Доступ предоставлен для: Guest
Портал Begell Электронная Бибилиотека e-Книги Журналы Справочники и Сборники статей Коллекции
Journal of Porous Media
Импакт фактор: 1.752 5-летний Импакт фактор: 1.487 SJR: 0.43 SNIP: 0.762 CiteScore™: 2.3

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

Выпуски:
Том 23, 2020 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.v16.i7.10
pages 585-596

APPLICABILITY OF ARTIFICIAL NEURAL NETWORKS TO PREDICT EFFECTIVE THERMAL CONDUCTIVITY OF HIGHLY POROUS METAL FOAMS

Rajpal S. Bhoopal
Thermal Physics Laboratory, Department of Physics, University of Rajasthan, Jaipur 302 055, India
P. K. Sharma
Thermal Physics Laboratory, Department of Physics, University of Rajasthan, Jaipur 302 055, India
Ramvir Singh
Thermal Physics Laboratory, Department of Physics, University of Rajasthan, Jaipur 302 055, India
R. S. Beniwal
CSIR-National Institute of Science Communication and Information Resources, New Delhi 110 012, India

Краткое описание

This paper presents the applicability of artificial neural networks to predict effective thermal conductivity of highly porous metal foams. Artificial neural network models are based on feedforward backpropagation network with training functions such as gradient descent (GD), gradient descent with adaptive learning rate (GDA), gradient descent with momentum (GDM), gradient descent with momentum and adaptive learning rate (GDX), and scaled conjugate gradient (SCG). Volume fraction of fluid phase and thermal conductivity of solid and fluid phases are input parameters for the artificial neural network to predict the effective thermal conductivity. The training algorithm for neurons and hidden layers for different feedforward backpropagation networks runs at the uniform threshold function TANSIG-PURELIN for 500 epochs. Better agreement of predicted effective thermal conductivity values is obtained by using artificial neural networks with the experimental results. A comparison with other models is also made and it is found that the values of effective thermal conductivity predicted by using the present model are in good agreement with the reported experimental values.


Articles with similar content:

PREDICTION OF THE MECHANICAL PROPERTIES OF COPPER POWDER-FILLED LOW-DENSITY POLYETHYLENE COMPOSITES. A COMPARISON BETWEEN THE ANN AND THEORETICAL MODELS
Composites: Mechanics, Computations, Applications: An International Journal, Vol.6, 2015, issue 1
P. K. Sharma, A. S. Luyt, Ramvir Singh, R. S. Bhoopal
EXPERIMENTAL AND NUMERICAL INVESTIGATIONS OF EFFECTIVE THERMAL CONDUCTIVITY OF LOW-DENSITY POLYETHYLENE FILLED WITH Ni AND NiO PARTICLES
Composites: Mechanics, Computations, Applications: An International Journal, Vol.3, 2012, issue 1
Rajpal S. Bhoopal, Ramvir Singh, Dharmendra Tripathi, Madhusree Kole, T.K. Dey
NEURAL-NETWORK METAMODELLING FOR THE PREDICTION OF THE PRESSURE DROP OF A FLUID PASSING THROUGH METALLIC POROUS MEDIUM
Journal of Porous Media, Vol.17, 2014, issue 5
Nicolas Gascoin, Philippe Gillard, Eddy EL Tabach
PREDICTION OF EFFECTIVE THERMAL CONDUCTIVITY OF POLYMER COMPOSITES USING AN ARTIFICIAL NEURAL NETWORK APPROACH
Special Topics & Reviews in Porous Media: An International Journal, Vol.3, 2012, issue 2
P. K. Sharma, Rajpal S. Bhoopal, Ramvir Singh, R. S. Beniwal, Sajjan Kumar, Alok Pandey
NEURAL NETWORK MODEL FOR ON-LINE THERMAL MARGIN ESTIMATION OF A NUCLEAR POWER PLANT
ICHMT DIGITAL LIBRARY ONLINE, Vol.0, 1992, issue
Soon-Heung Chang, Seung-Hyuk Lee, Hyun-Koon Kim