Application of neural networks to prediction of phase transport characteristics in high-pressure two-phase turbulent bubbly flows

Abstract The phase transport phenomenon of the high-pressure two-phase turbulent bubbly flow involves complicated interfacial interactions of the mass, momentum, and energy transfer processes between phases, revealing that an enormous effort is required in characterizing the liquid–gas flow behavior. Nonetheless, the instantaneous information of bubbly flow properties is often desired for many industrial applications. This investigation aims to demonstrate the successful use of neural networks in the real-time determination of two-phase flow properties at elevated pressures. Three back-propagation neural networks, trained with the simulation results of a comprehensive theoretical model, are established to predict the transport characteristics (specifically the distributions of void-fraction and axial liquid–gas velocities) of upward turbulent bubbly pipe flows at pressures covering 3.5–7.0 MPa. Comparisons of the predictions with the test target vectors indicate that the averaged root-mean-squared (RMS) error for each one of three back-propagation neural networks is within 4.59%. In addition, this study appraises the effects of different network parameters, including the number of hidden nodes, the type of transfer function, the number of training pairs, the learning rate-increasing ratio, the learning rate-decreasing ratio, and the momentum value, on the training quality of neural networks.

[1]  O. C. Jones,et al.  Development of a k-ε Model for Bubbly Two-Phase Flow , 1994 .

[2]  M. G. Allen,et al.  An imaging neural network combustion control system for utility boiler applications , 1993 .

[3]  Jenq-Shyong Chen.  Neural network-based modelling and error compensation of thermally-induced spindle errors , 1996 .

[4]  D.R.H. Beattie,et al.  Two-phase flow structure and mixing length theory , 1972 .

[5]  Donald A. Drew,et al.  Phase-distribution mechanisms in turbulent low-quality two-phase flow in a circular pipe , 1982, Journal of Fluid Mechanics.

[6]  S. Levy,et al.  Prediction of Two-Phase Pressure Drop and Density Distribution From Mixing Length Theory , 1963 .

[7]  Robert A. Jacobs,et al.  Increased rates of convergence through learning rate adaptation , 1987, Neural Networks.

[8]  T. J. Liu.  Bubble size and entrance length effects on void development in a vertical channel , 1993 .

[9]  R. Reid,et al.  The Properties of Gases and Liquids , 1977 .

[10]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[11]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[12]  Michio Sadatomi,et al.  Momentum and heat transfer in two-phase bubble flow—I. Theory , 1981 .

[13]  Stephen H. Lieberman,et al.  Use of a neural network for the analysis of fluorescence spectra from mixtures of polycyclic aromatic hydrocarbons , 1992, Other Conferences.

[14]  S. G. Bankoff,et al.  A Variable Density Single-Fluid Model for Two-Phase Flow With Particular Reference to Steam-Water Flow , 1960 .

[15]  J. P. V. Doormaal,et al.  ENHANCEMENTS OF THE SIMPLE METHOD FOR PREDICTING INCOMPRESSIBLE FLUID FLOWS , 1984 .

[16]  W. H. Hsieh,et al.  Inverse problem of specifying combustion parameters in the design of airbag inflators with neural networks , 1998 .

[17]  Steven Beyerlein,et al.  Prediction of bubble concentration profiles in vertical turbulent two-phase flow , 1985 .

[18]  Isao Kataoka,et al.  Turbulence structure of air-water bubbly flow—I. measuring techniques , 1975 .

[19]  R. E. Sonntag,et al.  Fundamentals of classical thermodynamics , 1973 .

[20]  Ching-Chang Chieng,et al.  EULERIAN-LAGRANGIAN COMPUTATIONS ON PHASE DISTRIBUTION OF TWO-PHASE BUBBLY FLOWS , 1997 .

[21]  B. Launder,et al.  The numerical computation of turbulent flows , 1990 .

[22]  Bubble size and system pressure effects on the phase distribution for two-phase turbulent bubbly flows , 2001 .

[23]  Effects of Two Phase Turbulent Structure Interactions on Phase Distribution In Bubbly Pipe Flows , 1999 .

[24]  Himanshu Pokharna,et al.  The particle fluid model and using Lagrangian representation in two-phase flow modeling , 1997 .

[25]  Kevin W. Whitaker,et al.  Specifying exhaust nozzle contours with a neural network , 1993 .