Fluid flow reconstruction modeling with application to liquid molding processes

1999 ◽  
Vol 20 (6) ◽  
pp. 809-817 ◽  
Author(s):  
Shawn M. Walsh ◽  
Colin E. Freese
Keyword(s):  
Fluid Flow ◽  
Flow Reconstruction ◽  
Liquid Molding

CARBONATE CEMENTS AS A TOOL FOR FLUID FLOW RECONSTRUCTION: A STUDY IN PARTS OF THE EASTERN ALPS (AUSTRIA, GERMANY, SLOVENIA)

1997 ◽  
pp. 167-181 ◽  
Author(s):  
STEFAN ZEEH ◽  
UWE WALTER ◽  
JOACHIM KUHLEMANN ◽  
UROS HERLEC ◽  
EDDY KEPPENS ◽  
...  
Keyword(s):  
Fluid Flow ◽  
Eastern Alps ◽  
Carbonate Cements ◽  
Flow Reconstruction

3D Fluid Flow Reconstruction Using A Compact Light Field Camera

2021 ◽  
Author(s):  
Yuqi Ding ◽  
Zhong Li ◽  
Yu Ji ◽  
Jingyi Yu ◽  
Jinwei Ye
Keyword(s):  
Fluid Flow ◽  
Light Field ◽  
Flow Reconstruction

Machine learning for fluid flow reconstruction from limited measurements

2021 ◽  
pp. 110733
Author(s):  
Pierre Dubois ◽  
Thomas Gomez ◽  
Laurent Planckaert ◽  
Laurent Perret
Keyword(s):  
Machine Learning ◽  
Fluid Flow ◽  
Flow Reconstruction

scholarly journals Shallow neural networks for fluid flow reconstruction with limited sensors

2020 ◽  
Vol 476 (2238) ◽  
pp. 20200097 ◽  
Author(s):  
N. Benjamin Erichson ◽  
Lionel Mathelin ◽  
Zhewei Yao ◽  
Steven L. Brunton ◽  
Michael W. Mahoney ◽  
...  
Keyword(s):  
Fluid Flow ◽  
Flow Field ◽  
Measurement Data ◽  
Estimation Method ◽  
Data Driven ◽  
Superior Performance ◽  
High Dimensional ◽  
Approximation Techniques ◽  
Flow Reconstruction ◽  
Monitoring Technologies

In many applications, it is important to reconstruct a fluid flow field, or some other high-dimensional state, from limited measurements and limited data. In this work, we propose a shallow neural network-based learning methodology for such fluid flow reconstruction. Our approach learns an end-to-end mapping between the sensor measurements and the high-dimensional fluid flow field, without any heavy preprocessing on the raw data. No prior knowledge is assumed to be available, and the estimation method is purely data-driven. We demonstrate the performance on three examples in fluid mechanics and oceanography, showing that this modern data-driven approach outperforms traditional modal approximation techniques which are commonly used for flow reconstruction. Not only does the proposed method show superior performance characteristics, it can also produce a comparable level of performance to traditional methods in the area, using significantly fewer sensors. Thus, the mathematical architecture is ideal for emerging global monitoring technologies where measurement data are often limited.

Sign in / Sign up

Export Citation Format

Share Document