Accelerating fluid simulations with graph convolution network predicted flow fields
文献类型：期刊论文
| 作者 | Lim, Wei Xian4; Jessica, Loh Sher En3; Lv Y(吕钰)2; Kong, Adams WaiKin3,4; Chan, Wai Lee1,4 |
| 刊名 | AEROSPACE SCIENCE AND TECHNOLOGY
 |
| 出版日期 | 2025-09-01 |
| 卷号 | 164页码:12 |
| 关键词 | Deep learning Graph convolution networks Reynolds-averaged Navier-Stokes simulations Flow initialization |
| ISSN号 | 1270-9638 |
| DOI | 10.1016/j.ast.2025.110414 |
| 通讯作者 | Chan, Wai Lee(chan.wl@ntu.edu.sg) |
| 英文摘要 | The field of computational fluid dynamics (CFD) is integral to engineering disciplines, particularly for designing systems that operate under complex fluid flow conditions. Accurate simulation of flow fields is essential for optimizing performance across a variety of applications, including aviation, automotive, marine, and renewable energy sectors. Recent advancements in deep learning, particularly graph convolution networks (GCNs), offer promising alternatives for improving simulation processes. This work introduces a novel approach to accelerating fluid simulations using GCNs for flow field initialization. To this end, two different GCN models were employed, incorporating prior knowledge of the problem like its boundary conditions, as well as residual training. Extensive experiments using over 2000 sets of simulation results of various NACA airfoil shapes and flow conditions demonstrate that GCN-based initialization significantly reduces computational resources while maintaining high accuracy, achieving a 30% - 50% reduction in simulation time compared to conventional CFD initialization method. |
| 分类号 | 一类 |
| 资助项目 | RIE2020 Industry Alignment Fund Industry Collaboration Projects (IAF-ICP) Funding Initiative[11801E0033] ; Rolls-Royce Singapore Pte Ltd |
| WOS研究方向 | Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:001511712000001 |
| 资助机构 | RIE2020 Industry Alignment Fund Industry Collaboration Projects (IAF-ICP) Funding Initiative ; Rolls-Royce Singapore Pte Ltd |
| 其他责任者 | Chan, Wai Lee |
| 源URL | [http://dspace.imech.ac.cn/handle/311007/101847]  |
| 专题 | 力学研究所_非线性力学国家重点实验室 |
| 作者单位 | 1.Nanyang Technol Univ, Sch Mech & Aerosp Engn, Nanyang 639798, Singapore 2.Chinese Acad Sci, Inst Mech, State Key Lab Nonlinear Mech, Beijing 100190, Peoples R China; 3.Nanyang Technol Univ, Coll Comp & Data Sci, Singapore 639798, Singapore; 4.Nanyang Technol Univ, Rolls Royce NTU Corp Lab, Singapore 637460, Singapore; |
| 推荐引用方式 GB/T 7714 | Lim, Wei Xian,Jessica, Loh Sher En,Lv Y,et al. Accelerating fluid simulations with graph convolution network predicted flow fields[J]. AEROSPACE SCIENCE AND TECHNOLOGY,2025,164:12. |
| APA | Lim, Wei Xian,Jessica, Loh Sher En,吕钰,Kong, Adams WaiKin,&Chan, Wai Lee.(2025).Accelerating fluid simulations with graph convolution network predicted flow fields.AEROSPACE SCIENCE AND TECHNOLOGY,164,12. |
| MLA | Lim, Wei Xian,et al."Accelerating fluid simulations with graph convolution network predicted flow fields".AEROSPACE SCIENCE AND TECHNOLOGY 164(2025):12. |
入库方式： OAI收割
来源：力学研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。