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. 非线性力学国家重点实验室
Combining direct and indirect sparse data for learning generalizable turbulence models

文献类型：期刊论文

作者Zhang XL(张鑫磊); Xiao, Heng; Luo, Xiaodong; He GW(何国威)
刊名JOURNAL OF COMPUTATIONAL PHYSICS
出版日期2023-09-15
卷号489页码:112272
ISSN号0021-9991
关键词Ensemble Kalman method Turbulence modeling Direct data Indirect data
DOI10.1016/j.jcp.2023.112272
英文摘要Learning turbulence models from observation data is of significant interest in discovering a unified model for a broad range of practical flow applications. Either the direct observation of Reynolds stress or the indirect observation of velocity has been used to improve the predictive capacity of turbulence models. In this work, we propose combining the direct and indirect sparse data to train neural network-based turbulence models. The backpropagation technique and the observation augmentation approach are used to train turbulence models with different observation data in a unified ensemble-based framework. These two types of observation data can explore synergy to constrain the model training in different observation spaces, which enables learning generalizable models from very sparse data. The present method is tested in secondary flows in a square duct and separated flows over periodic hills. Both cases demonstrate that combining direct and indirect observations is able to improve the generalizability of the learned model in similar flow configurations, compared to using only indirect data. The ensemble-based method can serve as a practical tool for model learning from different types of observations due to its non-intrusive and derivative-free nature.
分类号一类/力学重要期刊
WOS研究方向Computer Science ; Physics
语种英语
WOS记录号WOS:001028900500001
资助机构NSFC Basic Science Center Program for Multiscale Problems in Nonlinear Mechanics [11988102] ; National Natural Science Foundation of China [12102435] ; China Postdoctoral Science Foundation [2021M690154] ; Research Council of Norway [331644] ; National Centre for Sustainable Subsurface Utilization of the Norwegian Continental Shelf, Norway - Research Council of Norway ; [NCS2030]
其他责任者He, GW (corresponding author), Chinese Acad Sci, Inst Mech, State Key Lab Nonlinear Mech, Beijing 100190, Peoples R China. ; He, GW (corresponding author), Univ Chinese Acad Sci, Sch Engn Sci, Beijing 100049, Peoples R China. ; Xiao, H (corresponding author), Univ Stuttgart, Stuttgart Ctr Simulat Sci SC SimTech, D-70569 Stuttgart, Germany.
源URL[http://dspace.imech.ac.cn/handle/311007/92554]  
专题力学研究所_非线性力学国家重点实验室
作者单位1.{Luo, Xiaodong} Norwegian Res Ctr NORCE, N-5008 Bergen, Norway
2.{Zhang, Xin-Lei, He, Guowei} Chinese Acad Sci, Inst Mech, State Key Lab Nonlinear Mech, Beijing 100190, Peoples R China
3.{Zhang, Xin-Lei, He, Guowei} Univ Chinese Acad Sci, Sch Engn Sci, Beijing 100049, Peoples R China
4.{Xiao, Heng} Univ Stuttgart, Stuttgart Ctr Simulat Sci SC SimTech, D-70569 Stuttgart, Germany
推荐引用方式
GB/T 7714		 Zhang XL,Xiao, Heng,Luo, Xiaodong,et al. Combining direct and indirect sparse data for learning generalizable turbulence models[J]. JOURNAL OF COMPUTATIONAL PHYSICS,2023,489:112272.
APA 张鑫磊,Xiao, Heng,Luo, Xiaodong,&何国威.(2023).Combining direct and indirect sparse data for learning generalizable turbulence models.JOURNAL OF COMPUTATIONAL PHYSICS,489,112272.
MLA 张鑫磊,et al."Combining direct and indirect sparse data for learning generalizable turbulence models".JOURNAL OF COMPUTATIONAL PHYSICS 489(2023):112272.

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。