Modeling two-phase flows with complicated interface evolution using parallel physics-informed neural networks
文献类型：期刊论文
| 作者 | Qiu RD(丘润荻)6,7; Dong, Haosen5; Wang JZ(王静竹)4,7; Fan, Chun1,2,3 ; Wang YW(王一伟)4,6,7
|
| 刊名 | PHYSICS OF FLUIDS
 |
| 出版日期 | 2024-09-01 |
| 卷号 | 36期号:9页码:16 |
| ISSN号 | 1070-6631 |
| DOI | 10.1063/5.0216609 |
| 通讯作者 | Wang, Yiwei(wangyw@imech.ac.cn) |
| 英文摘要 | The physics-informed neural networks (PINNs) have shown great potential in solving a variety of high-dimensional partial differential equations (PDEs), but the complexity of a realistic problem still restricts the practical application of the PINNs for solving most complicated PDEs. In this paper, we propose a parallel framework for PINNs that is capable of modeling two-phase flows with complicated interface evolution. The proposed framework divides the problem into several simplified subproblems and solves them through training several PINNs on corresponding subdomains simultaneously. To enhance the accuracy of the parallel training framework in two-phase flow, the overlapping domain decomposition method is adopted. The optimal subnetwork sizes and partitioned method are systematically discussed, and a series of cases including a bubble rising, droplet splashing, and the Rayleigh-Taylor instability are applied for quantitative validation. The maximum relative error of quantitative values in these cases is 0.1319. Our results show that the proposed framework not only can accelerate the training procedure of PINNs, but also can capture the spatiotemporal evolution of the interface between various phases. This framework overcomes the difficulties of training PINNs to solve a forward problem in two-phase flow, and it is expected to model more realistic dynamic systems in nature. |
| 分类号 | 一类/力学重要期刊 |
| WOS关键词 | DEEP LEARNING FRAMEWORK ; BENCHMARK COMPUTATIONS ; NONUNIFORM SYSTEM ; INVERSE PROBLEMS ; FREE-ENERGY ; SCHEME ; SIMULATIONS ; IMPACT ; XPINNS ; DROP |
| 资助项目 | National Natural Science Foundation of China10.13039/501100001809[12293000] ; National Natural Science Foundation of China10.13039/501100001809[12293003] ; National Natural Science Foundation of China10.13039/501100001809[12293004] ; National Natural Science Foundation of China10.13039/501100001809[12122214] ; National Natural Science Foundation of China10.13039/501100001809[U22B6010] ; National Natural Science Foundation of China[2022019] ; Youth Innovation Promotion Association of Chinese Academy of Sciences |
| WOS研究方向 | Mechanics ; Physics |
| 语种 | 英语 |
| WOS记录号 | WOS:001314649000026 |
| 资助机构 | National Natural Science Foundation of China10.13039/501100001809 ; National Natural Science Foundation of China ; Youth Innovation Promotion Association of Chinese Academy of Sciences |
| 其他责任者 | Wang, Yiwei |
| 源URL | [http://dspace.imech.ac.cn/handle/311007/97154]  |
| 专题 | 力学研究所_流固耦合系统力学重点实验室(2012-) |
| 作者单位 | 1.Peking Univ, Natl Biomed Imaging Ctr, Beijing 100871, Peoples R China 2.Peking Univ, Changsha Inst Comp & Digital Econ, Changsha 410000, Peoples R China; 3.Peking Univ, Comp Ctr, Beijing 100871, Peoples R China; 4.Univ Chinese Acad Sci, Sch Engn Sci, Beijing 100049, Peoples R China; 5.Peking Univ, Sch Software & Microelect, Beijing 100871, Peoples R China; 6.Univ Chinese Acad Sci, Sch Future Technol, Beijing 100049, Peoples R China; 7.Chinese Acad Sci, Key Lab Mech Fluid Solid Coupling Syst, Inst Mech, Beijing 100190, Peoples R China; |
| 推荐引用方式 GB/T 7714 | Qiu RD,Dong, Haosen,Wang JZ,et al. Modeling two-phase flows with complicated interface evolution using parallel physics-informed neural networks[J]. PHYSICS OF FLUIDS,2024,36(9):16. |
| APA | 丘润荻,Dong, Haosen,王静竹,Fan, Chun,&王一伟.(2024).Modeling two-phase flows with complicated interface evolution using parallel physics-informed neural networks.PHYSICS OF FLUIDS,36(9),16. |
| MLA | 丘润荻,et al."Modeling two-phase flows with complicated interface evolution using parallel physics-informed neural networks".PHYSICS OF FLUIDS 36.9(2024):16. |
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。