literature reviews
write two literature reviews about:
– Environmentally Friendly Well Testing
– ANN Powered Virtual Well Testing.
summaries from the attached files.
Copyright 2002, Society of Petroleum Engineers Inc.
This paper was prepared for presentation at the SPE International Conference on Health,
Safety and Environment in Oil and Gas Exploration and Production held in Kuala Lumpur,
Malaysia, 20–22 March 2002.
This paper was selected for presentation by an SPE Program Committee following review of
information contained in an abstract submitted by the author(s). Contents of the paper, as
presented, have not been reviewed by the Society of Petroleum Engineers and are subject to
correction by the author(s). The material, as presented, does not necessarily reflect any
position of the Society of Petroleum Engineers, its officers, or members. Papers presented at
SPE meetings are subject to publication review by Editorial Committees of the Society of
Petroleum Engineers. Electronic reproduction, distribution, or storage of any part of this paper
for commercial purposes without the written consent of the Society of Petroleum Engineers is
prohibited. Permission to reproduce in print is restricted to an abstract of not more than 300
words; illustrations may not be copied. The abstract must contain conspicuous
acknowledgment of where and by whom the paper was presented. Write Librarian, SPE, P.O.
Box 833836, Richardson, TX 75083-3836, U.S.A., fax 01-972-952-9435.
Abstract
Burning hydrocarbons during cleanup and well-testing
operations produces toxic gases, soot, acid rain, unburned
hydrocarbons and noise. Not only do these emissions have a
damaging impact on the environment, but they also impose an
economic impact: the cost of the oil and gas flared and the cost
of the equipment used during the flaring operations.
A joint task force between two offshore operating
companies in Abu Dhabi, United Arab Emirates (U.A.E.),
with the help of the contracted service provider, worked to
implement innovative solutions to achieve flaring-emission
elimination targets and eliminate environmental risk.
Innovative equipment modifications and design, coupled
with new operational procedures, were implemented to
neutralize the fluids used to prepare the well for production
(allowing well effluents to flow through the test separator
during the cleanup phase) and to use a boosting system to
pump the oil into the sealine (fully eliminating oil flaring).
The initial stages of the solution neutralized the acid
flowed back to surface and eliminated the oil flaring. A
multiphase flowmeter was then introduced to the system. Not
only did the multiphase flowmeter enhance operation
flexibility, confidence in the information acquired, and
accuracy of the results, but it also eliminated gas flaring after
the cleanup period. The minimal pressure drop across the
meter and the high-pressure rating of the meter allow well
effluents to flow naturally through the sealine without
separating the well-effluent phases. Deployment of the
multiphase flowmeter in the system reduced the gas flaring by
about 60% during the overall job.
Introduction
Conventionally, during cleanup and well-testing operations,
both oil and gas are burned away into the atmosphere. The
combustion efficiency of fully atmospheric oxidation is
insufficient. Oil- and gas-flaring operations create significant
amounts of emissions that contain unburned hydrocarbons,
carbon monoxide and nitrogen oxides, which produce acid
rain, smog, ozone at ground levels, and greenhouse gases in
the upper atmosphere.
Acid rain depletes soil, pollutes water, damages forests,
endangers animal habitats and food chains, and corrodes
human-made structures, such as buildings, statues,
automobiles, and other artifacts made of stone or metal. Smog
and ozone cause human respiratory ailments, such as asthma,
bronchitis and emphysema. Most scientists believe that
greenhouse gases are a major cause of global warming.
Increased concentrations of water vapor, carbon dioxide,
methane and other greenhouse gases trap heat energy in the
earth’s atmosphere. A gradual rise in the earth’s surface
temperature is expected to melt polar ice caps and glaciers,
expanding ocean volume and raising sea level, flooding some
coastal regions and even entire islands.
Middle Eastern countries, including the U.A.E. with its
low-lying coastal areas, are concerned about rising sea levels
and potential flooding caused by global warming. They are
concerned about increased radiation of heat and light from
global warming, leading to regional desertification. As major
producers of oil and gas, they are concerned about the
deterioration of air quality from inefficient combustion of a
sour gas supply.
Abu Dhabi is blessed with a charming environmental
heritage. Nevertheless, the environment in this part of the
world is no less fragile than anywhere else.
Recognizing mounting international concerns over
environmental issues, a joint task force was formed in June
1997. The Abu Dhabi Marine Operating Company and the
Zakum Development Company, with the assistance of
Schlumberger, the testing services provider, worked to
implement pioneering solutions for optimizing acid
neutralization, reducing flaring operations in the short term,
and ultimately achieving zero hydrocarbon flaring to eliminate
environmental risk during well-testing operations(1-2).
SPE 74106
Environmentally Friendly Well Testing
Y. El-Khazindar,SPE, Schlumberger, M. Ramzi Darwish, ADMA-OPCO, and A. Tengirsek, Schlumberger
2 Y. EL-KHAZINDAR, R. DARWISH AND A. TENGIRSEK SPE 74106
Environmentally Friendly Well Testing
This paper describes the equipment and processes used to
achieve zero hydrocarbon flaring.
The First Stages: Acid Neutralization and Oil Reinjection.
The separation and reinjection of oil was introduced in June
1998 (see Fig. 1). In this process, single-phase oil-reinjection
pumps, specially designed to overcome high sealine pressures
of up to 1300 psi, were used to reinject the oil back into the
production sealine. They covered the range from 12,000
BOPD at 410 psi to 3500 BOPD at 1300 psi. The use of
reinjection pumps, which eliminated the need for oil flaring
during postcleanup operations, reduced the total oil flared
by 65%.
To stimulate wells after drilling or workover operations,
10 to 15 gal/ft of 15% HCl are pumped downhole. The spent
acid flowing back to surface typically has a pH of 2 to 3. In
February 2000, an acid neutralization system was introduced
(see Fig. 2). In this process, neutralizing agents are used to
keep the pH of the effluents flowing back to surface after an
acid job between 5.5 and 6. Na2CO3 was chosen because it is
soluble in water, cost effective and generally available on
well sites.
The neutralization system keeps the pH of water dumped
overboard the rig between 5.5 and 6. Furthermore, it allows oil
separation from the start of flowback operations so that the
reinjection pumps can inject 100% of the oil back into the
production sealine.
The neutralization system involves pumping demulsifying
agents upstream of the choke manifold and pumping the
neutralizing agent, Na2CO3, downstream of the choke
manifold. The neutralizing agent then flows into a test
separator, a 100-bbl dual-compartment skimmer, where
chemical treatment reduces the oil-in-water content to 100
ppm before the water is dumped overboard.
Introducing the neutralization system and the reinjection
pumps eliminated the need for oil-flaring operations. Even
though initial stages considerably reduced emissions to
atmosphere, improving the system to eliminate gas flaring
during cleanup and well-testing operations remained
a challenge.
The PhaseTester multiphase flowmeter. In May 2001, the
PhaseTester* portable multiphase periodic well testing
equipment(3-5) was introduced to the setup (see Fig. 3). The
PhaseTester’s high working pressure of 5000 psi allows
placing the tool upstream of the choke manifold (see Fig. 4).
This tool was selected to
• reduce the amount of gas flared by
approximately 60%
• eliminate unnecessary shut-ins and flow disturbance
during testing operations (for example, during a
helicopter landing)
• provide a reliable, stand-alone flow rate
measurement.
* Mark of Schlumberger
The PhaseTester multiphase flowmeter simultaneously
measures the total mass flow rate of the stream passing
through, with a venturi meter, and the individual phase
fractions, with a dual-energy gamma fraction meter. Working
on the multiple-energy principle, the detector picks up the total
count of photons hitting the sensor, as well as the energy of
each hit. The high-speed detector produces a signature count
rate, over the two peak energy bands, which is a function of
the measured medium. Hits at two different energy levels are
filtered out and used for the fraction of oil, water and gas
calculations. The sampling frequency of 45 Hz is sufficient to
define the continuous variations in the process flow.
The measuring section includes the venturi meter and the
dual-energy gamma fraction meter. Both measurements—
performed at the same time and place—eliminate anomalies or
inaccuracies associated with meters that have a series of
sensors implemented along a pipe and that do not detect the
same flow instantaneously.
The PhaseTester multiphase flowmeter uses a blind tee in
the flowline upstream of the measuring section to impose a
predictable flow shape onto the flowstream. Effectively
removing flow anomalies imposed by downhole conditions
and surface piping, this tee eliminates high-frequency flow
instabilities in the measuring section.
With an American Petroleum Institute (API) 6A rating,
the PhaseTester multiphaseflowmeter does not require
additional shutdown and pressure-relief systems. The
PhaseTester Vx* multiphase well testing technology can be
used to accept fluids directly from the flowline and, after
measurement, flow them back naturally to the production
sealine without any boosting services. Pressure loss across the
system is typically 3 to 30 psi, much lower than for a
conventional test-separation system.
Testing. Between May 15 and October 1, 2001, 23 wells were
cleaned up and tested using the reinjection, neutralization
system and PhaseTester multiphase flowmeter combination.
The operation involved 36 postcleanup flow tests. Flowing
conditions during the flow periods were
• wellhead flowing pressure range: 90–1300 psi
• oil flow rate range: 400–5500 BOPD
• gas flow rate range: 0.3–4.0 MMscf/D
• gas volume fraction (GVF) range: 60–98%
• CO2 range: 1.5–8.0%
• H2S range: 0–4%
• basic sediment and water (BS&W) range: 0–34%
Figs. 5 through 11 plot the distribution of these parameters
against the number of flow periods.
The 36 flow tests were compared to a traditional test
separator(6-7). Various authors have mentioned the difficulty of
making comparisons with test separators (for example, Ting8
or Amdal et al.9). Separators are limited to performing a
reasonable liquid-to-liquid separation. In most tests the water
cut is calculated from in-line sampling from the choke
manifold. The PhaseTester tool obtains reliable water
measurements with the dual-energy spectral gamma-ray
SPE 74106 ENVIRONMENTALLY FRIENDLY WELL TESTING 3
composition meter because this nuclear determination is not
sensitive to the distribution of the phases.
Uncertainties are not limited to those of the individual oil
and gas meters installed on a test separator. Other factors that
can affect the separator uncertainties are
• meter factor drift caused by gas entrainment in the
liquid leg of the test separator
• slugging of the wells, which affects
test-separator performance
• an operator-dependent process
• poor liquid-to-liquid separation
• overall accuracy affected by the whole system (back
pressures, lines, controls, etc.)
• frequency of data gathering.
For a calibrated separator operated by a dedicated crew,
the uncertainties are expected to be
• gas uncertainty in the range of 5 to 8%
• total liquid uncertainty in the range of 5 to 8%.
Comprehensive preparation of the reference separator was
performed in advance, ensuring a proper conclusion. A
comparison of flow rate results between the PhaseTester tool
and the reference separator indicated that the PhaseTester tool
performed within its operating specifications, yielding the
PhaseTester multiphase flowmeter uncertainty figures +/- the
separator uncertainties.
The flow rate uncertainties(10) for the PhaseTester flowmeter
are as follows:
Liquid:
The larger of 2.5% of the reading, or 300 bbl/d, for
GVF between 0 and 98%
Gas:
The larger of 1% of the reading, or 140 scf/d, for
GVF between 0% and 30%
The larger of 3% of the reading, or 420 scf/d, for
GVF between 30% and 60%
The larger of 10% of the reading, or 1410 scf/d, for
GVF between 60% and 90%
The larger of 15% of the reading, or 2120 scf/d, for
GVF between 90% and 95%
Water-Liquid Ratio (WLR):
± 3% absolute for GVF between 0% and 70%
± 4% absolute for GVF between 70% and 80%
± 5% absolute for GVF between 80% and 90%
± 8% absolute for GVF between 90% and 95%.
Toward Zero Gas Flaring. The ultimate goal is to achieve a
flaring-free operation. As a step toward this goal, the
PhaseTester multiphase flowmeter was deployed to reduce gas
flaring to a minimum. The PhaseTester flowmeter was
expected to decrease gas flaring by approximately 60% during
the overall job, as well as eliminate unnecessary shut-ins and
flow disturbance during the testing operations.
After the flowback and acid neutralization, once the
wellhead pressure increased to overcome the production
sealine pressure, well effluents bypassed the conventional
separator system and flowed naturally through the PhaseTester
tool into the production sealine. Separating, boosting and
flaring operations were not required. The extremely low
pressure drop across the PhaseTester tool helped to achieve
gas-flaring reduction.
Confidence in the PhaseTester multiphase flowmeter’s
measurement reliability and flexibility was developed during
its evaluation over 36 flow tests. The PhaseTester multiphase
flowmeter was then deployed on three tests to reduce gas
flaring. Table 1 shows the reduction in gas flaring when the
PhaseTester multiphase flowmeter was integrated into the
system. (Gas is typically flared during the initial
cleanup phase.)
TABLE 1—[Summary of gas flaring reduction results]
Well no. 1 Well no. 2 Well no. 3
Total job duration, hours 75 80 41
Total gas produced, MMscf 13.6 8.3 3.6
Gas flared, MMscf 3.20 0.54 0.77
Gas flared, % 24 7 21
Gas injected, MMscf 10.4 7.7 2.9
Gas Injected, % 76 93 79
Future Plans. Various studies have been carried out to define
practical and economical means of fully eliminating the gas
flaring. A multiphase pump is currently being considered as a
solution. The challenges to designing a multiphase pump for
this application include the pump capability to cover a wide
range of flow conditions, as well as size and power
requirements. The joint task force is currently studying
technical details and performance of a multiphase pump
specifically designed to suit a wide range of flow conditions.
The current water treatment skimmer system is capable of
achieving an oil-in-water level of approximately 100 ppm.
Different options were considered to achieve an oil-in-water
level of less than 15 ppm, the environmental emissions
guidelines limit specified by Abu Dhabi National Oil
Company’s Health, Safety and Environment policy. The joint
task force proposed an integrated water deoiling package. Full
feasibility and Hazardous and Operability studies were
performed. The water deoiling unit, currently being
manufactured, is planned for utilization in January 2002.
The water deoiling unit was designed to meet the
following criteria:
• a compact integrated solution including a degasser,
hydrocyclone, reject oil tank, pumping units and
control panel, all on one skid that can be
accommodated easily on the rig/barge without
inflicting space limitations
• the ability to recycle the liquids within the system to
ensure an optimum oil-in-water level
• the ability to cover a wide range of flow rates and
cope with changing flowing conditions. The system is
capable of handling up to 6,000 B/D of water with
oil-in-water levels of up to 1% at the inlet of
the system.
4 Y. EL-KHAZINDAR, R. DARWISH AND A. TENGIRSEK SPE 74106
Figure 12 is a schematic for the proposed future setup.
Conclusions
During the initial stages of the project, utilizing acid
neutralization and oil-reinjection systems achieved zero oil
flaring. After integrating the PhaseTester multiphase
flowmeter into these systems, the following benefits
were observed:
• When the wellhead pressure is high enough to
overcome the production sealine pressure, the well
effluents flow naturally through the PhaseTester
multiphase flowmeter (bypassing the separator) into
the production sealine. Gas flaring is eliminated
(because of the minimal pressure drop across the
PhaseTester flowmeter), reducing the amount of gas
flared during the whole job by more than the
targeted 60%.
• The PhaseTester multiphase flowmeter results,
compared to a reference test separator, showed that it
performed within its operating specifications and
provided reliable, stand-alone flow rate
measurements.
• Shut-ins to accommodate helicopter landings were
eliminated because fluids flow directly through the
PhaseTester multiphase flowmeter into the
production sealine. Furthermore, helicopter flights are
no longer dependent of the flow programs.
Eliminating the risk to the environment posed by flaring
hydrocarbons during well testing operations is a challenge.
Keys to achieve environmentally friendly well
testing operations:
– understanding the flow conditions and
operational constraints.
– setting reasonable targets to achieve flaring
free operations.
– examining and revising the existing
operational procedures.
– looking for areas in which a significant value could
be achieved by implementing innovative ideas
and solutions.
The deployment of an acid neutralization system and oil
reinjection pumps to completely eliminate oil flaring as well
as the utilization of the PhaseTester multiphase flow meter to
reduce the gas flaring by more than 60% are examples of
solutions that can be implemented to achieve environmentally
friendly well testing operations.
Acknowledgments
The authors would like to thank the management of ADMA-
OPCO and Schlumberger for permission to publish this paper.
References
1. Messiri A., Al Attas, M.O., and Mohamed, N.: “Towards
Zero Flaring Emission,” paper ADIPEC 0964, presented at
the 2000 Abu Dhabi International Petroleum Exhibition and
Conference, Abu Dhabi, UAE, October 15–18.
2. Hassan, M.M., Fadaq, A.S. and Beadie, G.: “Reduction of
Well Emission During Clean Up and Testing Operations by
Rig,” paper SPE 68151, presented at the 2001 SPE Middle
East Oil Show and Conference, Bahrain, March 17–20.
3. Kontha, I.N.H, Weimer, B, Retnanto, A., Azim A and
Martinon, D.: “Monitoring Well Performance Using
Multiphase Flow Meters,” paper SPE 68718, presented at
the 2001 SPE Asia Pacific Oil and Gas Conference and
Exhibition, Jakarta, Java, Indonesia, April 17–19.
4. “Multiphase Flow Meters: A New Way to test Wells in
Production,” Hart First Look (September 1999).
5. Mus, E. A, Toskey, E.D and Bascoul, S.J.F: “Added Value
of a Multiphase Flow Meter in Exploration Well Testing,”
paper OTC 13146, presented at the 2001 Offshore
Technology Conference, Houston, Texas, USA, April 30–
May 3.
6. Atkinson, D.I, Berard, M and Segeral, G.: “Qualification of
a Nonintrusive Multiphase Flow Meter in Viscous Flows,”
paper SPE 63118, presented at the 2000 SPE Annual
Technical Conference and Exhibition, Dallas, Texas, USA,
October 1–4.
7. Theuveny, B.C., Segeral, G. and Pinguet, B.: “Multiphase
Flowmeters in Well Testing Applications,” paper SPE
71475, presented at the 2001 SPE Annual Technical
Conference and Exhibition, New Orleans, Louisiana, USA,
September 30–October 3.
8. Ting, V.C.: “Effects of Non-Standard Operating Conditions
on the Accuracy of Orifice Meters,” SPE Production &
Facilities (February 1993) 58.
9. Amdal, J., Danielsen, Dykesteen, E, Flølo, D., Grendstad,
J., Hide, H.O., Moestue, H., and Torkildsen, B.H.:
Handbook of Multiphase Metering, Norwegian Society for
Oil and Gas Measurement, (1997).
10. Retnanto, A.: “Production Optimization Using Multiphase
Well Testing: A Case Study from East Kalimantan,
Indonesia,” paper SPE 71556, presented at the 2001 SPE
Annual Technical Conference and Exhibition, New
Orleans, Louisiana, USA, September 30–October 3.
Metric Conversion Factors
cp x 1.0* E–03 = Pa·s
bar x 1.013 25* E+05 = Pa
psi x 6.894 757 E+00 = kPa
bbl x 1.589 873 E–01 = m3
B/D x 6.624 471 E–03 = m3/h
ft3 x 2.831 685 E–02 = m3
ft3/D x 1.179 869 E–03 = m3/h
lb/ft3 x 1.601 846 E+01 = kg/m3
*Conversion factor is exact.
SPE 74106 ENVIRONMENTALLY FRIENDLY WELL TESTING 5
Fig. 1—Schematic of the surface well testing setup and
reinjection pump
Fig. 2—Schematic of the surface well testing setup,
reinjection pump and neutralization package
Fig. 3—Schematic of the surface well testing setup,
reinjection pump, neutralization package and PhaseTester
multiphase flowmeter
Fig. 4—The PhaseTester multiphase flowmeter
0
2
4
6
8
10
12
90-200 200-500 500-750 750-1000 1000-1500 1500-1800
Wellhead Flowing Pressure (Psi)
N
um
be
r
of
te
st
s
pe
rf
or
m
ed
Fig. 5—Wellhead flowing pressure distribution versus the
number of tests
0
2
4
6
8
10
12
14
>400 400-1000 1000-
2000
2000-
3000
3000-
5000
4000-
5500
Oil Flow rate (bbl/d)
N
um
be
r
of
te
st
s
pe
rf
or
m
ed
Fig. 6—Oil flow rate distribution versus the number
of tests
6 Y. EL-KHAZINDAR, R. DARWISH AND A. TENGIRSEK SPE 74106
0.0
1.0
2.0
3.0
4.0
5.0
6.0
7.0
8.0
9.0
10.0
>0.3 0.5-0.75 0.75-1 1-1.5 1.5-2 2-3 3-4
Gas Flow Rate (MMscf/D)
N
um
be
r
of
te
st
s
pe
rf
or
m
ed
Fig. 7—Gas flow rate distribution versus the number
of tests
0
2
4
6
8
10
12
14
16
60-70 70-80 80-90 90-95 95-98
GVF (%)
N
um
be
r
of
te
st
s
pe
rf
or
m
ed
Fig. 8—Gas volume fraction distribution versus the
number of tests
0
2
4
6
8
10
12
14
16
18
1.5-2 2-3 3-5 6-8
CO2 (%)
N
um
be
r
of
te
st
s
pe
rf
or
m
ed
Fig. 9—Carbon dioxide distribution versus the number
of tests
0
2
4
6
8
10
12
14
16
18
0 0.2-1 1-1.5 1.5-2 2-4
H2S (%)
N
um
be
r
of
te
st
s
pe
rf
or
m
ed
Fig. 10—Hydrogen sulphide distribution versus the
number of tests
0
2
4
6
8
10
12
14
0 1 2 3 4 5 6 7 8 9 10 24 34
BS&W
N
um
be
r
of
T
es
ts
p
er
fo
rm
ed
Fig. 11—Basic sediment and water distribution versus the
number of tests
Fig. 12—Schematic of the reinjection pump, neutralization
package, PhaseTester multiphase flowmeter, water
deoiling unit and multiphase pump
OTC 24981
ANN Powered Virtual Well Testing
A. Aggarwal, S. Agarwal, Indian School of Mines
Copyright 2014, Offshore Technology Conference
This paper was prepared for presentation at the Offshore Technology Conference Asia
held in Kuala Lumpur, Malaysia, 25–28 March 2014.
This paper was selected for presentation by an OTC program committee following review
of information contained in an abstract submitted by the author(s). Contents of the paper
have not been reviewed by the Offshore Technology Conference and are subject to
correction by the author(s). The material does not necessarily reflect any position of the
Offshore Technology Conference, its officers, or members. Electronic reproduction,
distribution, or storage of any part of this paper without the written consent of the Offshore
Technology Conference is prohibited. Permission to reproduce in print is restricted to an
abstract of not more than 300 words; illustrations may not be copied. The abstract must
contain conspicuous acknowledgment of OTC copyright.
Abstract
Due to the drying up of old oil fields throughout the
globe, the age of easy oil is over and the newly discovered
fields have reservoirs with complex heterogeneous media.
The reservoir parameters are identified indirectly by
correctly interpreting well test model which is recognized
by the feature of pressure derivative curves. Well testing
involves creation of disturbance in fluid flow by injecting
liquids and simultaneously recording the pressure
transient data. Lost production, equipment and personnel
costs turn well testing as highly cost intensive job making
it difficult to cover all the important wells in a particular
field. But with the advent of artificial neural networks
(ANN) it is now possible to generate synthetic pressure
transient data. This technique provides a basis to leach out
detailed information from the available pressure transient
data and it doesn’t eradicate the need for actual well tests.
This technique can also prove to be very vital in cases
where equipment breakdown may have taken place and
full set of data couldn’t be availed. This simulated well
testing involves training of a neural network from
pressure transient data obtained from designated wells in
the field, which has the potential to generate pressure
transient responses at other well sites where no well test
has been conducted.
In this paper a 3 layer multi-layer perceptron (MLP) Time
Delay Neural Network – NARX model has been designed
working on resilient backpopagation algorithm for
training. Cubic Spline Interpolation has been used from
enriching the data before feeding it to NARX model. A
simulated example which highlights the efficiency of
NARX model in attaining accurate synthetic pressure
transient data has been discussed. The neural network is
successful in predicting well test interpretation model.
The ANN thus produces expeditious and reliable synthetic
data which has the potential to revamp the industry.
Introduction
Due to the complex structures and heterogeneous media,
of oil and gas reservoirs, characterizing reservoirs
precisely is a herculean task. Petroleum Engineers solve
this challenge by acquiring and analyzing in depth
reservoir information, which is crucial for the study of the
reservoir performance (Vaferi et al., 2011). Well Testing
or Pressure Transient Testing has proved to be a powerful
reservoir characterization tool to study such complex
media (Muskat, 1937). Pressure testing is conducted by
recording the well bore bottom hole pressure responses
which are created as result of induced flow disturbances.
The most general test methods are 1) By creating a
pressure drawdown in the wellbore by producing the well
at a constant rate, after keeping it in shut-in condition for
a set period (Figure 1); 2) By developing a pressure
build-up in the wellbore by shutting-in at the bottom hole,
due to which formation fluids c
ann
ot flow into the
wellbore. Thus, measured flow rates and pressures during
these tests can provide sufficient information for the
characterization of the tested well (Matthews et al., 1967;
Earlougher et al., 1977).
Well testing enables accurate determination of cash flow
of the well by obtaining comprehensive reservoir
description. The core purpose of well testing lies in the
determination of the fluid production capability of a
formation and incurring the inherent reason for
productivity of well. A meticulously designed and
performed well test operation can provide accurate facts
and figures about formation permeability, average
conductivities, extent of wellbore damage or stimulation,
reservoir pressure, and extended testing may deliver
information regarding underlying geological barriers
(faults, pinch-outs, etc.), reservoir boundaries and
heterogeneities (Matthews et al., 1967; Earlougher et al.,
1977). On the same note Da Prat et al. in 1992 have
classified well test objectives into short term and long
term objectives. Obtaining the reservoir description in the
vicinity of the well bore, from analysis of gathered data,
are categorized as short term objective. While, long term
objectives of well test are to analyze gathered data for
obtaining complete description of the whole reservoir.
However, huge production time losses, manpower and
equipment costs turn it into a cost intensive affair
(Dakshindas, 1999). Since its introduction to the
2 OTC-24981-MS
petroleum engineering industry around 1937 by ground
water hydrology scientists (Gringarten, 2008), plethora of
novel technologies have been introduced both for data
acquisition and analysis. The introduction of electronic
pressure gauges was a great step ahead in enhancing
obtaining of reservoir description, and continuously
upgraded versions of these are being developed to meet
current challenges. Moreover, for expeditious data
acquisition and interpretation, and in depth rigorous
insight into the reservoir, industry anticipates close
integration of advanced microprocessors and innovative
computational techniques.
Theory
This paper features a unique approach for synthetic
pressure transient data generation by application of Cubic
Spline Interpolation technique and Artificial Neural
Networks (ANN). The main objective of the work
presented is to formulate an artificial neural network
which has the ability to forecast transient pressure
responses without any need for an actual well test. The
data thus generated can be analyzed using traditional well
test analysis methods for reservoir characterization. In a
nutshell, this is made possible by training the neural
network using pressure transient data available from
proximate wells, flow parameters values and reservoir
characteristics, and then the error is reduced significantly
by retraining the network and testing the network
efficiency by comparing the network results to the data
available from actually conducted well tests.
Cubic Spline Interpolation
Data points are interpolated by using cubic spline curve
fitting (CSCF) technique. This can be realized by
arranging the available data into a table [pi,qi], i ϵ [0,n],
thus providing with n intervals for n+1 control points. The
cubic spline curve is a continuous piecewise third order
polynomial, satisfying all the input values (Figure 2).
Each polynomial’s second derivative is usually set to zero
at the endpoints, as this offers a boundary condition which
makes the system of n-1 equations complete. Also this is
not the only possible option, as other boundary conditions
can also be used. Thus a “natural” cubic spline is
produced that results to an elementary tridiagonal system,
which is computed to deliver coefficients of the
polynomials.
The main purpose of using CSCF technique is to increase
data points between minimum and maximum, as with
higher amount of input data points better results through
ANN can be obtained. Moreover its high accuracy of
estimation and capacity to produce seamless curves makes
it a popular interpolation technique.
Neural Networks
Neural Networks are a form of massive parallel
distribution of biologically inspired processing units
comprising of smaller units termed as neuron, as these
seek to imitate the brain microstructure (Noriega, 2005).
The multilayer perceptron, a widely applied example of
artificial neural networks, is a programming epitome that
was developed around half a century back by W.S.
McCulloch and W. Pitts in 1943. The neural network is an
intensely parallel, distributive, adaptive, non-arithmetic
and non-digital system, which can solve problems ranging
from pattern recognition, to innovative symbolic
manipulation
Biological Basis
The neural network attempts to model functioning of
biological nervous system or human brain. The brain is
made up of huge parallel interconnected processing units.
These processing units or neurons are electrically
excitable, which through electrical and chemical signals
transmits and process information. Majorly dendrites,
soma and axon form the neuron body. A neuron receives
the input information from other neurons in the network
connected to it at synapses through dendrites. The
received information is then processed at the soma, which
integrates it over time and space, the generated output is
activated depending on the input. The synapses located at
the end of axon transmit the output signal to connected
dendrites. This forms an intensely complex parallel
computer.
Similarly, an artificial neural network is a composite
architecture of soft computing based neurons integrated
into numerous parallel layers which are connected to all
the neurons of preceding and succeeding layers by the
means of weights. A variety of developed neurons and
network specifications can be programmed to interpret,
recognize and retrieve patterns to solve optimization
problems and clear noise from input data (Kumar, 2012).
Network Mechanics
The neural network has two types of learning processes,
supervised and un-supervised. Supervised learning or
training process is the crux of ANN mechanics, initially
random weight values (between -1 to 1) are assigned to
network connections, furthermore the network analyses
input data to estimate weights of the connections between
successive neuron layers (Figure 3). The data is input to
the first layer in which each neuron multiplies the data
with the associated weight and is summed with a bias.
The result is then fed to an activation function, or transfer
function, of the neuron which determines if the result is
above the threshold or not, to instruct the neuron for
transmitting data. This output to activation function is
calculated by
The output values and the input values are compared for
error and then accordingly weights are updated for
OTC-24981-MS 3
minimising error. This process is repeated a number of
times (epochs) to achieve precise weight values. Now, the
network output is tested against the input data sets for
measuring the prediction quality, which if acceptable can
be applied to generate data, for environments whose
outputs are unknown.
Background
These are being applied to counter a large variety of
challenges from simple pattern-recognition task, to
advance symbolic manipulation (Noriega, 2005). Neural
networks have gained ground in geophysical application
and well test interpretation in last couple of decades.
Their effective application is to provide remarkably
precise solution to solve a range of problems like well-log
analysis (Huang et al., 1991), seismic deconvolution
(Wang et al., 1992; Calder´on–Mac´ias et al., 1997),
waveform recognition and first-break picking (Murat et
al., 1992; McCormack et al., 1993); for electromagnetic
(Poulton et al., 1992), magnetotelluric (Zhang et al.,
1997), and seismic inversion purposes (R¨oth et al., 1994;
Langer et al., 1996; Calder´on–Mac´ias et al., 1998);
event classification (Dowla et al. 1990; Romeo, 1994),
zone identification (White et al., 1995), trace editing
(McCormack et al., 1993) and for shear-wave splitting
(Dai et al., 1994), in geophysics domain (Van der Bann et
al., 2000), while making significant contribution to the
well test interpretation domain by enabling permeability
prediction (Singh et al., 2005), reservoir model
identification (Vaferi et al., 2011), well test model
recognition (Sung et al., 1996) and many more.
However, not much application of this Artificial
Intelligence (AI) technology has been observed in the
generation of synthetic well test Pressure Transient Data
(PTD) and rigorous utilization of advanced neural
network functions, training algorithms and advanced
computational techniques in this specific field have not
been witnessed.
Time Delay Neural Networks (TDNN
)
The designing of neural networks can be understood by
classifying them into two categories dynamic and static.
Static networks are comparatively simple with neither
feedback elements nor delays. On the other hand, in case
of dynamic networks, the output generated is governed by
current inputs, previous inputs, outputs and network
states. However, dynamic networks can be trained by the
same algorithms used by static networks but due to
complex nature of error surfaces computing gradients is
more intensive. Moreover in this study NARX model has
been implemented which is a type of dynamic network or
more specifically Time Delay Neural Network (TDNN)
(Figure 4).
NARX Neural Network Model
Instead of conventional dynamic networks that are either
feedforward networks or focused networks, with only
input layer dynamics. In this, fully connected feedback
connections are enclosed in numerous layers of a
recurrent dynamic network which is Nonlinear
Autoregressive with eXogenous inputs (NARX recurrent
models). Contrary to other recurrent networks, feedback
comes only from output neuron instead from hidden
states, it is modeled with a tapped delay line (embedded
memory) which is clubbed to a delayed feeding line from
the output, second tapped delay line. This type of limited
viewed on part of the input series is referred to as time
window (Diaconescu, 2008). A NARX model is
formulated by the following equation
y(t) = f(y(t-1), y(t-2),….., y(t-ny), u(t-1), u(t-2),….., u(t-nu))
where, y(t) and u(t) denotes input and output signal of the
network at time t, ny and nu signifies input and output
order, while f represent the mapping performed by
Multilayer Perceptron (Siegelmann et al., 1997). The
value of dependent output y(t) is reverted to earlier output
values and values of eXogenous input (Figure 5). This
real-time feeding of output to the network is called as
parallel architecture, which results in more accurate
training and due its purely feedforward architecture, static
backpropagation can be used.
Application Methodology
The steps incurred in throughout this process are
explained below:
1. Candidate Identification: A set of wells are chosen,
which are producing from a particular formation
(zone). Segregate the wells where prediction is to be
done.
2. Information Gathering: Pressure Testing is
performed on the selected zone at all picked well
locations and PTD is recorded. Other vital
information about the test and reservoir is also
acquired.
3. Data Enrichment: NARX works best when highly
dense data sets are fed to it. Thus according to the
type of cures produced by the specific pressure
testing procedure followed, data interpolation
technique is chosen and applied.
4. Normalization: The input data for the NARX is
scaled down to the range of 0 to 1.
5. Network Training: The network is configured with
appropriate parameters and then input data is fed to
the network for training it.
6. Network Testing: Performance of the network is
validated against known data sets, if the results are
4 OTC-24981-MS
unsatisfactory then the network parameters are
tweaked and the NARX is retrained.
7. Prediction: Utilize the trained NARX for simulating
data for unknown outputs.
To minimize error and produce the best pressure transient
predictions, the whole process was tested numerous times
with varied network models and interpolation techniques.
Due to the monotonically increasing nature of pressure
curve generated using PTD the best suited technologies
are identified was Cubic Spline Curve Fitting (CSCF) and
NARX neural model (Figure 6).
Case Study
This case deals with simulator generated pressure build-
up test data considering of five active producing wells for
an infinitely large homogenous field (Figure 7). The data
was generated using analytical simulator, which is based
on principle of superposition and infinite acting line
source solution. All the five wells considered had
identical shut-in and production time, and different flow
rates. The wells are shut-in at 215 hours and the data is
recorded for 67 hours.
The ANN is trained from pressure responses of four wells
and the data for well 5 is predicted. Complete data set for
each well is prepared for training the NARX network.
Each well’s pressure transient data, (tp+∆t)/∆t, modified
inter-well distances, and flow rates along with their
functional links are used as inputs for the network
(Figure). The output from the network is pressure which
is generated by also taking into account the interference
effects from the proximate wells. Modified distance is
formulated to be:
Distmod = QW1 * Dist(W1 – W2)/QW2
After taking into account modified distance and functional
links better prediction results were observed but with
increased CPU usage and network training time.
Similarly, initially 60 data values were available, which
by using Cubic Spline Interpolation were increased to 89.
Resilient backpropagation algorithm was used to update
bias values and connection weights during training
because it enables optimizing the magnitude of weight
change by reducing it in case weights are oscillating and
increasing it when for several iterations weight changes
continuously in the same direction. Sigmoid or
‘squashing’ functions were used as transfer functions for
all the neurons at every layer, as the derivative of sigmoid
function can be swiftly calculated which is needed to be
backpropagated to calculate error. It is defined by:
F(i) = (1+e
-i
)
-1
Where, F(i) is the function output and ‘i’ is the input. The
performance of the network was judged on the basis of
mean square error (MSE). The input set was divided using
interleaved indices. The applied NARX model is a three
layer network with 18 input layer neurons, 25 neurons in
hidden layer and 1 output layer neuron. The time delay
configured for this particular problem is 1:2, thus
producing 87 outputs for 89 inputs.
A good match is observed is observed between the
network and the simulator output (Figure 8-11),
confirming that NARX has the potential to predict well
test pressure responses accurately. The prediction
performed by the network for well 5 is also remarkable
considering the complexity of the problem (Figure 12).
With increased available data from more number of wells
the network will deliver more precise predictions but the
wells must be chosen meticulously to ensure inclusion of
interference effects, flow rate effects, shut-in and
production effects, boundaries and heterogeneity effects.
But the risk that network might get over-trained also
escalates with increased number of training wells.
Conclusions
In this paper a unique synthetic pressure transient data
generation has been introduced. The discussed simulated
field case study has justified the approach and delivered
recommendations on how to increase the accuracy of the
prediction. The precision of the network remarkably
improves when neural network is exposed to variety of
data from more number of strategically selected wells.
Incorporation of more data functional links, multiple
inputs from the field after rigorous iterative testing can
increase reliability of the network.
The NARX model has been able to analyze and interpret
the response almost perfectly which is proved by the
fashion in which the output curve closely traces the
simulator curve. Moreover, for cases where due to some
downhole equipment failure test couldn’t be completed or
some data is lost, by using this we can complete the data.
This doesn’t eradicate the need for actual well tests, but it
remarkably curbs the frequency of actual tests when
clubbed with tactical well test pattern planning. Using
NARX technology more informed well tests can be
designed by extracting more information from the
available data, thus reflecting enormous potential to
revamp the petroleum industry by delivering expeditious
and reliable solutions.
Acknowledgements
The authors are indebted to officials from Schlumberger,
ONGC, Reservoil and Dept. of Petroleum Engineering,
Indian School of Mines Dhanbad for their constant
support during this research. The authors are also obliged
to Mr. Mohit Punjabi, Mr. Swapnil Gupta, Mr. Ajay
Singh, Mr. Paras Goel and Mr. Praveen Pushkar, all from
Indian School of Mines Dhanbad, for always stimulating
and rejuvenating us.
OTC-24981-MS 5
References
1. Bartels, R. H. Beatty, J. C. and Barsky, B. A. 1998.
Hermite and Cubic Spline Interpolation, An Introduction to
Splines for Use in Computer Graphics and Geometric
Modelling, Morgan Kaufmann, San Francisco, CA, Chapter
3: 9-17.
2. Beale, M.H. Hagan, M.T. and Demuth, H.B. 2013. Neural
Network ToolboxTM User’s Guide, The MathWorks Inc.,
MA, USA.
3. Bertolini, A.C. Booth, R.J. Morton, K.L. and Fitzpatrick,
A.J. 2013. Design of Objective Function for Interference
Well Testing, OTC 24513, Offshore Technology
Conference Brazil, Rio de Janeiro, 29-31 October.
4. Burden, R. L. Faires, J. D. and Reynolds, A. C. 1997,
Numerical Analysis, Brooks/Cole, Boston, MA. 6: 120-121.
5. Calder ´on–Mac´ıas, C. Sen, M. K. and Stoffa, P. L. 1997.
Hopfield neural networks, and mean field annealing for
seismic deconvolution and multiple attenuation,
Geophysics: 992–1002.
6. Calder ´on–Mac´ıas, C. Sen, M. K. and Stoffa, P. L. 1998.
Automatic NMO correction and velocity estimation by a
feedforward neural network, Geophysics: 1696-1707.
7. Dai, H. and MacBeth, C. 1994. Split shear-wave analysis
using an artificial neural network? First Break: 605–613.
8. Dakshindas, S.S. Ertekin, T. and Grader, A.S. 1999. Virtual
Well Testing, SPE 5745, SPE Eastern Regional Meeting,
Charleston, West Virginia, 21-22 October.
9. Diaconnescu, E. 2008. The use of NARX Neural Networks
to predict Chaotic Time Series, WSEAS Transactions of
Computer Research.
10. Dowla, F. U. Taylor, S. R. and Anderson, R. W. 1990.
Seismic discrimination with artificial neural networks:
Preliminary results with regional spectral data, Bull. Seis.
Soc. Am.: 1346–1373.
11. Earlougher, R.C. Jr. 1997. Advances in Well Test Analysis,
Monograph Series, SPE, Dallas.
12. Gringarten, A.C. 2008. From Straight Lines to
Deconvolution: The Evolution of the State of the Art in
Well Test Analysis, SPE 102079, SPE Reservoir
Evaluation & Engineering, SPE.
13. Huang, S. C. and Huang, Y. F. 1991. Bounds on the
number of hidden neurons in multilayer perceptrons, IEEE
Trans. Neur. Networks: 47–55.
14. Kumar, A. 2012. Artificial Neural Network as a Tool for
Reservoir Characterization and its Application in the
Petroleum Engineering, OTC 22967, Offshore Technology
Conference, Houston, 30 April – 3 May.
15. Lee, J. 1982. Well Testing, SPE, New York, USA.
16. Lin, T. Giles, L. Horne, B.G. and Kung, S.Y. 1998. A
Delay Damage Model Selection Algorithm for NARX
Neural Networks, University of Maryland Technical Report
17. Matthews, C.S and Russell, D.G. 1967, Pressure Buildup
and Flow Tests in Wells, Monograph Series, SPE, Dallas.
18. McCormack, M. D. Zaucha, D. E. and Dushek, D. W.
1993. Firstbreak refraction event picking and seismic data
trace editing using neural networks, Geophysics: 67–78.
19. McCulloch, W.S. and Pitts, W. 1943. A Logical Calculus
of the Ideas Immanent in Nervous Activity, Bulletin of
Mathematical Biophysics, 5.
20. Mohaghegh, S. Arefi, R. Ameri, S. and Rose, D. 1994.
Design and Development of an Artificial Neural Network
for Estimation of Formation Permeability, SPE 28237, SPE
Petroleum Computer Conference, Dallas. 31 July – 3 Aug.
21. Murat, M. E. and Rudman, A. J. 1992. Automated first
arrival picking: A neural network approach, Geophysics
Prosp: 587–604.
22. Muskat, M. 1937. Flow of Homogeneous Fluids Through
Porous Media, McGraw Hill, New York.
23. Noriega, L. 2005. Multilayer Perceptron Tutorial, School
of Computing, Staffordshire University, Staffordshire.
24. Poulton, M. M. Sternberg, B. K. and Glass, C. E. 1992.
Location of subsurface targets in geophysical data using
neural networks, Geophysics: 1534–1544.
25. R¨oth, G. and Tarantola, A. 1994. Neural networks and
inversion of seismic data, J. Geophys. Res.: 6753–6768.
26. Ramey, H.J. Jr. 1993. Advances in Practical Well-Test
Analysis, SPE 20592, Journal of Petroleum Technology,
SPE, USA.
27. Romeo, G. 1994. Seismic signals detection and
classification using artificial neural networks, Annali di
Geofisica: 343–353.
28. Siegelmann, H.T. Horne, B.G. and Giles, C.L. 1997.
Computational Capabilities of Recurrent NARX Neural
Networks, IEEE Transactions on Systems, Man and
Cybernetics – Part B: Cybernetics, 27 (2): 1083-4419.
29. Singh, S. 2005. Permeability Prediction Using Artificial
Neural Network (ANN): A Case Study of Uinta Basin,
SPE-99286-STU, SPE ATCE, Dallas, 9 – 10 October.
30. Sung, W. Inhang, Y. Seunghoon, R. and Heungjun, P.
1996. Development of the HT-BP Neural Network System
for the Identification of a Well-Test Interpretation Model,
SPE 30974, SPE Eastern Regional Meeting, Morgantown,
17-21 September.
31. Vaferi, B. Eslamloueyan, R. and Ayatollahi, S. 2011.
Automatic recognition of oil reservoir models from well
testing data by using multi-layer perceptron networks,
Journal of Petroleum Science and Engineering, Elsevier
B.V., 77 : 254-262.
32. Van der Baan, M. and Jutten, C. 2000. Neural networks in
geophysical applications, Geophysics, SEA, 65 (4): 1032-
1047.
33. Wang, L.X. and Mendel, J. M. 1992. Adaptive minimum
prediction error deconvolution and source wavelet
estimation using Hopfield neural networks, Geophysics:
670–679.
34. White, A.C. Molnar, D. Aminian, K. Mohaghegh, S.
Ameri, S. and Esposito, P. 1995. The Application of ANN
for Zone Identification in a Complex Reservoir, SPE
30977, SPE Eastern Regional Conference & Exhibition,
Morgantown, West Virginia, 19 – 21 September.
35. Zhang, Y. and Paulson, K. V. 1997. Magnetotelluric
inversion using regularized Hopfield neural networks,
Geophysics Prosp.: 725–743.
6 OTC-24981-MS
Figure 1: A Schematic diagram of drawdown test of a homogeneous reservoir with infinite acting boundary (Vaferi et al. 2011)
(a) (b)
Figure 2: (a) Three polynomials making up a cubic spline; (b) Input curve for cubic spline interpolation
OTC-24981-MS 7
Figure 3: Mathematical neuron (Baan et al., 2000)
Figure 4: A fully connected recurrent Time Delay neural network (Siegelmann et al., 1997)
Figure 5: A NARX neural network with ny = 2, nu = 3 and H= 4 (Lin et al., 1998)
Figure 6: Overall flowchart for synthetic pressure transient data generation system
8 OTC-24981-MS
Figure 7: Case evaluating infinitely large field with 5 wells
Figure 8: Comparison of simulator and ANN data for Training Well 1
Figure 9: Comparison of simulator and ANN data for Training Well 2
3500
3700
3900
4100
4300
4500
4700
4900
5100
210 220 230 240 250 260 270 280 290
P
re
ss
u
re
(
p
si
a
)
Time (hr)
actual
ann
3500
3700
3900
4100
4300
4500
4700
4900
5100
210 220 230 240 250 260 270 280
P
re
ss
u
re
(
p
si
a
)
Time (hr)
actual
ann
OTC-24981-MS 9
Figure 10: Comparison of simulator and ANN data for Training Well 3
Figure 11: Comparison of simulator and ANN data for Training Well 4
Figure 12: NARX model prediction result for Well 5
3500
3700
3900
4100
4300
4500
4700
4900
5100
210 220 230 240 250 260 270 280 290
P
re
ss
u
re
(
p
si
a
)
Time (hr)
actual
ann
3500
3700
3900
4100
4300
4500
4700
4900
5100
210 220 230 240 250 260 270 280 290
P
re
ss
u
re
(
p
si
a
)
Time (hr)
actual
ann
3500
3700
3900
4100
4300
4500
4700
4900
5100
210 220 230 240 250 260 270 280 290
P
re
ss
u
re
(
p
si
2
a
)
Time (hr)
ann