A framework for learning symbolic turbulence models from indirect observation data via neural networks and feature importance analysis
文献类型：期刊论文
| 作者 | Wu CT(吴楚畋)1,2; Zhang XL(张鑫磊)1,2; Xu D(徐多)1,2 ; He GW(何国威)1,2
|
| 刊名 | JOURNAL OF COMPUTATIONAL PHYSICS
 |
| 出版日期 | 2025-09-15 |
| 卷号 | 537页码:22 |
| 关键词 | Turbulence model Ensemble Kalman method Symbolic regression Feature importance analysis Neural networks |
| ISSN号 | 0021-9991 |
| DOI | 10.1016/j.jcp.2025.114068 |
| 通讯作者 | Zhang, Xin-Lei(zhangxinlei@imech.ac.cn) |
| 英文摘要 | Learning symbolic turbulence models from indirect observation data is of significant interest as it not only improves the accuracy of posterior prediction but also provides explicit model formulations with good interpretability. However, it typically resorts to gradient-free evolutionary algorithms, which can be relatively inefficient compared to gradient-based approaches, particularly when the Reynolds-averaged Navier-Stokes (RANS) simulations are involved in the training process. In view of this difficulty, we propose a framework that uses neural networks and the associated feature importance analysis to improve the efficiency of symbolic turbulence modeling. In doing so, the gradient-based method can be used to efficiently learn neural networkbased representations of Reynolds stress from indirect data, which is further transformed into simplified mathematical expressions with symbolic regression. Moreover, feature importance analysis is introduced to accelerate the convergence of symbolic regression by excluding insignificant input features. The proposed training strategy is tested in the flow in a square duct, where it correctly learns underlying analytic models from indirect velocity data. Further, the method is applied in the flow over the periodic hills, demonstrating that the feature importance analysis can significantly improve the training efficiency and learn symbolic turbulence models with satisfactory generalizability. |
| 分类号 | 一类/力学重要期刊 |
| WOS关键词 | FLOWS |
| 资助项目 | NSFC Basic Science Center Program for 'Multiscale Problems in Nonlinear Mechanics'[12588201] ; NSFC Basic Science Center Program for 'Multiscale Problems in Nonlinear Mechanics'[11988102] ; National Natural Science Foundation of China[12102435] ; CAS Project for Young Scientists in Basic Research[YSBR-087] ; Young Elite Scientists Sponsorship Program by CAST[2022QNRC001] |
| WOS研究方向 | Computer Science ; Physics |
| 语种 | 英语 |
| WOS记录号 | WOS:001499588400001 |
| 资助机构 | NSFC Basic Science Center Program for 'Multiscale Problems in Nonlinear Mechanics' ; National Natural Science Foundation of China ; CAS Project for Young Scientists in Basic Research ; Young Elite Scientists Sponsorship Program by CAST |
| 其他责任者 | 张鑫磊 |
| 源URL | [http://dspace.imech.ac.cn/handle/311007/101745]  |
| 专题 | 力学研究所_非线性力学国家重点实验室 |
| 作者单位 | 1.Univ Chinese Acad Sci, Sch Engn Sci, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Mech, State Key Lab Nonlinear Mech, Beijing 100190, Peoples R China; |
| 推荐引用方式 GB/T 7714 | Wu CT,Zhang XL,Xu D,et al. A framework for learning symbolic turbulence models from indirect observation data via neural networks and feature importance analysis[J]. JOURNAL OF COMPUTATIONAL PHYSICS,2025,537:22. |
| APA | 吴楚畋,张鑫磊,徐多,&何国威.(2025).A framework for learning symbolic turbulence models from indirect observation data via neural networks and feature importance analysis.JOURNAL OF COMPUTATIONAL PHYSICS,537,22. |
| MLA | 吴楚畋,et al."A framework for learning symbolic turbulence models from indirect observation data via neural networks and feature importance analysis".JOURNAL OF COMPUTATIONAL PHYSICS 537(2025):22. |
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。