arrow
返回

An unsupervised data completion method for physically-based data-driven models

delete2019-02-01
delete12
delete
OA
AI
J
Jacobo Ayensa-Jiménez
M
Mohamed H. Doweidar
J
Jose A. Sanz‐Herrera
M
M. Doblaré *
DOI:10.1016/j.cma.2018.09.035delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Data-driven methods are an innovative model-free approach for engineering and sciences, still in process of maturation. The idea behind is the combination of data analytics techniques, to handle the huge amount of data derived from continuous monitoring or experimental measurements, and of the constraints imposed by universal physical laws, particular to the field in hands. A well-known problem in the former corresponds to the quality and completeness of the available data that, sometimes, are so poor that make the predictions useless. In data-driven simulation-based engineering and sciences (DDSBES), the intrinsic physical constraints may help in completing the missing data in a more precise manner, by forcing them to remain in the manifold defined by the physical laws. In this work, a suitable imputation method to complete incomplete data that preserves the data context-dependent structure is presented. This is accomplished by enforcing the data to fulfill the set of physical constraints, specific to the problem. For this purpose, a generalization of the weighted mean concept is proposed, where the distance to the admissible points (in a physical sense) is used as a weighting function to get the optimal candidate. The method is evaluated in a classical regression problem, where it is compared with other standard methods, showing better results. Then, its application is illustrated in two data-driven problems, where no filling data procedure has been yet proposed, showing good predictive capability, provided that the data are close enough to the actual system state. (C) 2018 Elsevier B.V. All rights reserved.
Keyword:
Data-driven methods
Data completion
Statistical imputation
Weighted mean
Computational mechanics
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Computer Methods in Applied Mechanics and Engineering 封面图
Computer Methods in Applied Mechanics and Engineering
IF:
7.3
论文数:
1.3W
被引数:
7.5W

机构

U
University of Zaragoza
学者数:
325
论文数: 149
被引数: 6.7K
C
ciber-bbn
学者数:
0
论文数: 1
被引数: 4
引用论文

引用论文

Vision Based Robot Assistance in TTTS Fetal Surgery
err2019-07-01
err0
errOAAI
errNarcis Sayols; Albert Hernansanz; Johanna Parra; Elisenda Eixarch; Eduard Gratacos; Josep Amat; Alicia Casals
err分享
err收藏
Preliminary report on a mass screening program for neonatal hypothyroidism
err1975-05-01
err0
PREAI
errJean H. Dussault; Pierre Coulombe; Claude Laberge; Jacques Letarte; Harvey Guyda; Khalil Khoury
err分享
err收藏
A new reliability-based data-driven approach for noisy experimental data with physical constraints
err2018-01-01
err38
errOAAI
errAyensa-Jimenez, Jacobo; Doweidar, Mohamed H.; Sanz-Herrera, Jose A.; Doblare, Manuel
err分享
err收藏
Relativistic effects on ground state properties of 4d and 5d transition metals
err1999-01-01
err0
PREAI
errC Elsasser; N Takeuchi; K M Ho; C T Chan; P Braun; M Fahnle
err分享
err收藏
学者 查看更多内容