Доступ предоставлен для: Guest
Портал Begell Электронная Бибилиотека e-Книги Журналы Справочники и Сборники статей Коллекции
Atomization and Sprays
Импакт фактор: 1.189 5-летний Импакт фактор: 1.596 SJR: 0.814 SNIP: 1.18 CiteScore™: 1.6

ISSN Печать: 1044-5110
ISSN Онлайн: 1936-2684

Том 28, 2018 Том 27, 2017 Том 26, 2016 Том 25, 2015 Том 24, 2014 Том 23, 2013 Том 22, 2012 Том 21, 2011 Том 20, 2010 Том 19, 2009 Том 18, 2008 Том 17, 2007 Том 16, 2006 Том 15, 2005 Том 14, 2004 Том 13, 2003 Том 12, 2002 Том 11, 2001 Том 10, 2000 Том 9, 1999 Том 8, 1998 Том 7, 1997 Том 6, 1996 Том 5, 1995 Том 4, 1994 Том 3, 1993 Том 2, 1992 Том 1, 1991

Atomization and Sprays

DOI: 10.1615/AtomizSpr.v12.i4.10
pages 359-386


M. A. Aamir
Department of Mechanical, Aerospace and Manufacturing Engineering, UMIST, Manchester, United Kingdom
M. M. Awais
Department of Mechanical Engineering, Imperial College, London, United Kingdom
A. Paul Watkins
Energy and Multiphysics Research Group, School of Mechanical, Aerospace, and Civil Engineer- ing, University of Manchester, United Kingdom

Краткое описание

Artificial neural networks (ANN) models have been developed and applied to free propane sprays and to water spray cooling heat flux predictions. For the propane spray conditions the ANN model is trained against the computational fluid dynamics (CFD) results and verified against experimental data for drop diameter at the centreline 95 mm from the nozzle. It is shown that an ANN model trained on CFD gives results comparable to the CFD predictions and that it can therefore be employed online in industry to investigate and limit the consequences of a depressurization accident. When enough experimental data are present, as in the spray cooling case, the ANN model can be welt trained and proves to be an alternative numerical modeling technique to CFD, with the numerical predictions comparable to the CFD predictions, but in real-time mode.