Predict Natural Gas Water
Content
4
CONTENTS
4.1 Introduction ....................................................................................................... 33
4.2 Method ............................................................................................................... 34
4.2.1 Artificial Neural Networks ...................................................................... 34
4.3 Results ............................................................................................................... 36
4.4 Discussion .......................................................................................................... 39
4.5 Conclusion ......................................................................................................... 40
Keywords ................................................................................................................... 41
References .................................................................................................................. 41
4.1 INTRODUCTION
Natural gas reservoirs always have water associated with them: gas in the reservoir is
saturated by water. When the gas is produced water is produced too from the reservoir
directly. Other water produced with the gas is water of condensation formed because
of the changes in pressure and temperature during production. In the transmission of
natural gas further condensation of water is troublesome [1]. It can enlarge pressure
drop in the line and frequently goes to corrosion problems. Therefore, water should be
removed from the natural gas before it is offered to transmit in the pipeline. For these
argue, the water content of sour gas could be important for engineering attention. In a
study of the water content of natural gases Lukacs [1] measured the water content of
pure methane at 160°F and pressures up to 1,500 psia also Gillespie et al. [2] predicted
the water content of methane in the range of 122–167°F and for pressures from 200
to 2,000 psia. Sharma et al. [3] proposed a method for calculating the water content
of sour gases, originally designed for hand calculations, but it was slightly compli-
cated. Bukacek [4] suggested a relatively simple correlation for the water content of
sweet gas, based on using an ideal contribution and a deviation factor. McKetta et al.
published a chart for estimating the water content of sweet natural gas. This chart has
been modified slightly over the years and has been reproduced in many publications
[5]. Recently, Ning et al. [6] proposed a correlation based on the McKetta et al. chart.
This correlation reveals how difficult it can be to correlate something that is as seem-
ingly simple as the water content of natural gas. Maddox [7] developed a method for
estimating the water content of sour natural gas. His method assumes that the water
34 Advanced Process Control and Simulation for Chemical Engineers
content of sour gas is the sum of three terms sweet gas contribution (Methane, CO
2
,
and H
2
S).
Most of the traditional methods work in the limited range of pressure and tem-
perature and they have a good accuracy in this limited range, which is near the ideal
equilibrium condition. But in the high pressure and temperature gases have nonlinear
behavior that these methods cannot predict the gas behavior [10]. The ANN as a good
nonlinear function approximator can simulate the nonlinear functions with high ac-
curacy [14, 16]. In this chapter we predicted the water content of the sour natural gas
mixtures with the ANN method. The results show the ANN’s capability to predict
the measured data. We compare our results with the other numerical and analytical
methods. For example Wichert and Bukacek Maddox. These comparisons con rm the
superiority of the ANN method.
In this chapter a new method based an (ANN) for prediction of natural gas mixture
water content is presented. The dehydration of natural gas is very important in the
gas processing industry, for design of facilities of the production, transmission, and
processing of natural gas. It is necessary to remove water vapor present in the gas
stream that may cause hydrate formation at low temperature conditions that may plug
the valves and ttings in gas pipelines. In this study, the available data for mixtures
and available methods for predicting the water content of sour gas have been studied.
Based on obtained results from ANN simulation, our methods is more accurate than
current used methods and can be used in gas engineering studies.
4.2 METHOD
4.2.1 Artificial Neural Networks
The ANN is constructed as a massive connection model of simply designed comput-
ing unit called “neuron”. Figure 1 illustrates a simple model of n-inputs single-output
neuron. All the input signals are summed up as z and the amplitude of the output signal
is determined by the nonlinear activation function
()fz
. In this work, we employ the
modified sigmoid function
()fz
given as follow [14]:
1
()
1
kz
kz
e
fz
e
=
+
(1)
FIGURE 1 Basic model of multi-inputs one-output neuron.

Get Advanced Process Control and Simulation for Chemical Engineers now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.