Escolar Documentos
Profissional Documentos
Cultura Documentos
Mechanical Engineering Department, Shahid Rajaee Teacher Training University, Tehran, Iran
Mechanical Engineering Department, K. N. Toosi University of Technology, Tehran, Iran
c
Central Training Department of National Iranian Oil Company (NIOC), Tehran, Iran
b
art ic l e i nf o
a b s t r a c t
Article history:
Received 19 September 2015
Received in revised form
4 April 2016
Accepted 6 May 2016
Available online 7 May 2016
Accurate predictions of uid properties, such as density, oil formation volume factor and bubble point
pressure, are essentials for all reservoir engineering calculations. In this paper, an approach based on
nonlinear system identication modeling; Nonlinear ARX (NARX) and Hammerstein-Wiener (HW) predictive model, is proposed for forecasting the pressure/volume/temperature (PVT) properties of crude oil
systems. To this end, two datasets; one containing 168 PVT samples from different Iranian oil reservoirs
and other a databank containing 755 data from various geographical locations, were employed to construct (i.e. train) and evaluate (i.e. test) the models. Simulation results demonstrate that the proposed
NARX and HW models outperform previously employed methods including three types of articial
neural networks models (committee machine, multilayer perceptron and radial basis function), two
types of ANFIS models (grid partition and fuzzy c-mean) and several empirical correlations with the
smallest prediction error, and that they are reliable models for predicting the oil properties in reservoirs
engineering among other soft computing approaches.
& 2016 Elsevier B.V. All rights reserved.
Keywords:
PVT
Oil formation volume factor
Density
Bubble point pressure
Nonlinear autoregressive exogenous (NARX)
Hammerstein-Wiener
1. Introduction
Obtaining properties of reservoir uid has a very important
application in reservoir engineering computation such as inow
performance calculations, well test analysis, numerical reservoir
simulation, reserve estimates and material balance calculations
(Osman et al., 2001). One essential necessity for all types of petroleum calculations is the PVT properties such as design of uid
handling equipment, reservoir volumetric estimates and determination of hydrocarbon owing properties. Idyllically, in order
to extract desired PVT properties, these properties must be acquired through laboratorial analysis of real measurements/samples collected from the oil wells location. Most often, though, these
measurements are not fully available, because of one or more of
these reasons: a) Samples collected are not reliable. b) Samples
have not been taken because of cost saving. c) PVT analyses are not
available when needed (Hemmati and Kharrat, 2007). As a result,
many correlations models have been developed to relate these
desired properties (e.g. density and bubble point pressure) to
other measures which are relatively abundant and/or easier to
n
Corresponding author.
E-mail address: saeed.salehinia@gmail.com (S. Salehinia).
http://dx.doi.org/10.1016/j.petrol.2016.05.008
0920-4105/& 2016 Elsevier B.V. All rights reserved.
measure (e.g. temperature, pressure and API gravity). The geological condition is considered important for the development of a
correlation, since the chemical composition of crude oil varies
from region to region (Al-Marhoun, 2004). Therefore, all calculations will depend on the precision of the correlations used for
predicting the uid properties (Osman et al., 2001).
During the past sixty years, the importance of developing and
utilizing empirical correlations for PVT properties has been recognized by engineers. Consequently, much research has been
conducted in this eld and lead to the development of new empirical correlations. Katz (1942) published a graphical correlation
for predicting oil formation volume factor (Bo) factor. Katz used U.
S. mid-continent crude to develop his correlations. Al-Marhoun
(1985, 2004) correlations consist of equations for estimating
bubble point pressure (Pb), solution gas-oil ratio and Bo for Saudi
Arabia oils. These correlations were developed using 75 bottomhole samples from 62 reservoirs in Saudi Arabia. Petrosky and
Farshad (1993) presented correlations for estimating Pb, solution
gas oil ratio, Bo factor and oil compressibility for Gulf of Mexico
oils. The correlations were developed with uid samples taken
from offshore Texas and Louisiana. Khan et al. (1987) used samples
from 75 bottom-hole from 65 Saudi Arabia reservoirs and developed equations for estimating oil viscosity for Saudi Arabia oils at
above and below the bubble point. Glaso (1980) presented
48
S. Salehinia et al. / Journal of Petroleum Science and Engineering 147 (2016) 4755
Nomenclature
ANFIS
ANN
API
Bo
Ea
Emax
Emin
Er
FCM
GP
HW
M
NARX
P
Pb
R2
Rs
T
o
g
o
Hammerstein-wiener
membership function
nonlinear autoregressive exogenous
pressure (psia)
bubble point pressure
coefcient of determination
solution gas/oil (scf/stb)
temperature (F)
oil specic gravity
gas specic gravity
density (g/cm3)
S. Salehinia et al. / Journal of Petroleum Science and Engineering 147 (2016) 4755
49
Table 1
Ranges of inputs and outputs data used in training of the models.
Inputs
Maximum
Minimum
Average
Outputs
Pb (psia)
Temperature (F)
Pressure (psia)
Rs (Scf/STB)
API
Bo
o (g/cm3)
4416
1090
2805.4
277
140
222.3
6548
1413
3778.1
1998.4
255.16
899.92
34.77
18.91
26.87
0.8807
0.5351
0.7086
1.3103
0.7883
1.0405
2.3947
1.1680
1.5908
0.8798
0.5345
0.7079
Table 2
Ranges of output data used in validation (calibration) and test of the models.
Maximum
Minimum
Average
Validation (calibration)
Test
Bo
Bo
2.3532
2.0612
2.2101
0.5839
0.5345
0.5577
2.1782
1.9722
2.0671
0.6165
0.5839
0.6022
u2
T
u3
P
u4
Rs
u5
API
u6
o
u7
HW and ANFIS-GP
Bo
Table 4
Conguration of the HW model.
Output Inputs nonlinearity
Bo
nb = [1 1 1 1 1 1 1]
nf = [3 3 3 3 3 3 3]
2. Methodology
2.1. Adaptive Neuro-Fuzzy Inference System (ANFIS)
Table 3
Inputs specication used for each model.
Type of input
nk = [0 0 0 0 0 0 0]
Table 5
Conguration of the NARX model.
Output
Class of estimator
Regressors orders
Density
na = [1]
nb = [1 1 1 1 1 1]
nk = [0 0 0 0 0 0]
50
S. Salehinia et al. / Journal of Petroleum Science and Engineering 147 (2016) 4755
y(t ) = f (
(1)
y^ (t ) = F (x(t ))
(2)
F (x) = LT (x r ) + d + g (Q (x r ))
(3)
Bj, i(q)
Fj, i(q)
(4)
S. Salehinia et al. / Journal of Petroleum Science and Engineering 147 (2016) 4755
51
volume at a specic pressure and temperature. This property is one of the most
important parameters necessary for reservoir calculations and uid mobility. Pb is
one of the key PVT property of reservoir uid, which plays a critical role in almost
all tasks related to reservoir and production engineering. On one hand, obtaining
uid properties of reservoirs is very important for petroleum engineering. On the
other hand, a complete data information of PVT properties is not available for some
reservoirs, and moreover, calculating uid properties in laboratories is time consuming and expensive-not to mention human errors. Hence, a soft computing
technique to predict necessary uid properties is the solution which engineers have
been using recently.
Table 6
Testing results for prediction of density (o).
Model
R2
0.994 0.2471
0.996 0.1555
0.996 1.0139
0.991 0.470
0.996 0.0646
0.999 6.60E 4
Er (%)
Ea (%)
0.2580
0.1555
1.0139
0.479
0.0718
0.0028
0.0423
0.0343
0.2820
0.252
3.48E 3
8.36E 7
1.1085
0.2549
2.3367
0.643
0.3140
0.0163
Table 7
Testing results for prediction of Bo.
Model
R2
0.996 9.2714
9.2714 9.1052
0.997 10.8012 10.8012 9.3991
0.996 8.4578
8.4578 7.0791
0.973 1.743
1.743
0.466
Er (%)
0.999 0.2004
0.999 7.14E 03
Ea (%)
|Er|min (%)
1.2723 0.8766
0.0137 5.01E 07
|Er|max (%)
9.5440
12.2908
9.3193
2.71
1.9974
0.0989
To design the predictive models for Bo and density, a dataset comprising of 168
data points from 21 different petroleum elds from the south and west reservoirs
of the Iran have been used. In this dataset, there are 8 data points from each eld
with limited range of API gravity. To develop the models, 136 out of 168 PVT data
points was used to train the models. In order to prevent the over tting of the
models during training process, 16 data points was used for validation. The remaining 16 data points that were not shown to the models (blind data) were used
to investigate and test the accuracy of the models. These data has not been introduced to the system in the training process. All the PVT data used in this study
were selected from undersaturated petroleum reservoirs. Choosing appropriate
ranges of input and output is a really important step to have well-trained models
and leads to very accurate and reliable results at the end. The ranges of input and
output data used for training of the models are shown in Table 1. Also, the ranges of
output data used for validation (calibration) and test are shown in Table 2.
Finding the best conguration for an ANFIS model must be done through
testing different setting; there is yet no basis to nd most effective conguration
for ANFIS at any dened problem. However, monitoring root mean squared errors
at the different number of epochs for training and checking data is the simplest
way to steer at desired performance. To design an ANFIS model, number and type
of MF have a key role. Extensive search carried out to nd the proper structure and
optimal number of MFs for the best ANFIS model(s). To this end, best model for
density obtained through generating a FIS using FCM with 11 Gaussian MFs for each
input and constant MF for output. Then the obtained FIS used to train an ANFIS
model. Furthermore, best model for Bo obtained through generating a FIS using GP
with 2 MFs for each input and linear MF for the output. By applying various linear
and nonlinear MF, triangular MF for inputs 1, 4 and 7; and generalized-bell MF for
inputs 2, 3, 5 and 6 have displayed better performance. Then the obtained FIS used
for training of an ANFIS model. In order to tune adaptive parameters of ANFIS
models, training of network and optimal distribution of MFs are executed by hybrid
learning algorithm composed of least squares estimates and back propagation error
to perform forward pass and backward pass respectively.
In the case of proposed blocks-structured models, also several NARX and HW
models were obtained. Apart from choosing the type of inputs for models, in addition, the combination of various estimator and order were tested too. To speed up
the process of nding the best models and also decreasing the complexity choosing
the proper ones; best-t as shown in Eq. (5) between model output and real data as
a percentage value was monitored. In this equation, y is the measured output, y^ is
the predicted model output, and y is the mean of y. The higher the value is closer to
100%, the better the model can perform and predict the real data. After investigating several possibilities, the best result achieved through using a NARX
model for predicting density and a HW model for Bo.
y y^
Best fit=(1
y y
)*100
(5)
The inputs used for estimating the NARX, HW and ANFIS models are shown in
Table 3. The real dataset contains 26 different properties of oil. As it can be seen in
Table 3, after thorough study of the inputs and their effect on the behavior of the
outputs, the appropriate inputs were selected. The selected inputs for the best
NARX, HW and ANFIS models are the same. Tables 4 and 5 summarize the conguration, and Figs. 4 and 5 illustrate the structure and properties of linear and
nonlinear blocks of the best attained HW and NARX models, respectively.
To evaluate the performance and accuracy of the selected NARX, HW and ANFIS
models, the 16 blind data points were fed to the models, and the predicted outputs
of the models were compared with real data of density and Bo using important
statistical criteria including coefcient of determination (R2), average percent relative error (Er) and average absolute percent relative error (Ea). These statistical
quality measures are calculated as follows:
R2 = 1
Er =
100
n
n
i = 1 (yireal yimodel )2
n
i = 1 (yireal average(yireal ))2
n
(
i =1
yireal yimodel
yireal
(6)
)
(7)
52
S. Salehinia et al. / Journal of Petroleum Science and Engineering 147 (2016) 4755
Ea =
100
n
(
i =1
yireal yimodel
yireal
)
(8)
where yireal is the real/measured value of ith sample, yimodel is the predicted
value of the ith sample by the model, and n represent the total number of data
points.
The empirical correlations of Ahmed (1985), Hanafy et al. (1997) and Vazquez
and Beggs (1980) have been selected for estimating and comparing the results of
density; and correlations of Ahmed (1985), Glaso (1980) and Vazquez and Beggs
(1980) were used for estimating and comparing the results of Bo. Furthermore, the
results also were compared with a committee machine type ANN model that was
trained and evaluated with the same dataset used in this study. The comparison
results are summarized in Tables 6 and 7.
As can be seen from the Tables 6 and 7, performance of NARX and HW models
are outstanding. The results show that the NARX and HW models have predicted
the density and Bo values to the satisfactory extent. It can be seen that the NARX
and HW model results outperforms all ANFIS, ANN models and three most common published empirical correlations. The proposed NARX and HW models,
achieved the lowest Er, lowest Ea and a high R2 in the prediction of density and Bo
among the empirical correlations, ANN and ANFIS models. The Ea is an important
indicator of the accuracy of the models, which NARX and HW models achieved the
highest accuracy. It can be seen that NARX model shows a 96.6% improvement in
term of Ea over the ANFIS model, 99.4% over the ANN model, and also 98.2% over
best empirical correlation at predicting density. Also, the HW model shows a 98.9%
improvement in term of Ea over the ANFIS model, 99.2% over the ANN model, and
also 99.8% over best empirical correlation at predicting Bo.
Fig. 6 shows a comparison of the Ea and further illustrate the superiority of the
performance of the proposed NARX and HW models for predicting density and Bo
against the results from the ANFIS and ANN models. It is evident from the Fig. 6
that the performance of NARX and HW models is excellent. The results for empirical correlations had to be plotted separately, since their numerical results are
much greater than the NARX, HW and ANFIS models; would have made the results
in Fig. 6 incomparable.
Next, a sensitivity study carried out to illustrate the effect of the number of
training data on the accuracy of the results obtained from NARX, HW and ANFIS
methods. To this end, the training data have been reduced from 136 data in a
multistep test by the amount of 16 data in each step, while the 16 validation data
and 16 test data were remained the same (same as the previous test) at each step.
Fig. 7 demonstrate the results of sensitivity analysis for prediction of density and Bo.
According to the results from Fig. 7, the ANFIS models showed the highest
correlation with the number of training data; as the number of the training data
decreased so was the performance of ANFIS models. On the other hand, the accuracy of NARX model remained in a relatively constant range (less than 4e 3) up
until step ve. Even though the accuracy of NARX model decreased when the
number of training data became less than 72 data points, but even then the prediction accuracy of NARX model was to the satisfactory extend. It can be seen that
the NARX model was able to accurately predict the density using only 24 training
data. The sensitivity analysis of HW model showed that more training data is not
always equal to the greater accuracy, and that the HW model also can achieve high
prediction accuracy using less training data. The NARX and HW models showed
that they can provide satisfactory accuracy even when a few numbers of experimental data available to train with.
Finally, to achieve an unbiased estimation of the model performance for each
oil elds, the dataset can be divided randomly into k subsets of equal size and kfold cross-validation performed. In this method, models are built k times, each time
leaving out a single subset as the validation data for testing the model and the
remaining k 1 subsets are used as training data. The k results from the folds, then
averaged to yield a single result. Since our dataset contains 168 data points from 21
different oil elds and each oil eld has 8 data points. Thus, the dataset can be
divided into 21 folds in which each fold contains 8 data (i.e., each fold contains the
data of one oil eld). This way, the prediction performances of the models can be
evaluated for 21 different elds. As stated, the result of a cross-validation test is
presented as a single averaged number presenting the performance of the proposed method over k subsets. However, here the prediction results and CPU time
from each subsets also provided so that the results in more details are available for
comparison. The results of 21-fold cross-validation for density and Bo are shown in
Fig. 8.
It can be seen from cross-validation results in Fig. 8 that the blocks-structured
NARX and HW models with the lowest average of Ea have an excellent predictive
performance of PVT properties. The results demonstrate that the NARX and HW
models estimated 8 data points of the density and Bo in each 21 fold to the satisfactory extend. Hence, it could be concluded at this point that the NARX and HW
modeling approaches have better and reliable performance compared to the
S. Salehinia et al. / Journal of Petroleum Science and Engineering 147 (2016) 4755
Fig. 8. Error results of cross-validation: (a) NARX (b) ANFIS-FCM (c) HW (d) ANFIS-GP.
53
54
S. Salehinia et al. / Journal of Petroleum Science and Engineering 147 (2016) 4755
Table 8
Ranges of PVT properties of crude oil systems in the databank.
Maximum
Minimum
Average
Rs (Scf/STB)
API
T (F)
Pb (psi)
3298.66
1.395
592.387
3.4445
0.521
1.1156
56.8
6.0
34.36
360.93
74.00
207.167
6613.82
58.0152
1846.0504
Table 9
Conguration of the developed NARX, HW and ANFIS models for Pb.
Model
Orders of
NARX
Regressors:
na [0]
nb [1 1 1 1]
nk [0 0 0 2]
HW
input1
input2
input3
input4
Linear block:
nb [3 3 3 3]
nf [4 4 4 4]
nk [0 0 0 0]
ANFIS-GP input1
input2
MF
input3
input4
MFs: [2 2 2 2]
(API): Gaussian MF
( g ): Difference between two sigmoidal
MF
output (Pb): Linear MF
developed empirical correlations and the two types of ANFIS models presented
here.
3.2. Dataset 2: bubble point pressure
In this subsection, in order to investigate the effectiveness of the proposed
NARX and HW modeling method on other oil elds and as well as for estimating
other PVT properties, the predictive performance of the NARX and HW models
were assessed for prediction of reservoir oil saturation pressure at various conditions. For this purpose, a large databank attained from Talebi et al. (2014) which in
turn they have gathered from nine other studies. The gathered databank includes
755 experimental data of Rs, , T, API, and bubble point pressure (Pb) from a variety
of crude oils (heavy oils to volatile oil) ranges and from various geographical locations. The PVT data in the databank cover a wide range of conditions, as shown
Table 8.
Talebi et al. (2014) developed two models based on Multilayer Perceptron
(MLP) and Radial Basis Function (RBF) neural networks for prediction of Pb, and
considered the Pb to be a function of Rs, g , T and API. At the end, the MLP-ANN and
RBF-ANN models prediction results have been compared with sixteen published
correlations. Similarly, in this study two models based on NARX and HW methods
have been built using Rs, g , T and API as inputs and Pb as output. Similar to the
previous section, an ANFIS model also has been built for comparison purposes. The
outlines of the developed NARX, HW and ANFIS models are presented in Table 9.
Moreover, the amount of data for training set and testing set has been selected
equal to the chosen numbers of the RBF-ANN model in Talebi et al. (2014).
Fig. 9 shows cross plots of the developed NARX and HW models predicting Pb.
In cross plots, a close-tting cloud of points about 45 line for all of the data indicate the robustness of the developed models. Table 10 shows the result of statistical quality measures ((Eqs. (6)8)) of NARX and HW models compared with
different approaches for estimation of Pb in the databank.
As can be seen from Table 10, the HW model and especially the NARX model
shows a very good performance estimating Pb from various geographical locations
at various conditions. The superiority of NARX model is also evident from Fig. 9 in
which the cloud points of NARX model is tighter around 45 line than that of HW
model. Talebi et al. (2014) reported in their study that the majority of the presented
correlations have high error and could not accurately estimate the experimental
saturation pressures; among published empirical correlations the Ikiensikimama
and Ogboja (2009) correlation had the worst prediction performance and Arabloo
et al. (2014) correlation had the best result. Table 10 demonstrates that the developed NARX model has the smallest Er, Ea and also it has a high value of R2 close
to 1 in comparison to the two types of ANN models and sixteen empirical correlations presented by Talebi et al. (2014). Therefore, using NARX modeling method
Table 10
Prediction results of Pb by NARX, HW and ANFIS models in comparison with the
published results in Talebi et al. (2014).
Method
Er (%)
Ea (%)
R2
555.5
94.0
0.1
2.8
3.2
2.73
3.28
1.29
0.79
1.37
555.5
94.0
25.7
25.6
18.9
16.94
15.53
16.18
15.06
32.54
0.4
0.77
0.82
0.86
0.86
0.94
0.95
0.92
0.94
0.86
S. Salehinia et al. / Journal of Petroleum Science and Engineering 147 (2016) 4755
Acknowledgment
The authors extend their thanks to Mr. Mohammad Mahdi
Ghiasi for sharing the PVT databank with us that made the improvement of the manuscript possible.
References
Abedini, R., Esfandyari, M., Nezhadmoghadam, A., Rahmanian, B., 2012. The prediction of undersaturated crude oil viscosity: an articial neural network and
55