Abo Bibliothek: Guest
Digitales Portal Digitale Bibliothek eBooks Zeitschriften Referenzen und Berichte Forschungssammlungen
International Journal of Fluid Mechanics Research
ESCI SJR: 0.206 SNIP: 0.446 CiteScore™: 0.5

ISSN Druckformat: 2152-5102
ISSN Online: 2152-5110

Volumes:
Volumen 46, 2019 Volumen 45, 2018 Volumen 44, 2017 Volumen 43, 2016 Volumen 42, 2015 Volumen 41, 2014 Volumen 40, 2013 Volumen 39, 2012 Volumen 38, 2011 Volumen 37, 2010 Volumen 36, 2009 Volumen 35, 2008 Volumen 34, 2007 Volumen 33, 2006 Volumen 32, 2005 Volumen 31, 2004 Volumen 30, 2003 Volumen 29, 2002 Volumen 28, 2001 Volumen 27, 2000 Volumen 26, 1999 Volumen 25, 1998 Volumen 24, 1997 Volumen 23, 1996 Volumen 22, 1995

International Journal of Fluid Mechanics Research

DOI: 10.1615/InterJFluidMechRes.v39.i5.40
pages 416-437

Frictional Pressure Drop for Gas − Non-Newtonian Liquid Flow through 90° and 135° Circular Bend: Prediction Using Empirical Correlation and ANN

Nirjhar Bar
Chemical Engineering Department, University of Calcutta Kolkata - 700 009, India
Sudip Kumar Das
University of Calcutta

ABSTRAKT

Experiments have been carried out to determine the two-phase frictional pressure drop across 90° and 135° bend for gas-non-Newtonian liquid flow on the horizontal plane. Empirical correlation has been developed to predict the two-phase friction factor using the physical and dynamic variables of the system. The applicability of Artificial Neural Networks (ANN) methodology have also been reported. The ANN prediction have been reported using Multilayer Perceptrons (MLP) trained with five different algorithms, namely: Backpropagation (BP), Scaled Conjugate gradient (SCG), Delta-Bar-Delta (DBD), Levenberg−Marquardt (LM), Quick-Prop (QP). Four different transfer functions were used in a single hidden layer for all algorithms. The χ-square test confirms that the best network for prediction of frictional pressure drop is when it is trained with Backpropagation algorithm in the hidden and output layer with the transfer function 4 in hidden layer having 13 processing elements for 90° bend. The χ-square test also confirms that the best network for prediction of frictional pressure drop is when it is trained with Levenberg − Marquardt algorithm in the hidden and output layer with the transfer function 1 in hidden layer having 7 processing elements for 135° bend. Both the methods are equally predictive in nature but the empirical correlation is based on the physical and dynamic variables of the system, whereas the ANN prediction is not dependent on the individual relationship between the input variables.


Articles with similar content:

BOILING HEAT TRANSFER PREDICTION IN HELICAL COILS UNDER TERRESTRIAL GRAVITY WITH ARTIFICIAL NEURAL NETWORK
4th Thermal and Fluids Engineering Conference, Vol.11, 2019, issue
Yongqi Xie, Hongwei Wu, Rodney Day, Xing Liang
AN EXPERIMENTAL STUDY ON PRESSURE DROP AND HEAT TRANSFER PERFORMANCE OF SUB-COOLED AND SATURATED FLOW BOILING IN A MICRO-TUBE
International Heat Transfer Conference 13, Vol.0, 2006, issue
W. J. Hui, Y. X. Hong, T. D. Wei
ENTROPY-BASED HEAT TRANSFER POTENTIALS - FORCED CONVECTION SINGLE-PHASE FLOW APPLICATIONS
International Heat Transfer Conference 8, Vol.6, 1986, issue
Henri Soumerai
FUZZY LOGIC INTERFACIAL TRANSFER IN TWO-PHASE FLOW
International Heat Transfer Conference 13, Vol.0, 2006, issue
Jae Young Lee, Mamoru Ishii
LAGRANGIAN CHAOS AND HEAT TRANSFER
International Heat Transfer Conference 11, Vol.16, 1998, issue
Asen Mokrani, C. Castelain , Hassan Peerhossaini