Abstract
In this paper, based on dual-energy broad beam gamma ray attenuation technique (using two transmission 1-inch NaI detectors and a dual-energy gamma ray source), an artificial neural network (ANN) model was used in order to predict the volume fraction of gas, oil and water in three-phase flows independent of the flow regime. A multilayer perceptron (MLP) neural network was used for developing the ANN model in MATLAB 8.1.0.604 software. The input parameters of the MLP model were registered counts under first and second full energy peaks of the both transmission NaI detectors, and the outputs were gas and oil percentage. The volume fractions were obtained precisely independent of flow regime using the presented model. Mean absolute error of the presented model was less than 2.24%.
Similar content being viewed by others
References
Bishop CM, James GD (1992) Analysis of multiphase flows using dual-energy gamma densitometry and neural networks. Nucl Instrum Methods A327:580
Hewitt GF (1993) Developments in multiphase metering. In: Conference on developments in production separation systems, 4–5 March, London
Thorn R, Johansen GA, Hammer EA (1997) Recent developments in three-phase flow measurement. Meas Sci Technol 8:691–701
Ismail I, Gamio JC, Bukhari SFA, Yang WQ (2005) Tomography for multi-phase flow measurement in the oil industry. Flow Meas Instrum 16:145–155
Abouelwafa MSA, Kendall EJM (1980) The measurement of component ratios in multiphase systems using gamma-ray attenuation. J Phys E Sci Instrum 13:341–345
Roshani GH, Feghhi SAH, Mahmoudi-Aznaveh A, Nazemi E, Adineh-Vand A (2014) Precise volume fraction prediction in oil–water–gas multiphase flows by means of gamma-ray attenuation and artificial neural networks using one detector. Measurement 51:34–41
Abro E, Khoryakov VA, Johansen GA (1999) Determination of void fraction and flow regime using a neural network trained on simulated data based on gamma-ray densitometry. Meas Sci Technol 10(7):619–630
El Abd A (2014) Intercomparison of gamma ray scattering and transmission techniques for gas volume fraction measurements in two phase pipe flow. Nucl Instrum Methods Phys Res A 735:260–266
Roshani GH, Nazemi E, Feghhi SAH (2016) Investigation of using 60Co source and one detector for determining the flow regime and void fraction in gas-liquid two-phase flows. Flow Meas Instrum 50:73–79
Nazemi E, Feghhi SAH, Roshani GH (2014) void fraction prediction in two-phase flows independent of the liquid phase density changes. Radiat Meas 68:49–54
Roshani GH, Nazemi E, Feghhi SAH, Setayeshi S (2015) Flow regime identification and void fraction prediction in two-phase flows based on gamma ray attenuation. Measurement 62:25–32
Nazemi E, Roshani GH, Feghhi SAH, Setayeshi S, Gholipour Peyvandi R (2015) A radiation-based hydrocarbon two-phase flow meter for estimating of phase fraction independent of liquid phase density in stratified regime. Flow Meas Instrum 46:25–32
Nazemi E, Roshani GH, Feghhi SAH, Gholipour Peyvandi R, Setayeshi S (2016) Precise void fraction measurement in two-phase flows independent of the flow regime using gamma-ray attenuation. Nucl Eng Technol 48:64–71
Jing CG, Xing GZ, Liu B, Bai QG (2006) Determination of gas and water volume fraction in oil water gas pipe flow using neural networks based on dual modality densitometry. Advances in Neural Networks, Lecture Notes in Computer Science, New York, Springer. vol 3973, 1248–1253
Jing CG, Bai Q (2009). Flow regime identification of gas/liquid two-phase flow in vertical pipe using RBF neural networks. Chinese control and decision conference (CCDC)
Salgado CM, Pereira CMNA, Schirru R, Brandao LEB (2010) Flow regime identification and volume fraction prediction in multiphase flows by means of gamma-ray attenuation and artificial neural networks. Prog Nucl Energy 52:555–562
Yadollahi A, Nazemi E, Zolfaghari A, Ajorloo AM (2016) Application of artificial neural network for predicting the optimal mixture of radiation shielding concrete. Prog Nucl Energy 89:69–77
Salgado CM, Brandao LEB, Schirru R, Pereira CMNA, Xavier da Silva A, Ramos R (2009) Prediction of volume fractions in three-phase flows using nuclear technique and artificial neural network. Appl Radiat Isot 67:1812–1818
Roshani GH, Feghhi SAH, Shama F, Salehizadeh A, Nazemi E (2014) Prediction of materials density according to number of scattered gamma photons using optimum artificial neural network. Comput Methods Phys, Article ID, p 305345
Cong T, Su G, Qiu S, Tian W (2013) Applications of ANNs in flow and heat transfer problems in nuclear engineering: a review work. Prog Nucl Energy 62:54–71
Yadollahi A, Nazemi E, Zolfaghari A, Ajorloo AM (2016) Optimization of thermal neutron shield concrete mixture using artificial neural network. Nucl Eng Des 305:146–155
Salgado CM, Brandao LEB, Pereira CMNA, Salgado WL (2014) Salinity independent volume fraction prediction in annular and stratified (water–gas–oil) multiphase flows using artificial neural networks. Prog Nucl Energy 76:17–23
Nazemi E, Roshani GH, Feghhi SAH, Setayeshi S, Eftekhari Zadeh E, Fatehi A (2016) Optimization of a method for identifying the flow regime and measuring void fraction in a broad beam gamma-ray attenuation technique. Int J Hydrog Energy 41:7438–7444
Pelowitz DB (2005) MCNP-X TM User’s Manual, version 2.5.0. LA-CP-05-0369. Los Alamos National Laboratory
Taylor JG (1996) Neural networks and their applications. Wiley, West Sussex
Gallant AR, White H (1992) On learning the derivatives of an unknown mapping with multilayer feed forward networks. Neural Netw 5:129–138
Levenberg KA (1944) Method for the solution of certain non-linear problems in least squares. Quart Appl Math 2:164–168
Marquardt D (1963) An algorithm for least-squares estimation of nonlinear parameters. SIAM J Appl Math 11:431–441
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Roshani, G.H., Nazemi, E. & Roshani, M.M. Flow regime independent volume fraction estimation in three-phase flows using dual-energy broad beam technique and artificial neural network. Neural Comput & Applic 28 (Suppl 1), 1265–1274 (2017). https://doi.org/10.1007/s00521-016-2784-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-016-2784-8