Flow Measurement and Instrumentation 46 (2015) 25–32

Contents lists available at ScienceDirect

Flow Measurement and Instrumentation

journal homepage: www.elsevier.com/locate/flowmeasinst

A radiation-based hydrocarbon two-phase flow meter for estimating

of phase fraction independent of liquid phase density
in stratified regime
E. Nazemi a, S.A.H. Feghhi b, G.H. Roshani a,n, S. Setayeshi c, R. Gholipour Peyvandi d
a
Young Researchers and Elite Club, Kermanshah Branch, Islamic Azad University, Kermanshah, Iran
b
Radiation Application Department, Shahid Beheshti University, G.C., Iran
c
Department of Energy Engineering and Physics, Amirkabir University of Technology, Iran
d
Nuclear Science and Technology Research Institute, Tehran, Iran

art ic l e i nf o a b s t r a c t

Article history: The fluid properties strongly affect the performance of radiation-based multiphase flow meter. By changing the
Received 15 April 2015 fluid properties (especially density), recalibration is necessary. In this study, a method was presented to
Received in revised form eliminate the dependency of multiphase flow meter on liquid phase density in stratified two phase horizontal
19 August 2015
flows. At the first step the position of the scattering detector was optimized in order to achieve highest sen-
Accepted 14 September 2015
Available online 16 September 2015
sitivity. Several experiments in optimized position were done. Counts under the full energy peak of trans-
mission detector and total counts of scattering detector were applied to the Radial Basis Function neural
Keywords: network and the void fraction percentage was considered as the neural network output. Using this method, the
Radial Basis Function void fraction was predicted independent of the liquid phase density change in stratified regime of gas–liquid
Radiation-based MPFM
two-phase flows with mean relative error percentage less than 1.2%.
Detector
& 2015 Elsevier Ltd. All rights reserved.
Void fraction
Prediction

1. Introduction regimes in gas–liquid flows in a pipe with a diameter of 2 in. Jing

The radiation-based multiphase flow meter (MPFM) is relatively
new technology in Oil industry. MPFMs are used to measure the phase
fractions of oil, gas and water in the flow from an oil well. The con-
ventional methods used to measure the phase fraction in the flow
for each well at wide intervals that could span over several months.
The radiation-based MPFMs provide such information instantly, easing
monitoring problems and enabling quick access to data, which allows
rapid decisions to be made on well performance. The wealth of data
accumulated by radiation-based MPFM can be fed into reservoir
simulation codes to enhance their accuracy and reliability [1].
In recent years, many researchers and engineers have im-
plemented gamma ray attenuation in order to measure volume
fraction and identify the flow regime in multiphase flows. Tjugum
et al. used a multibeam gamma-ray densitometry to identify flow
regimes in hydrocarbon multiphase oil, water and gas pipe flows
[2]. They demonstrated that a fan beam geometry with one ra-
diation source and several collimated detectors is sufficient to
provide information on the liquid–gas distribution of the pipe
flow. Using 241Am source with the activity of 500 mCi and
9 CdZnTe semiconductor detectors, they identified several flow
n
Corresponding author.
E-mail address: hosseinroshani@yahoo.com (G.H. Roshani).
et al. investigated the dual modality densitometry method using
artificial neural networks (ANNs) in order to determinate the gas
and water volume fraction in a three-phase flow [3]. Jing and Bai,
also studied the flow regime identification in two phase flow in
vertical pipe using Radial Basis Function (RBF) neural networks
based on dual modality densitometry [4]. In 2014, Roshani et al.
used a dual energy source consists of 241Am (59.5 KeV) and 137Cs
(662 KeV) with just one transmission NaI detector to predict vo-
lume fraction in oil–water–gas three-phase flows [5]. By using
ANN, they predicted the volume fraction of oil, water and gas
phases with Mean Absolute error (MAE%) of less than 1%. Roshani
et al. also proposed a method based on dual modality densito-
metry using ANN to first identify the flow regime and then predict
the void fraction in gas–liquid two-phase flows [6]. They used the
total count in the scattering detector, the full energy peak and
photon counts of Compton edge in transmission detector as the
three inputs of the ANN. By applying this method, they correctly
distinguished all the three regimes of stratified, homogenous and
annular and estimated the void fraction of each phase in the range
of 5–95% with error of less than 1.1%. Also it has been shown that
artificial neural networks could be as a useful tool for predicting,
classification and optimization for industrial nuclear gauges
especially in cases that lots of parameters could influence the
operation of the system [7–14].
Calibration of radiation-based multiphase flow meter (MPFM)

http://dx.doi.org/10.1016/j.flowmeasinst.2015.09.002
0955-5986/& 2015 Elsevier Ltd. All rights reserved.
26 E. Nazemi et al. / Flow Measurement and Instrumentation 46 (2015) 25–32
depends strongly on the fluid properties [15]. By changing the
fluid properties such as density, recalibration is required. Perfor-
mance of radiation-based MPFMs will be improved by eliminating
any dependency on the fluid properties. In all previous studies, the
void fraction has been measured with a constant density liquid
phase and little attention has been paid to the changes of the
density of the liquid phase. Since attenuation of gamma-ray de-
pends on both amount and density of the matter, fluctuations of
the density of the liquid phase can cause significant errors in de-
termination of the void fraction. For example, fluctuations of
temperature and pressure which occur typically in pipe-lines of Oil
industry, could cause changes of the liquid density and conse-
quently measuring the void faction would deal with significant
errors.
In this work, an approach is proposed based on dual modality
densitometry using ANN to solve the problem of measuring the
void fraction in stratified regime of hydrocarbon gas–liquid two-
phase flows in situations that the liquid phase density is change-
able. At the first step, sensitivity response of the scattering de-
tector relative to the density changes of liquid phase in different
positions around the pipe, was investigated by using Monte Carlo
N Particle (MCNP) code. As much as the sensitivity is more, the
ANN could predict the void fraction independent of density
changes of the liquid phase with less error and consequently the
measuring precision of the system would be improved. After ob-
taining the most sensitive position relative to density changes for
the detectors by simulation, an experimental setup according to
the simulated geometry was designed in order to provide the
experimental required data for ANN. By applying this methodol-
ogy, the void fraction was predicted independent of the liquid
phase density in stratified regime of gas–liquid two-phase flows
with root mean square error of less than 1.4.
2. Proposed methodology
2.1. Monte Carlo simulation
As the first step in this study, a Monte Carlo simulation model is
used to obtain the best positions for the detectors in dual modality
densitometry configuration. The Monte Carlo model used in this
work is based on the Monte Carlo N-Particle (MCNP) code, version
X, which is used for neutron, photon, electron, or coupled neutron/
photon/electron transport. In this work, a dual modality densito-
metry setup based on the existing devices in our laboratory has
been simulated. As shown in Fig. 1, the position of 1-in. NaI
pipe
Collimator
Shield of
Source
135
120 105 90 75
Fig. 1. A top view of positioning of the scattering detector in different angles used in simulated geometry in order to obtain the most sensitive position relative to density
changes.
transmission detector was kept fixed in the angle of 0° and posi-
tion of 1-in. NaI scattering detector was changed from 15° to 135°
respect to center of the pipe with steps of 15°.
The void fractions in the range of 10–70% for stratified regime
of gas–liquid two-phase flows were simulated. Distance between
both the detectors and pipe was chosen 5 cm. The 137Cs source was
placed 10 cm far from the pipe. Also the source was collimated in
order to make a narrow beam passing through the center of the
pipe. Air with density of 0.001 g/cm3 was used as the gas phase in
the pipe. For making a wide range of density for liquid phase in
laboratory (from 0.735 g/cm3 to 0.980 g/cm3), gasoline, kerosene,
gasoil, lubricant oil, and water with the densities of 0.735, 0.795,
0.826, 0.852, and 0.980 (g/cm3), respectively, have been used as
the liquid phases. Same as the experiments, in simulations these
liquid phases were used, too. Since the predominant interaction
mechanism for high energy photons in low atomic number ma-
terials is Compton scattering and the photoelectric interaction
could be negligible, therefore, the interaction probability depends
just on the density of the liquid phase regardless of its composi-
tion. Also, because the effective atomic numbers of used liquids are
close to each other, it could be assumed that all of the 5 liquid
phases regardless of their compositions, are considered as one li-
quid phase with various densities.
Registered counts in both transmission and scattering detectors
were calculated per one source particle in the MCNP-X code using
Pulse Height Tally F8. A special tally card with the Gaussian Energy
Broadening (GEB) option is also included in the model in order to
take into account the Gaussian energy broadening and obtain a
better and more realistic simulation of the whole spectrum in
detectors. The technique consists of using a “FT8 GEB” card in the
input file of MCNP code and calculating the full width at half
maximum (FWHM) of the full energy peak of gamma ray with
different energies in the laboratory. The tallied energy is broa-
dened by sampling from the Gaussian function shown in Eq. (1)
[16]:
⎛ ( E − E0 ) ⎞2
−⎜⎜ ⎟⎟
f (E ) = Ce ⎝ A ⎠ (1)
Where, E is the broadened energy, E0 is the un-broadened energy
of the tally, C is the normalization constant and also A is related to
the FWHM by Eq. (2):
FWHM
A=
2 ln (2) (2)
The desired FWHM which is specified by the user-provided
T=Transmission Detector
S=Scattering Detector
T
15
30
45
60
 E. Nazemi et al. / Flow Measurement and Instrumentation 46 (2015) 25–32 27

140000

120000

100000
Count
80000

60000

40000

20000

0
0 200 400 600 800
Channel

40000

30000
Count

20000

10000

0
0 200 400 600 800
Channel

16000

14000

12000

10000
Count

8000

6000

4000

2000

0
0 200 400 600 800
Channel
241 137 60
Fig. 2. Calculation of FWHM of energy peak using experimental spectrum and Gaussian fitting function for radioactive sources of: (a) Am (b) Cs (c) Co.

constants (a, b, and c), has a nonlinear response relative to energy Where, E is the incident gamma-ray energy. The units of “a”, “b”
according to Eq. (3): and “c” parameters are MeV, MeV1/2, and MeV
1, respectively. To
calculate “a”, “b” and “c” parameters, one 1-in. NaI detector and
3 gamma emitter radioactive sources of 241Am (energy 60 KeV),
FWHM = a + b E + cE2 (3) 137
Cs (energy 662 KeV) and 60Co (energies 1173 and 1333 KeV)
28 E. Nazemi et al. / Flow Measurement and Instrumentation 46 (2015) 25–32

0.07

0.06
FWHM (MeV)

0.05

0.04

0.03

0.02

0.01

Fig. 7. Experimental setup.

0.00
0.0 0.2 0.4 0.6 0.8 1.0 1.2 1.4
241
Am, 137Cs and 60Co sources are shown in Fig. 2. The obtained
Energy (MeV)
FWHM from experimental spectrum is in terms of number of
Fig. 3. Calculation of GEB card parameters using obtained FWHM for different channels. For converting it in terms of energy (MeV) we used Eq.
energies and a non-linear fitting function.
(4):
22 FWHM (channel) × Energy of peak (MeV)
FWHM (MeV) =
Sensitivity of Scattering Detector Relate

20 Channel‵s number of peak (channel) (4)

to Density Changes (percent)

18
After obtaining the experimental FWHM for each energy peak,
16
as shown in Fig. 3, FWHM (MeV) curve as a function of energy
14
(MeV) was plotted and a non-linear fitting function (Eq. (3)) was
12
applied to calculate the values of the “a”, “b” and “c”. Parameters of
10
“a”, “b” and “c” were calculated 0.0109, 0.0696 and 0.0226, re-
8
spectively. These parameters were used with the GEB command in
6
the input file of MCNP code in order to take account the energy
4
resolution of the 1-in. NaI detector in the simulations.
2
At each position of the scattering detector, sensitivity response
10 20 30 40 50 60 70
Void Fraction (percent)
of this detector relative to density changes of the liquid phase from
the lowest density (0.735 g/cm3 ) to the highest density
Fig. 4. Sensitivity of the scattering detector relative to the density changes of the
(0.980 g/cm3) of liquid phase for void fractions in the range of 10–
liquid phase from 0.735 g/cm3 to 0.980 g/cm3 versus different void fractions.
70% was calculated according Eq. (5):
⎛ Registered count for density of 0.98 (g/cm3) ⎞
⎜ ⎟
⎜ −Registered count for density of 0.735 (g/cm3) ⎟
Sensitivity = ⎜ 3 ⎟
⎜ Registered count for density of 0.98 (g/cm ) ⎟
⎜ ⎟
⎝ ⎠
× 100 (5)

Sensitivity of the scattering detector relative to the density

changes of the liquid phase for different void fractions was shown
in Fig. 4.
As it is shown in Fig. 4, by increasing alignment angle of the
scattering detector, the sensitivity increases regularly in angles
from 0° to 75°, but suddenly in angle 90°, the sensitivity increases
largely and becomes almost as same as the sensitivity of angle
Fig. 5. Defined parameters in stratified regime. 120° and again after angle 90°, the sensitivity increases regularly.
As it is obvious in Fig. 4, in angle 135° the scattering detector has
including four gamma energies in the range from 60 KeV to the most sensitivity relative to density changes of liquid phase.
1333 KeV, were used. At first, FWHM of each peak of energy was Thus, angle 135° was chosen as the best position for locating of the
determined in terms of channel. The experimental spectrums for scattering detector.

Fig. 6. Cross sectional view of the made void fractions for stratified regime in the range of 10–70%.
 E. Nazemi et al. / Flow Measurement and Instrumentation 46 (2015) 25–32 29

320000
0.735 (g/cm3)
310000
0.795(g/cm3)
300000 0.826(g/cm3)
0.852(g/cm3)

Registered Count in the Transmission

290000
0.980(g/cm3)
280000
Detector (#) 270000

260000

250000

240000

230000

220000

210000

200000

190000
10 20 30 40 50 60 70
Void Fraction (percent)

200000 3
0.735 (g/cm )
Registered Count in the Scattering Detector (#)

0.795(g/cm3)
0.826(g/cm3)
180000 0.852(g/cm3)
0.980(g/cm3)

160000

140000

120000

100000

10 20 30 40 50 60 70
Void fraction (percent)

Fig. 8. Registered counts versus void fraction in different densities: (a) transmission detector (b) scattering detector.

2.2. Experimental Setup static conditions, there is no difference between locating the pipe
vertically or horizontally. A cross sectional view of the made void
An experimental setup was designed based on the obtained fractions for stratified regime in the laboratory was shown in
best positions for the detectors by simulation in order to generate Fig. 6.
required data for training and testing the artificial neural network Gasoline, kerosene, gasoil, lubricant oil, and water with the
(ANN). All the experiments were carried out in static conditions. A densities of 0.735, 0.795, 0.826, 0.852, and
pipe made of Pyrex-glass with radius of 4.75 cm and wall thick- 0.980 g/cm3,respectively, have been used as liquid phases and also
ness of 0.25 cm was chosen as the main pipe. For modeling the air was used as the gas phase. The void fractions of 10%, 20%, 30%,
stratified regime in static conditions, PVC (polyvinyl chloride) film 40%, 50%, 60% and 70%, were tested for each liquid phase (5 liquid
with thicknesses of 0.40 mm was used as a separator between li- phase with different densities  7 different void fraction ¼ totally
quid and gas phases. Required calculation for making various void 35 tests). A 137Cs source with activity of 2 mCi and a measurement
fractions from 10% to 70% in stratified regime was done according time of 600 s were chosen for all the experiments. The source was
to Eq. (6) [17]: collimated (a cubic collimator with 0.8 cm width, 8 cm height and
8 cm length) in order to make a narrow beam passing through the
1⎡ ⎛ R − L0 ⎞ 1 ⎛ ⎛ R − L0 ⎞⎞⎤ center of the pipe. One 1-in. NaI detector was located 25 cm far
αs = 1 − ⎢ arc cos ⎜ ⎟ − sin ⎜ 2arc cos ⎜ ⎟⎟⎥
π⎣ ⎝ R ⎠ 2 ⎝ ⎝ R ⎠⎠⎦ (6) from the source (5 cm far from the pipe) as transmission detector.
Another 1-in. NaI detector was located 5 cm far from the pipe and
Where L 0 is the level of the liquid in the pipe, R is the radius of the in angle of 135° respect to the center of the pipe as the scattering
pipe, and αs is the void fraction in stratified regime. These para- detector. The experimental setup is shown in Fig. 7.
meters are shown in Fig. 5. In transmission detector, counts under the full energy peak of
137
Although the stratified regime occurs in horizontal pipes, but in Cs were registered, while in the scattering detector total count
this work we located the pipe vertically to change simply the was registered. With the described setup and measurement time
samples in the pipe. Because our experiments were carried out in of 600 s, the relative standard deviation of registered count in both
30
Registered Count (Normalised to unit) E. Nazemi et al. / Flow Measurement and Instrumentation 46 (2015) 25–32

1.00
Experimental Data 80
Simulated Data
R.D=0%

0.95 70
R.D=0.3%

0.90
R.D=0.2% 60

Predicted Void Fraction (%)

0.85
R.D=0.8%
50
0.80 R.D=1%

40
0.75 R.D=2.3%

R.D=1.7% 30
0.70
10 20 30 40 50 60 70
Void Fraction (percent) 20

10
1.00 Experimental Data
Registered Count (Normalised to unit)

R.D=0% Simulated Data

0.95 0
10 20 30 40 50 60 70
0.90 R.D=0.5%
Void Fraction (%)
0.85 R.D=1%

0.80 R.D=1.6%
70
0.75
R.D=1.7%
0.70
60
0.65 R.D=2.4%
Predicted Void Fraction (%)

0.60
R.D=2.8% 50
0.55
10 20 30 40 50 60 70
Void Fraction (percent) 40
Fig. 9. Comparison of experimental and simulated data for liquid phase of gasoline
with density of 0.735 g/cm3: (a) transmission detector (b) scattering detector.
30

20

10
10 20 30 40 50 60 70
Void Fraction (%)

Fig. 11. Regression diagrams of experimental and predicted results for (a) training
data (b) testing data using presented RBF neural network.

maximum relative difference between experimental and simu-

lated data for transmission and scattering detectors, is 2.3% and
2.8%, respectively. Results show that simulated data are in good
Fig. 10. Radial Basis Function structure [22].
agreement with the experimental results. The most part of ob-
served deviations could be somewhat related to making the stra-
detectors is less than 0.004. tified regime phantoms in the experiments.
Registered counts versus void fraction for both detectors was
shown in Fig. 8. In the transmission detector, by increasing the 2.3. Artificial neural network
void fraction for one liquid-phase with constant density, the
number of counts would increase. Also in this detector, by in- ANN is a strong tool in order to modeling, prediction, optimi-
creasing the density for a constant void fraction, the number of zation and classification. Therefore it has many applications in
counts would decrease. The scattering detector demonstrates a nuclear engineering [12–15]. In this study, the void fraction per-
vice versa response in comparison with the transmission detector. centage was predicted using Radial Basis Function (RBF) neural
By increasing void fraction for one liquid-phase with constant network. The RBF has a feed forward ANN structure which is
density, the number of counts would decrease and also by in- consists of three layers: input layer, hidden layer and output layer
creasing the density for a constant void fraction, the number of [18,19]. This type of neural networks is one the most famous type
counts would increase. of feed forward networks. The RBF neural network structure has
The simulated results for liquid phase of gasoline with density been shown in Fig. 10. The first layer is made from source nodes
of 0.735 g/cm3 were benchmarked toward experimental data. This and the second layer consists of a set basis function units that
step was done in order to valid the simulator MCNP code. For the perform a nonlinear transformation from the input space to the
sake of simplicity in evaluation of the data, both simulated and hidden space [20,21].
experimental data were normalized to unit. As shown in Fig. 9, the The data set required for training the network was achieved,
 E. Nazemi et al. / Flow Measurement and Instrumentation 46 (2015) 25–32 31

Table 1 From Tables 1 and 2 and Fig. 11, clearly the predicted void
The data that were used for training the network and predicted void fraction fraction percentage by presented model is close to the experi-
percentages.
mental results. These results show the applicability of ANN as an
Density (g/cm3) Counts in trans- Counts in Void frac- Predicted accurate and reliable model for the prediction of void fraction
mitted detector scattering tion (%) void fraction percentage according to the counted gamma photons in trans-
detector (%) mission and scattering detectors. Two types of errors (mean re-
lative error percentage (MRE%) and the root mean square error
0.735 236,403 153,319 10 9.709535
0.795 226,957 163,893 10 10.23984
(RMSE)) were used in order to show the precision of the proposed
0.852 219,932 172,704 10 9.934259 neural network .The MRE% and the RMSE of the network are cal-
0.98 198,375 200,901 10 10.01297 culated by:
0.795 242,468 155,704 20 19.58138
N
0.826 239,534 160,128 20 20.51575 1 Xj (Exp) − Xj (Pred)
0.852 235,672 164,551 20 19.82555 MRE% = 100 × ∑
N j=1
Xj (Exp ) (7)
0.735 262,678 138,847 30 30.49037
0.795 255,449 147,747 30 30.84105
0.826 252,142 151,308 30 30.08618
0.98 229,422 179,789 30 29.88916
0.735 275,463 130,341 40 42.14215
0.826 264,871 141,947 40 40.44589 N 2
∑ j = 1 ( Xj (Exp) − Xj (Pred) )
0.852 261,091 145,518 40 38.55896 RMSE =
0.735 286,000 119,993 50 48.33656 N (8)
0.795 281,233 127,157 50 50.91241
0.852 274,083 133,425 50 47.71875 where N is the number of data and ‘X (Exp)’ and ‘X (Pred)’ stand
0.98 259,783 154,021 50 50.52808 for experimental and predicted (ANN) values, respectively. Ob-
0.795 296,428 112,506 60 60.01559 tained MRE percentages for training and testing sets were 0.0795
0.826 293,021 117,006 60 60.74899
and 1.1140, respectively. Obtained RMSE for training and testing
0.852 290,476 120,606 60 61.58983
0.735 316,349 93,892 70 70.21274 sets were 1.2660 and 1.3589, respectively. These low errors show
0.795 312,781 97,503 70 69.92444 the accuracy and precision of the presented RBF neural network.
0.826 309,375 101,115 70 69.68112
0.98 294,942 118,268 70 69.05846

4. Conclusion

Table 2
The data that were used for testing the network and predicted void fraction
Attenuation of gamma-ray strongly depends on density of
percentages. matter; therefore the density fluctuation of the liquid phase can
cause significant errors in determination of the void fraction. In
Density(g/cm3) Counts in trans- Counts in Void Frac- Predicted this study, a method was presented based on dual modality den-
mitted detector scattering tion (%) Void Fraction
sitometry using RBF neural network for determining the void
detector (%)
fraction independent of the density changes in stratified regime of
0.826 223,844 168,299 10 10.40418 two-phase flows. The presented RBF neural network has 2 inputs
0.735 252,419 145,973 20 22.47479 and 1 output. The inputs were counts of full energy peak of
0.98 215,284 191,092 20 19.22676
transmitted detector and total count of scattering detector and the
0.852 248,219 154,868 30 28.14699
0.795 268,277 138,376 40 41.58127 output was the void fraction percentage. Trained network pre-
0.98 244,324 166,944 40 39.85354 dicted void fraction percentage with root mean square error less
0.826 278,073 129,843 50 48.40015 than 1.4. These results show the applicability of RBF as an precise,
0.735 299,999 108,005 60 59.33674 accurate and reliable model for the prediction of void fraction
0.98 276,190 137,707 60 58.56083
0.852 306,835 103,823 70 69.25613
according to the registered counts in two detectors independent of
the liquid phase density change.
The proposed methodology could be applied for measuring the
using described experiment. The number of samples for training volume fraction in situations where the density of liquid phase
and testing data were 25 (about 72%) and 10 (about 28%) respec- could be changed. For instance, in situations where the gas void
tively. For training the RBF model, a program was developed using fraction (GVF) is low and the water cut of liquid is high. In such
MATLAB 8.1.0.604 software. The best structure of network (spread situations, salinity changes of the water could lead to density
and number of neurons in hidden layer) was founded using an changes of water and consequently would cause error in mea-
iterative loop in written program. In this iterative loop the spread suring the volume fraction. As another example, in situations
and the number of neurons in hidden layer were changed step by where the temperature is variable and consequently the density of
step and finally, the best structure with minimum error was saved. liquid phase would change, the proposed methodology could be as
In the best structure, the spread was 0.7 and the number of neu- a good choice for measuring the volume fraction.
rons in hidden layer was 10.

References
3. Results and discussion
The relation between the experimental and predicted results
using the presented RBF model for training and testing data in two
regression diagrams, have been shown in Fig. 11. These diagrams
show the high accuracy and precision of the presented model.
The predicted void fraction percentages for training and testing
samples were tabulated in Tables 1 and 2, respectively.
[1] F. Abu-Jarad, Application of radiation sources in the oil & gas industry and
shortages in their services, in: Proceedings of the International Symposium on
the Peaceful Applications of Nuclear Technology in the GCC Countries, Jeddah,
2008.
[2] S.A. Tjugum, B.T. Hjertaker, G.A. Johansen, Multiphase flow regime identifi-
cation by multibeam gamma-ray densitometry, Meas. Sci. Technol. 13 (2002)
1319–1326.
[3] C.G. Jing, G.Z. Xing, B. Liu, Q.G. Bai, Determination of gas and water volume
fraction in oil water gas pipe flow using neural networks based on dual
32 E. Nazemi et al. / Flow Measurement and Instrumentation 46 (2015) 25–32
modality densitometry. in: Advances in Neural Networks, Lecture Notes in
Computer Science, 3973, Springer–Verlag, New York, 2006, pp. 1248–1253.
[4] C.G. Jing, Q. Bai, Flow regime identification of gas/liquid two-phase flow in
vertical pipe using RBF neural networks, in: Proceedings of the Chinese Con-
trol and Decision Conference (CCDC), 2009.
[5] G.H. Roshani, S.A.H. Feghhi, A. Mahmoudi-Aznaveh, E. Nazemi, A. Adineh-
Vand, 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 (2014) 34–41.
[6] G.H. Roshani, E. Nazemi, S.A.H. Feghhi, S. Setayeshi, Flow regime identification
and void fraction prediction in two-phase flows based on gamma ray at-
tenuation, Measurement 65 (2015) 25–32.
[7] C.M. Salgado, L.E.B. Brandao, R. Schirru, C.M.N.A. Pereira, A. Xavier da Silva,
R. Ramos, Prediction of volume fractions in three-phase flows using nuclear
technique and artificial neural network, Appl. Radiat. Isot. 67 (2009)
1812–1818.
[8] C.M. Salgado, C.M.N.A. Pereira, R. Schirru, L.E.B. Brandao, Flow regime identi-
fication and volume fraction prediction in multiphase flows by means of
gamma-ray attenuation and artificial neural networks, Prog. Nucl. Energy 52
(2010) 555–562.
[9] C.M. Salgado, L.E.B. Brandao, C.M.N.A. Pereira, W.L. Salgado, Salinity in-
dependent volume fraction prediction in annular and stratified (water–gas–
oil) multiphase flows using artificial neural networks, Prog. Nucl. Energy 76
(2014) 17–23.
[10] G.H. Roshani, S.A.H. Feghhi, F. Shama, A. Salehizadeh, E. Nazemi, Prediction of
materials density according to number of scattered gamma photons using
optimum artificial neural network, Comput. Methods Phys. (2014), Article ID
305345, 6 pp.
[11] E. Nazemi, S.A.H. Feghhi, G.H. Roshani, Void fraction prediction in two-phase
flows independent of the liquid phase density changes, Radiat. Meas. 68
(2014) 49–54.
[12] T. Cong, G. Su, S. Qiu, W. Tian, Applications of ANNs in flow and heat transfer
problems in nuclear engineering: A review work, Prog. Nucl. Energy 62 (2013)
54–71.
[13] M. Khorsandi, S.A.H. Feghhi, A. Salehizadeh, G.H. Roshani, Developing a
gamma ray fluid densitometer in petroleum products monitoring applications
using Artificial Neural Network, Radiat. Meas. 59 (2013) 183–187.
[14] G.H. Roshani, S.A.H. Feghhi, A. Adineh-Vand, M. Khorsandi, Application of
adaptive neuro-fuzzy inference system in prediction of fluid density for a
gamma ray densitometer in petroleum products monitoring, Measurement 46
(2013) 3276–3281.
[15] S. Corneliussen, J.P. Couput, E. Dahl, E. Dykesteen, K.E. Frøysa, E. Malde,
H. Moestue, P.O. Moksnes, L. Scheers, H. Tunheim, Handbook of Multiphase
Flow Metering, Norwegian Society for Oil and Gas Measurement, Oslo, 2005.
[16] D.B. Pelowitz, MCNP-X TM User’s Manual, Version 2.5.0. LA-CP-05e0369, Los
Alamos National Laboratory, 2005.
[17] E. Abro, G.A. Johansen, Improved void fraction determination by means of
multibeam gamma-ray attenuation measurements, Flow Meas. Instrum. 10 (2)
(1999) 99–108.
[18] S. Haykin, Neural Networks: A Comprehensive Foundation, Prentice-Hall, USA,
1999.
[19] A. Shahsavand, A. Ahmadpour, Application of optimal Rbf neural networks for
optimization and characterization of porous materials, Comput. Chem. Eng. J.
29 (2005) 2134–2143.
[20] B. Yu, X. He, Training radial basis function networks with differential evolu-
tion, PWASET 11 (2006) 57–160.
[21] E.J. Hartman, J.D. Keeler, J.M. Kowalski, Layered neural networks with Gaussian
hidden units as universal approximators, Neural Comput. (1990) 210–215.
[22] M. Hayati, A. Rezaei, L. Noori, Application of radial basis function network for
the modeling and simulation of turbogenerator, J. Adv. Inf. Technol. 4 (2)
(2013) 76.