Flow2Mesh: A flow-guided data-driven mesh adaptation framework

被引:0
|
作者
Yu, Jian [1 ]
Lyu, Hongqiang [2 ]
Xu, Ran [1 ]
Ouyang, Wenxuan [2 ]
Liu, Xuejun [1 ]
机构
[1] Nanjing Univ Aeronaut & Astronaut, Coll Comp Sci & Technol, Minist Ind & Informat Technol, Key Lab Pattern Anal & Machine Intelligence, Nanjing 211106, Peoples R China
[2] Nanjing Univ Aeronaut & Astronaut, Coll Aerosp Engn, Nanjing 211106, Peoples R China
关键词
FINITE-ELEMENT METHODS;
D O I
10.1063/5.0188690
中图分类号
O3 [力学];
学科分类号
08 ; 0801 ;
摘要
Mesh adaptation is crucial in numerical simulation, providing optimal resource allocation for accurately capturing physical phenomena. However, when applied to Computational Fluid Dynamics (CFD) problems with complex multi-scale properties, existing adaptation methods face huge challenges due to the high computational cost of solving auxiliary partial differential equations (PDEs) and the difficulty in aligning the flow features with mesh geometric features. In this work, an end-to-end data-driven mesh adaptation framework, Flow2Mesh, is proposed to address these challenges by adopting a hybrid modeling strategy to construct the mapping from pixelated flow-fields to graph-based meshes. It achieves a rapid and accurate one-step mesh adaptation via a perceptual feature network (PFN) and a mesh movement network (MMN). PFN extracts the global perceptual features from flow-fields to enhance flow feature representation and mesh resolution independence. In MMN, these features are utilized to deform the initial mesh to a topology-invariant adaptive mesh by a proposed physically driven mesh convolutional network. It considers the inherent mesh geometric information for efficient node feature aggregation and alignment of mesh density with a flow-field structure. To generate high-quality adaptive meshes, various mesh-related losses are designed to regularize the mesh movement and alleviate the mesh tangling. Experiments in CFD scenarios demonstrate the generalization of our model to different design parameters and mesh configurations. It takes three orders of magnitude less time to generate similar meshes than the PDE-based method. The results exhibit the potential of Flow2Mesh to be a flexible and reliable tool for rapid mesh adaptation in scientific and industrial fields.
引用
下载
收藏
页数:20
相关论文
共 50 条
  • [21] A data assimilation framework for data-driven flow models enabled by motion tomography
    Chang, Dongsik
    Edwards, Catherine R.
    Zhang, Fumin
    Sun, Jing
    INTERNATIONAL JOURNAL OF INTELLIGENT ROBOTICS AND APPLICATIONS, 2019, 3 (02) : 158 - 177
  • [22] A data assimilation framework for data-driven flow models enabled by motion tomography
    Dongsik Chang
    Catherine R. Edwards
    Fumin Zhang
    Jing Sun
    International Journal of Intelligent Robotics and Applications, 2019, 3 : 158 - 177
  • [23] Distributed Modeling in a MapReduce Framework for Data-Driven Traffic Flow Forecasting
    Chen, Cheng
    Liu, Zhong
    Lin, Wei-Hua
    Li, Shuangshuang
    Wang, Kai
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2013, 14 (01) : 22 - 33
  • [24] DATA-DRIVEN COMPENSATION FOR 2 COLOR FLOW CYTOMETRY
    van Rodijnen, N.
    Hoop, S.
    Nap, M.
    CYTOMETRY PART B-CLINICAL CYTOMETRY, 2008, 74B (06) : 411 - 411
  • [25] A parallel unstructured mesh adaptation for unsteady compressible flow simulations
    Kinoshita, T
    Inoue, O
    PARALLEL COMPUTATIONAL FLUID DYNAMICS: RECENT DEVELOPMENTS AND ADVANCES USING PARALLEL COMPUTERS, 1998, : 65 - 72
  • [26] Mesh adaptation for simulation of unsteady flow with moving immersed boundaries
    Zhou, C. H.
    Ai, J. Q.
    INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN FLUIDS, 2013, 72 (04) : 453 - 477
  • [27] Algorithm for Mesh Adaptation to a Flow Field with a Bow Shock Wave
    I. V. Voronich
    N. S. Smirnova
    V. A. Titarev
    Computational Mathematics and Mathematical Physics, 2024, 64 (9) : 2111 - 2120
  • [28] Dynamical mesh adaptation for two-dimensional unsteady flow
    Mazaheri, K
    Lesani, B
    COMPUTATIONAL FLUID DYNAMICS '98, VOL 1, PARTS 1 AND 2, 1998, : 108 - 113
  • [29] Application of mesh-adaptation for pollutant transport by water flow
    Benkhaldoun, Fayssal
    Elmahi, Imad
    Seaid, Mohammed
    MATHEMATICS AND COMPUTERS IN SIMULATION, 2009, 79 (12) : 3415 - 3423
  • [30] Verification of Anisotropic Mesh Adaptation for Unsteady Mixing and Reacting flow
    Zou, Jianfeng
    Zhou, Chenglin
    Zhang, Yang
    Zheng, Yao
    AIAA JOURNAL, 2021, 59 (10) : 4071 - 4085