Mutual-information-based dimensional learning: Objective algorithms for identification of relevant dimensionless quantities
文献类型：期刊论文
| 作者 | Zhang L(张磊)1; He GW(何国威)1,2
|
| 刊名 | COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
 |
| 出版日期 | 2025-05-01 |
| 卷号 | 440页码:117922 |
| 关键词 | Data-driven dimensional analysis Mutual information Objectivity Machine learning |
| ISSN号 | 0045-7825 |
| DOI | 10.1016/j.cma.2025.117922 |
| 英文摘要 | The classical dimensional analysis provides powerful insights into underlying physical mechanisms, but has limitations in determining the uniqueness and measuring the relative importance of dimensionless quantities. To address these limitations, we propose a data-driven approach, called mutual-information-based dimensional learning, to identify unique and relevant dimensionless quantities from available data. The proposed method employs a novel information- theoretic criterion to measure the relative importance of dimensionless quantities, whereas the existing methodologies rely on sensitivity/derivative-based measures. This entropy-based measure provides two significant advantages: (1) invariance (objectivity) with respect to reparametrizations of variables, and (2) robustness against outliers. Numerical results show that our method outperforms the current state-of-the-art method in these aspects, and enables identifying dominant dimensionless quantities. Examples include the study of the friction factor in benchmark pipe flows, the eddy viscosity coefficients in turbulent channel flows and the vapor depression dynamics in laser-metal interaction. |
| 分类号 | 一类 |
| WOS研究方向 | Engineering, Multidisciplinary ; Mathematics, Interdisciplinary Applications ; Mechanics ; Engineering ; Mathematics |
| 语种 | 英语 |
| WOS记录号 | WOS:001450168100001 |
| 资助机构 | This research was supported by the National Natural Science Foundation of China Basic Science Center Program for Multiscale Problems in Nonlinear Mechanics, Grant No. 11988102. L. Zhang was also supported by the National Natural Science Foundation of China under Grant No. 12202451. |
| 其他责任者 | 何国威 |
| 源URL | [http://dspace.imech.ac.cn/handle/311007/101443]  |
| 专题 | 力学研究所_非线性力学国家重点实验室 |
| 作者单位 | 1.中国科学院力学研究所; 2.中国科学院大学 |
| 推荐引用方式 GB/T 7714 | Zhang L,He GW. Mutual-information-based dimensional learning: Objective algorithms for identification of relevant dimensionless quantities[J]. COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING,2025,440:117922. |
| APA | 张磊,&何国威.(2025).Mutual-information-based dimensional learning: Objective algorithms for identification of relevant dimensionless quantities.COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING,440,117922. |
| MLA | 张磊,et al."Mutual-information-based dimensional learning: Objective algorithms for identification of relevant dimensionless quantities".COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING 440(2025):117922. |
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。