Optimization of a method for identifying the flow regime and measuring void fraction in a broad beam gamma-ray attenuation technique

Abstract A gamma-ray transmission technique is present to measure the void fraction and identify the flow regime of a two-phase flow using two detectors which were optimized in terms of detector orientation. Using Monte-Carlo simulation, experimental results were utilized for training an artificial neural network. Radial Basis Function was used to classify flow regimes (annular, stratified and bubbly) and predict the value of void fraction. All of the training and testing data sets were determined correctly and the mean relative error percentage of predicted void fraction was less than 1.5%. Although the method was applied to a certain pipe size in a static flow configuration, it provides a framework for application to other configurations.

[1]  Roberto Schirru,et al.  Prediction of volume fractions in three-phase flows using nuclear technique and artificial neural network. , 2009, Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine.

[2]  James D. Keeler,et al.  Layered Neural Networks with Gaussian Hidden Units as Universal Approximations , 1990, Neural Computation.

[3]  A. El Abd.  Intercomparison of gamma ray scattering and transmission techniques for gas volume fraction measurements in two phase pipe flow , 2014 .

[4]  K. Scott,et al.  Numerical investigation of the optimal Nafion® ionomer content in cathode catalyst layer: An agglomerate two-phase flow modelling , 2014 .

[5]  Seyed Amir Hossein Feghhi,et al.  Prediction of Materials Density according to Number of Scattered Gamma Photons Using Optimum Artificial Neural Network , 2014 .

[6]  Seyed Amir Hossein Feghhi,et al.  Precise Void Fraction Measurement in Two-phase Flows Independent of the Flow Regime Using Gamma-ray Attenuation , 2016 .

[7]  Jing Chunguo,et al.  Flow regime identification of gas/liquid two-phase flow in vertical pipe using RBF neural networks , 2009, 2009 Chinese Control and Decision Conference.

[8]  Ryan Anderson,et al.  Development of two-phase flow regime specific pressure drop models for proton exchange membrane fuel cells , 2015 .

[9]  Seyed Amir Hossein Feghhi,et al.  A radiation-based hydrocarbon two-phase flow meter for estimating of phase fraction independent of liquid phase density in stratified regime , 2015 .

[10]  Seyed Amir Hossein Feghhi,et al.  Void fraction prediction in two-phase flows independent of the liquid phase density changes , 2014 .

[11]  Geir Anton Johansen,et al.  Determination of void fraction and flow regime using a neural network trained on simulated data based on gamma-ray densitometry , 1999 .

[12]  Seyed Amir Hossein Feghhi,et al.  Application of adaptive neuro-fuzzy inference system in prediction of fluid density for a gamma ray densitometer in petroleum products monitoring , 2013 .

[13]  R. Faghihi,et al.  Void fraction measurement in modeled two-phase flow inside a vertical pipe by using polyethylene phantoms , 2015 .

[14]  Bin Liu,et al.  Determination of Gas and Water Volume Fraction in Oil Water Gas Pipe Flow Using Neural Networks Based on Dual Modality Densitometry , 2006, ISNN.

[15]  Geir Anton Johansen,et al.  Improved void fraction determination by means of multibeam gamma-ray attenuation measurements , 1999 .

[16]  Seyed Amir Hossein Feghhi,et al.  Precise volume fraction prediction in oil-water-gas multiphase flows by means of gamma-ray attenuation and artificial neural networks using one detector , 2014 .

[17]  C. M. Rangel,et al.  A dynamic two phase flow model for a pilot scale sodium borohydride hydrogen generation reactor , 2014 .

[18]  César Marques Salgado,et al.  Salinity independent volume fraction prediction in annular and stratified (water–gas–oil) multiphase flows using artificial neural networks , 2014 .

[19]  A. Shahsavand,et al.  Application of optimal RBF neural networks for optimization and characterization of porous materials , 2005, Comput. Chem. Eng..

[20]  Seyed Amir Hossein Feghhi,et al.  Flow regime identification and void fraction prediction in two-phase flows based on gamma ray attenuation , 2015 .

[21]  Bing Yu,et al.  Training radial basis function networks with differential evolution , 2006, 2006 IEEE International Conference on Granular Computing.

[22]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[23]  Mohsen Hayati,et al.  Application of Radial Basis Function Network for the Modeling and Simulation of Turbogenerator , 2013 .

[24]  R. Schirru,et al.  Flow regime identification and volume fraction prediction in multiphase flows by means of gamma-ray attenuation and artificial neural networks , 2010 .

[25]  S. Kær,et al.  A numerical study of the gas-liquid, two-phase flow maldistribution in the anode of a high pressure PEM water electrolysis cell , 2016 .