Identification of a steady-state flow in porous media using artificial neural networks

Marek J. Lefik, Daniela P. Boso, Bernhard A. Schrefler

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

For a steady state convection problem, assuming given concentration field values in a few measurement points and hydraulic head values in the same piezometers, the source of the concentration, and its intensity are deduced using Artificial Neural Networks (ANNs). ANNs are trained with data extracted from Finite Difference (FD) solution of a classical convection problem for small Peclet number. The numerical analysis is exemplified for vanishing, homogeneous and non-homogeneous field of velocity. It is shown that the diffusivity vector can also be identified. The complexity of the problem is discussed for each studied case.

Original languageEnglish (US)
Title of host publicationASME 2012 11th Biennial Conference on Engineering Systems Design and Analysis, ESDA 2012
Pages89-95
Number of pages7
Volume1
DOIs
StatePublished - Dec 1 2012
EventASME 2012 11th Biennial Conference on Engineering Systems Design and Analysis, ESDA 2012 - Nantes, France
Duration: Jul 2 2012Jul 4 2012

Other

OtherASME 2012 11th Biennial Conference on Engineering Systems Design and Analysis, ESDA 2012
CountryFrance
CityNantes
Period7/2/127/4/12

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Mechanical Engineering

Fingerprint Dive into the research topics of 'Identification of a steady-state flow in porous media using artificial neural networks'. Together they form a unique fingerprint.

Cite this