Data-driven discovery of dimensionless numbers and governing laws from scarce measurements

Xiaoyu Xie; Arash Samaei; Jiachen Guo; Wing Kam Liu; Zhengtao Gan

doi:10.1038/s41467-022-35084-w

Nature Communications (Dec 2022)

Data-driven discovery of dimensionless numbers and governing laws from scarce measurements

Xiaoyu Xie,
Arash Samaei,
Jiachen Guo,
Wing Kam Liu,
Zhengtao Gan

Affiliations

Xiaoyu Xie: Department of Mechanical Engineering, Northwestern University
Arash Samaei: Department of Mechanical Engineering, Northwestern University
Jiachen Guo: Theoretical and Applied Mechanics, Northwestern University
Wing Kam Liu: Department of Mechanical Engineering, Northwestern University
Zhengtao Gan: Department of Mechanical Engineering, Northwestern University

DOI: https://doi.org/10.1038/s41467-022-35084-w
Journal volume & issue: Vol. 13, no. 1
pp. 1 – 11

Abstract

Read online

Dimension reduction techniques allow to simplify complex process design and system optimization in various engineering problems. The authors propose here a machine learning approach to discover dominant dimensionless numbers and governing laws from scarce measurement data.

Published in Nature Communications

ISSN: 2041-1723 (Online)
Publisher: Nature Portfolio
Country of publisher: United Kingdom
LCC subjects: Science
Website: https://www.nature.com/ncomms/

About the journal