中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 力学研究所
  3. 中国科学院力学研究所
  4. 流固耦合系统力学重点实验室(2012-)
On the preprocessing of physics-informed neural networks: How to better utilize data in fluid mechanics

文献类型：期刊论文

作者Xu SF(许盛峰)1,2; Dai, Yuanjun3; Yan C(闫畅)1,4; Sun ZX(孙振旭)1; Huang RF(黄仁芳)1; Guo DL(郭迪龙)1; Yang GW(杨国伟)1
刊名JOURNAL OF COMPUTATIONAL PHYSICS
出版日期2025-05-01
卷号528
ISSN号0021-9991
DOI10.1016/j.jcp.2025.113837
英文摘要Physics-Informed Neural Networks (PINNs) serve as a flexible alternative for tackling forward and inverse problems in differential equations, displaying impressive advancements in diverse areas of applied mathematics. Despite integrating both data and underlying physics to enrich the neural network's understanding, concerns regarding the effectiveness and practicality of PINNs persist. Over the past few years, extensive efforts in the current literature have been made to enhance this evolving method, by drawing inspiration from both machine learning algorithms and numerical methods. Despite notable progressions in PINNs algorithms, the important and fundamental field of data preprocessing remain unexplored, limiting the applications of PINNs especially in solving inverse problems. Therefore in this paper, a concise yet potent data preprocessing method focusing on data normalization was proposed. By applying a linear transformation to both the data and corresponding equations concurrently, the normalized PINNs approach was evaluated on the task of reconstructing flow fields in four turbulent cases. The results illustrate that by adhering to the data preprocessing procedure, PINNs can robustly achieve higher prediction accuracy for all flow quantities under different hyperparameter setups, without incurring extra computational cost, distinctly improving the utilization of limited training data. Though mainly verified in NavierStokes (NS) equations, this method holds potential for application to various other equations.
分类号一类/力学重要期刊
WOS研究方向Computer Science, Interdisciplinary Applications ; Physics, Mathematical ; Computer Science ; Physics
语种英语
WOS记录号WOS:001428647900001
资助机构This work was supported by National Key Research and Development Project (Grant No. 2022YFB2603400) , China National Railway Group Science and Technology Program (Grant No. K2023J047) , and the International Partnership Program of Chinese Academy of Sciences (Grant No. 025GJHZ2022118 FN) .
其他责任者孙振旭
源URL[http://dspace.imech.ac.cn/handle/311007/101438]  
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.Institute of Mechanics, CAS;
2.National University of Singapore;
3.Peking University;
4.University of Chinese Academy of Sciences, CAS;
5.Institute of Mechanics, CAS
推荐引用方式
GB/T 7714		 Xu SF,Dai, Yuanjun,Yan C,et al. On the preprocessing of physics-informed neural networks: How to better utilize data in fluid mechanics[J]. JOURNAL OF COMPUTATIONAL PHYSICS,2025,528.
APA 许盛峰.,Dai, Yuanjun.,闫畅.,孙振旭.,黄仁芳.,...&杨国伟.(2025).On the preprocessing of physics-informed neural networks: How to better utilize data in fluid mechanics.JOURNAL OF COMPUTATIONAL PHYSICS,528.
MLA 许盛峰,et al."On the preprocessing of physics-informed neural networks: How to better utilize data in fluid mechanics".JOURNAL OF COMPUTATIONAL PHYSICS 528(2025).

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。