , et al. , 2021 . Simulating continuum mechanics with multi-scale graph neural networks . https://doi.org/10.48550/arXiv.2106.04900 https://doi.org/10.48550/arXiv.2106.04900

Liu Y , Wang WP , Lévy B , et al. , 2009 . On centroidal Voronoi tessellation—energy smoothness and fast computation . ACM Trans Graph , 28 ( 4 ): 101 . https://doi.org/10.1145/1559755.1559758 https://doi.org/10.1145/1559755.1559758

Lloyd S , 1982 . Least squares quantization in PCM . IEEE Trans Inform Theory , 28 ( 2 ): 129 - 137 . https://doi.org/10.1109/TIT.1982.1056489 https://doi.org/10.1109/TIT.1982.1056489

Lopes NP , 2023 . Torchy: a tracing JIT compiler for PyTorch . Proc 32nd ACM SIGPLAN Int Conf on Compiler Construction , p. 98 - 109 . https://doi.org/10.1145/3578360.3580266 https://doi.org/10.1145/3578360.3580266

Moukalled F , Mangani L , Darwish M , 2016 . The Finite Volume Method in Computational Fluid Dynamics: an Advanced Introduction with OpenFOAM ® and Matlab . Springer , Cham, Germany , p. 110 - 128 . https://doi.org/10.1007/978-3-319-16874-6 https://doi.org/10.1007/978-3-319-16874-6

Pak M , Kim S , 2017 . A review of deep learning in image recognition . Proc 4th Int Conf on Computer Applications and Information Processing Technology , p. 1 - 3 . https://doi.org/10.1109/CAIPT.2017.8320684 https://doi.org/10.1109/CAIPT.2017.8320684

Pan W , Lu XQ , Gong YH , et al. , 2020 . HLO: half-kernel Laplacian operator for surface smoothing . Comput Aided Des , 121 : 102807 . https://doi.org/10.1016/j.cad.2019.102807 https://doi.org/10.1016/j.cad.2019.102807

Papagiannopoulos A , Clausen P , Avellan F , 2021 . How to teach neural networks to mesh: application on 2-D simplicial contours . Neur Netw , 136 : 152 - 179 . https://doi.org/10.1016/j.neunet.2020.12.019 https://doi.org/10.1016/j.neunet.2020.12.019

Parthasarathy VN , Kodiyalam S , 1991 . A constrained optimization approach to finite element mesh smoothing . Finite Elem Anal Des , 9 ( 4 ): 309 - 320 . https://doi.org/10.1016/0168-874X(91)90004-I https://doi.org/10.1016/0168-874X(91)90004-I

Paszyński M , Grzeszczuk R , Pardo D , et al. , 2021 . Deep learning driven self-adaptive hp finite element method . Proc 21st Int Conf on Computational Science , p. 114 - 121 . https://doi.org/10.1007/978-3-030-77961-0_11 https://doi.org/10.1007/978-3-030-77961-0_11

Peng WH , Yuan ZL , Wang JC , 2022 . Attention-enhanced neural network models for turbulence simulation . Phys Fluids , 34 ( 2 ): 025111 . https://doi.org/10.1063/5.0079302 https://doi.org/10.1063/5.0079302

Pfaff T , Fortunato M , Sanchez-Gonzalez A , et al. , 2021 . Learning mesh-based simulation with graph networks . https://doi.org/10.48550/arXiv.2010.03409 https://doi.org/10.48550/arXiv.2010.03409

Prasad T , 2018 . A Comparative Study of Mesh Smoothing Methods with Flipping in 2D and 3D . MS Thesis, The State University of New Jersey , New Jersey, USA .

Reddy DR , 1976 . Speech recognition by machine: a review . Proc IEEE , 64 ( 4 ): 501 - 531 . https://doi.org/10.1109/PROC.1976.10158 https://doi.org/10.1109/PROC.1976.10158

Samstag RW , Ducoste JJ , Griborio A , et al. , 2016 . CFD for wastewater treatment: an overview . Water Sci Technol , 74 ( 3 ): 549 - 563 . https://doi.org/10.2166/wst.2016.249 https://doi.org/10.2166/wst.2016.249

Sharp N , Crane K , 2020 . A Laplacian for nonmanifold triangle meshes . Comput Graph Forum , 39 ( 5 ): 69 - 80 . https://doi.org/10.1111/cgf.14069 https://doi.org/10.1111/cgf.14069

Song WB , Zhang MR , Wallwork JG , et al. , 2022 . M2N: mesh movement networks for PDE solvers . Proc 36th Conf on Neur Information Processing Systems , p. 7199 - 7210 .

Spalart PR , Venkatakrishnan V , 2016 . On the role and challenges of CFD in the aerospace industry . Aeronaut J , 120 ( 1223 ): 209 - 232 . https://doi.org/10.1017/aer.2015.10 https://doi.org/10.1017/aer.2015.10

Ulyanov D , Vedaldi A , Lempitsky V , 2017 . Instance normalization: the missing ingredient for fast stylization . https://doi.org/10.48550/arXiv.1607.08022 https://doi.org/10.48550/arXiv.1607.08022

Vartziotis D , Papadrakakis M , 2017 . Improved GETMe by adaptive mesh smoothing . Comput Assisted Methods Eng Sci , 20 ( 1 ): 55 - 71

Vartziotis D , Wipper J , 2019 . The GETMe Mesh Smoothing Framework: a Geometric Way to Quality Finite Element Meshes . Taylor & Francis Group , Boca Raton, USA .

Vartziotis D , Athanasiadis T , Goudas I , et al. , 2008 . Mesh smoothing using the geometric element transformation method . Comput Methods Appl Mech Eng , 197 ( 45-48 ): 3760 - 3767 . https://doi.org/10.1016/j.cma.2008.02.028 https://doi.org/10.1016/j.cma.2008.02.028

Vollmer J , Mencl R , Müller H , 1999 . Improved Laplacian smoothing of noisy surface meshes . Comput Graph Forum , 18 ( 3 ): 131 - 138 . https://doi.org/10.1111/1467-8659.00334 https://doi.org/10.1111/1467-8659.00334

Wallwork JG , Lu JY , Zhang MR , et al. , 2022 . E2N: error estimation networks for goal-oriented mesh adaptation . https://doi.org/10.48550/arXiv.2207.11233 https://doi.org/10.48550/arXiv.2207.11233

Wang ZH , Chen XH , Li TJ , et al. , 2022 . Evaluating mesh quality with graph neural networks . Eng Comput , 38 ( 5 ): 4663 - 4673 . https://doi.org/10.1007/s00366-022-01720-8 https://doi.org/10.1007/s00366-022-01720-8

Wu TF , Liu XJ , An W , et al. , 2022 . A mesh optimization method using machine learning technique and variational mesh adaptation . Chin J Aeronaut , 35 ( 3 ): 27 - 41 . https://doi.org/10.1016/j.cja.2021.05.018 https://doi.org/10.1016/j.cja.2021.05.018

Wu ZH , Pan SR , Chen FW , et al. , 2021 . A comprehensive survey on graph neural networks . IEEE Trans Neur Netw Learn Syst , 32 ( 1 ): 4 - 24 . https://doi.org/10.1109/TNNLS.2020.2978386 https://doi.org/10.1109/TNNLS.2020.2978386

Xu KJ , Gao XF , Chen GN , 2017 . Hexahedral mesh quality improvement via edge-angle optimization . Comput Graphics , 70 : 17 - 27 . https://doi.org/10.1016/j.cag.2017.07.002 https://doi.org/10.1016/j.cag.2017.07.002

Zhang YJ , Bajaj C , Xu GL , 2009 . Surface smoothing and quality improvement of quadrilateral/hexahedral meshes with geometric flow . Commun Numer Methods Eng , 25 ( 1 ): 1 - 18 . https://doi.org/10.1002/cnm.1067 https://doi.org/10.1002/cnm.1067

Zhang ZY , Wang YX , Jimack PK , et al. , 2020 . MeshingNet: a new mesh generation method based on deep learning . Proc 20th Int Conf on Computational Science , p. 186 - 198 . https://doi.org/10.1007/978-3-030-50420-5_14 https://doi.org/10.1007/978-3-030-50420-5_14

Zhang ZY , Jimack PK , Wang H , 2021 . MeshingNet3D: efficient generation of adapted tetrahedral meshes for computational mechanics . Adv Eng Softw , 157-158 : 103021 . https://doi.org/10.1016/j.advengsoft.2021.103021 https://doi.org/10.1016/j.advengsoft.2021.103021

Zhou T , Shimada K , 2000 . An angle-based approach to two-dimensional mesh smoothing . Proc IMR , p. 373 - 384 .

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

No data

Related Author

Wenxuan Wang

Yongqin Liu

Xudong Chai

Lin Zhang

Xueying Han

Mingxi Xie

Ke Yu

Xiaohong Huang

Related Institution

School of Automation Science and Electrical Engineering, Beihang University

Department of Control Science and Engineering, Jilin University, Renmin Street 5988

CASICIoud, China Aerospace Science and Industry Corporation Limited

School of Computer Science, Beijing University of Posts and Telecommunications

School of Artificial Intelligence, Beijing University of Posts and Telecommunications

Chat

Address：Zhejiang University Press, 148 Tianmushan Road, Hangzhou, China Postal code：310028
Tel：+86-571-88273162 Email：fitee@zju.edu.cn
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰