Доступ предоставлен для: Guest
Портал Begell Электронная Бибилиотека e-Книги Журналы Справочники и Сборники статей Коллекции
Journal of Porous Media
Импакт фактор: 1.49 5-летний Импакт фактор: 1.159 SJR: 0.43 SNIP: 0.671 CiteScore™: 1.58

ISSN Печать: 1091-028X
ISSN Онлайн: 1934-0508

Выпуски:
Том 22, 2019 Том 21, 2018 Том 20, 2017 Том 19, 2016 Том 18, 2015 Том 17, 2014 Том 16, 2013 Том 15, 2012 Том 14, 2011 Том 13, 2010 Том 12, 2009 Том 11, 2008 Том 10, 2007 Том 9, 2006 Том 8, 2005 Том 7, 2004 Том 6, 2003 Том 5, 2002 Том 4, 2001 Том 3, 2000 Том 2, 1999 Том 1, 1998

Journal of Porous Media

DOI: 10.1615/JPorMedia.v17.i5.50
pages 431-438

NEURAL-NETWORK METAMODELLING FOR THE PREDICTION OF THE PRESSURE DROP OF A FLUID PASSING THROUGH METALLIC POROUS MEDIUM

Eddy EL Tabach
PRISME Laboratory, University of Orleans, 63 Avenue de Lattre de Tassigny, 18000 Bourges, France
Nicolas Gascoin
PRISME Laboratory, INSA-Centre Val de Loire, 88 boulevard Lahitolle, 18000 Bourges, France
Philippe Gillard
PRISME, IUT Bourges, 63, avenue de Lattre de Tassigny, 18000 Bourges, France

Краткое описание

The pressure drop across metallic porous mediums is a critical element in cooling aerospace engineering applications. This paper presents a metamodel based on artificial neural networks (ANNs) for estimating the pressure drop through metallic porous media. The ANN is developed using experimental data obtained from an experimental bench, developed at PRISME Laboratory, which ensures the monitoring of temperature, pressure, and mass flow rate in stationary and transient conditions. For each case the gas pressure which crosses the metallic porous material is measured as a function of inlet gas pressure, gas mass flow rate, and temperature. The optimal feedforward ANN architecture with error backpropagation (BPNN) was determined by the cross-validation method. The ANN architecture having 35 hidden neurons gives the best choice. Comparing the modelled values by ANN with the experimental data indicates that the neural-network model provides accurate results. The performance of the ANN model is compared with a metamodelling method using the multilinear regression approximation.


Articles with similar content:

A NOVEL DESIGN FOR VERTICAL AXIS WIND TURBINE
Second Thermal and Fluids Engineering Conference, Vol.17, 2017, issue
Luz Amaya, Reza Ghodsi
APPLICABILITY OF ARTIFICIAL NEURAL NETWORKS TO PREDICT EFFECTIVE THERMAL CONDUCTIVITY OF HIGHLY POROUS METAL FOAMS
Journal of Porous Media, Vol.16, 2013, issue 7
P. K. Sharma, Rajpal S. Bhoopal, Ramvir Singh, R. S. Beniwal
PREFACE: Manipulation of Macrophage Functions by Mycobacterium Tuberculosis
Forum on Immunopathological Diseases and Therapeutics, Vol.6, 2015, issue 3-4
Magdalena Klink
AN ANALYTICAL MODEL ON PRODUCTION PERFORMANCE OF MULTIPLE WELLS PRODUCING AT CONSTANT BOTTOMHOLE PRESSURES
Special Topics & Reviews in Porous Media: An International Journal, Vol.10, 2019, issue 1
Jalal Farhan Owayed, Md. Motiur Rahman, Jiaxing Xu, Jing Lu
EXPLORING THE ALIGNMENT OF BLACK SCIENTISTS WITH THE AMERICAN SCIENTIFIC COMMUNITY: DOES RACE STILL MATTER?
Journal of Women and Minorities in Science and Engineering, Vol.19, 2013, issue 2
J. Bryan Henderson, Bryan A. Brown, Eileen Parsons, Rhea Miles