of an Automated

Design of anDesign
Automated
Drilling-Prediction System
Drilling-Prediction System

ata-mining processes are

Second, the status of a particular event or nentially more meaningful and more effundamental in obtaining
well is constantly changing as key drill- ficient for monitoring purposes. Because
predictive benefits of real-time
ing factors change, and monitoring en- real-time data are properly related to
Second,
the
status
of
a
particular event or nentially more meaningful and more efata-mining processes are the
systems and have been progressing
gineers must review all data in detail be- drilling-program and well-correlation
well
is constantly changing
as key
drill-the new
ficient
purposes.
fundamental in obtaining from descriptive
to predictive
data, it is possible
to developBecause
models for
fore manually
defining
statusfor
of monitoring
optimization methods.
These change, and
predicting
outcomes
throughto
new
a system.
Third, a complete
update of a data
ing factors
monitoring
en- real-time
are future
properly
related
the predictive benefits of real-time
methods are enhanced by real-time
report is software systems that automatically regineers must review allgeneral
data well-operations
in detail be- status
drilling-program
and well-correlation
systems and have been progressing
and historic data. Advancedsensor
time consuming. The operations status late, set apart, and announce a potential
fore manually
definingforthe
new
status
it is possible
to develop models for
from descriptive to predictive technologies, improved
data-quality
drilling challenge.
a set
of wells
beingof
drilleddata,
and monitored canupdate
change dramatically
from one future outcomes through new
system. Third, a complete
of a predicting
optimization methods. These control, wellsitea information-transfer
standard-markup-language
(WITSML)
Application
of the Traffic-Light
minute
to thereport
next andis
therefore
requires systems
general well-operations
status
software
that automatically
remethods are enhanced by real-time
data advantages, and virtual real-time
the constant participation of an engineer. Methodology
time
consuming.
The
operations
status
late,
set
apart,
and
announce
a
potential
and historic data. Advancedsensor
drilling-optimization concepts have
Such a report should be automated to de- To reduce the time engineers invest debeen assimilated
the design
and beingrive
ciding where to focus their attention
maximum
from the
best realforinto
a set
of wells
drilled
andbenefit
monidrilling
challenge.
technologies, improved data-quality
implementation
of predictionsystems.
on conventional real-time consoles, the
time and historic
tored
can change dramatically
fromdata.
one
control, wellsite information-transfer
event or well status is defined by intuitive
minute to the next andDrilling-Data
therefore requires
standard-markup-language (WITSML)
the
Traffic-Light
colorsof
used
on the
system interface. They
Mining Application
Introduction
The drilling
industry is aware
of the im- are predefined as green for stable, or on
the constant participation
of an engineer.
data advantages, and virtual real-time
Methodology
the program;
yellow for alert,
or near
of pattern
analysis
past the
As technologies
evolve
and the WITSML
Such
a report
should beportance
automated
to dedrilling-optimization concepts have
Toand
reduce
time engineers
invest
de-the
standard allows data exploitation by performance of correlation wells. It has limits of the program; and red for critical,
rive applications,
maximum benefit
from the
bestdrilling-well
real- ciding
been assimilated into the design and
where
to focus
their attention
or outside
of the program.
This applies to
to similar
experiencmany specialized
more- looked
a particular
drilling aspect
and to the
a genaccurate and time
reliableand
drilling
data are
historic
data.es to predict the probability of
implementation of predictionsystems.
ona particuconventional
real-time
consoles,
eral
drilling-operations
dashboard
able
This or
haswell
available at real-time operation centers lar event or drilling outcome.
event
status
is defined by
intuitive
(RTOCs) to analyze and mitigate drilling been achieved effectively with human in- to reflect the status of several wells being
Drilling-Data
colors
used drilled
on theconcurrently.
system interface. They
multiple
issues. This enhances
and speeds up Mining
the tervention, despite the fact that
Introduction
The drilling
industry
aware
ofthat
theneeded
im- to beare
predefined
as green
forandstable,
or on
The
criterion
color definition
data
families
taken
into
drilling-optimization
process, and
allows is
automatically
applied
the system
account wereand
difficult
to access
forprogram;
differ- areyellow
a small group ofportance
highly skilled
en- analysis
As technologies evolve and the WITSML
ofdrilling
pattern
past
the
for alert,
orbynear
the
as new real-time values, and trends are
gineers to support several wellbore con- ent reasons.
standard allows data exploitation
by
performance
of
correlation
wells.
It
has
limits
of
the
program;
and
red
for
critical,
As well complexity has increased, constantly renewed and compared with
structions simultaneously.
many specialized applications, moreto similar
outside ofrelevant
the program.
This applies
to
historic information.
The status
data-processingortechnoloHowever, looked
the traditional
tasksdrilling-well
of computer experiencbe modified
manually
by a
thegenmoniinstrumentation,
and can
monitoring
are probability
still gies, telemetry
accurate and reliable drilling data
are drilling
es toparameters
predict the
of a particua particular
drilling
aspect
and to
constrained by the constant need for real-time data-acquisition systems have toring engineers if necessary.
available at real-time operation human
centers
lar event
This has
eral todrilling-operations
dashboard able
advanced, providing
the ability
use
intervention.
First, or
the drilling
particu- outcome.
(RTOCs) to analyze and mitigate lar
drilling
beenknowledge
achieved
effectively
with power
human
in- and
to reflect
status of several
wells being
to choose
examine the
field-operations
gained
by computer
More-Accurate
Alerts
increasing
volume of morecomplex
monitoring
engineers isdespite
very valu-theanfact
Traditionally, alerts have been prepared
issues. This enhances and speedsRTOC
up the
tervention,
that multiple
drilled
concurrently.
able but fragile, because it requires the data. This has enabled discovery of pre- by monitoring engineers at RTOCs. Howdrilling-optimization process, andcontinued
allows participation
data families
that needed to be taken into
The criterion and color definition
of team mem- viously undetected drilling patterns ever, most of them were triggered by ena small group of highly skilled drilling
account
were difficult
access
for differautomatically
applied
by theor system
from
correlation
wells and are
known
po- gineers data
bers. enTo ensure
that nothing
is over- to
visualization
alarms disdrilling
looked,
that knowledge
should be gath- tential events from ongoing
played byvalues,
the real-time
gineers to support several wellbore
conent reasons.
as new
real-time
and systems.
trends This
are is
ered and used by an intelligent system. programs, making real-time data expo- inefficient, because it demands signifiand compared with
structions simultaneously.
As well complexity has increased, constantly renewed
cant time from monitoring engineers to
The
status
However, the traditional tasks of computer data-processing technolo- relevant historic
validateinformation.
the accuracy of the
alarm
before
This article, written by JPT Technology Editor Chris Carpenter, contains highlights
an alert manually
is posted. by the monican
be
modified
monitoring drilling parameters are
still
gies,
telemetry
instrumentation,
and
of paper SPE 163709, Design of an Automated Drilling-Prediction System
Therefore, alarms in the computerengineers
if necessary.
constrained by the constant need
for real-time data-acquisition
Strengthening-While-Drilling
Decision Making, systems
by Samuelhave
R. Preztoring
Bardasz,
driven system were automated under the
SPE, Edwin David
Hernndez
Alejadre, and
human intervention. First, the particuadvanced,
providing
theArmando
ability Almeida
to useLen, Petrolink, premise that all should be as accurate
prepared
2013 SPE Digital
Energy
and Exhibition,
Woodlands, and important
as the data make possicomputer
power
to Conference
choose and
examine The More-Accurate
lar field-operations knowledge gained
byfor the
Alerts
Texas, USA, 57 March. The paper has not been peer reviewed.
ble. Hence, algorithms were developed

RTOC monitoring engineers is very valu- an increasing volume of more-complex Traditionally, alerts have been prepared
able but fragile, because it requires the data. This has enabled discovery of pre- by monitoring engineers at RTOCs. HowFor a limited time, the complete paper is free to SPE members at www.spe.org/jpt.
continued participation of team mem- viously undetected drilling patterns ever, most of them were triggered by enCopyright 2013, Society of Petroleum Engineers. Reprinted from the Journal of Petroleum Technology with permission.
bers. To ensure that nothing is over- from correlation wells and known po- gineers data visualization or alarms disJPT SEPTEMBER 2013
looked, that knowledge should be gath- tential events from ongoing drilling played by the real-time systems. This is
ered and used by an intelligent system. programs, making real-time data expo- inefficient, because it demands significant time from monitoring engineers to
validate the accuracy of the alarm before
This article, written by JPT Technology Editor Chris Carpenter, contains highlights
an alert is posted.
of paper SPE 163709, Design of an Automated Drilling-Prediction System
Therefore, alarms in the computerStrengthening-While-Drilling Decision Making, by Samuel R. Prez Bardasz, driven system were automated under the
SPE, Edwin David Hernndez Alejadre, and Armando Almeida Len, Petrolink, premise that all should be as accurate
prepared for the 2013 SPE Digital Energy Conference and Exhibition, The Woodlands, and important as the data make possiTexas, USA, 57 March. The paper has not been peer reviewed.
ble. Hence, algorithms were developed

147

For a limited time, the complete paper is free to SPE members at www.spe.org/jpt.
Copyright 2013, Society of Petroleum Engineers. Reprinted from the Journal of Petroleum Technology with permission.
JPT SEPTEMBER 2013

147

specifically to assess a limited set of

the most recent data points for temporal trends, and to compare them with
those expected on the basis of the drilling program and correlation wells from
the WITSML database. This reduces the
number of false alarm emissions coming from data-point outliers that sometimes are part of a log curve or from a
data-transmission failure (such as noise).
Algorithms have been intentionally designed to avoid system alarms being triggered if the transmission system is missing family data at a certain time or depth
interval, if one value is outside of the program range, or if a block of received data
is outside of the range at a depth or time
where it is expected to be that way.
Alarms are triggered taking into account two data sources (real-time stream
and historic database). Thus, alerts represent warnings derived not only from
surface potential issues or imminent
downhole threats being identified in real
time, but also from potential wellbore issues identified through correlation wells
or as predefined in the drilling program.
Because this process requires data
to be compared by a unique computer
application, the drilling-data standard
WITSML was put in place, as well as a system of measurements for downhole and
surface parametersthe set of units that
operators use. Similarly, new features related to the fluids data displayed were developed for the pre-existing application.
All drilling-program data must be available in a standardized format to be uploaded to the system.
More-accurate automated alarms
maximize the decision value of the alerts
that are finally prepared by the monitoring engineers.

Anticipating Events
and Trouble Zones

The design of an automated drillingprediction system was started by covering drill-bit performance, fluid changes,
and varying rock formations. These three
points have data in the form of a program
as well as in real time.
Drilling performance has a direct
relation to drill-bit efficiency. Therefore,
drill-bit information is used to monitor the well, taking into account start/
end depth; casing-stage diameter; initial/final weight on bit; minimum/maxi-

148

mum revolutions per minute; minimum/

maximum rate of penetration (ROP);
and minimum/maximum pump pressure, flow rate, torque, type, diameter,
and total flow area. These parameters
are filtered, related into a database, and
displayed on a console. If a real-time
value is outside of the range defined by
the program, the system will send audible and visible alarms. This is complemented and supported by a depthbased plot on which real-time data of
ROP, resistivity, and gamma ray are
visibly compared.
This information is complemented with downhole-drilling-equipment
features if available, either from a
conventional-motor or a rotary-steerable
system. The data taken into account are
maximum tool temperature, hours of
motor life, and motor brand and model.
An indicator of formation temperature
vs. motor temperature completes the information immediately available to the
monitoring engineer before an alert
isposted.
Drilling-fluids aspects taken into
account include program values for
density, plastic viscosity, yield point,
salinity, water/oil fraction, filtration,
emulsion stability, equivalent circulating density, loss, and gasification. All
program values are uploaded to the system, where specific algorithms are applied to compare them with real-time and
near-real-time fluid data. This results in
a display that quickly shows which parameter requires attention; each has a
traffic-lightindication.
Rock-formation and lithologycolumn information can be compared
using the real-time data stream and static
data stored in the system. Data available
from correlation wells and from the drilling program are matched with loggingwhile-drilling data and near-real-time
lithology data, if available. The era, formation, and lithology description are related to measured depth below the rotary
table, to true vertical depth below mean
sea level, and to measured depth and
measured bed thicknesses. Once these
static data are related with the real-time
data, a traffic light is displayed on the
console, indicating at least whether, for
a specific measured depth, the rock era,
formation, and lithology match those in
the program.

This console is complemented with

a depth-based well-correlation panel
that provides gamma-ray, resistivity, and
lithology-column information that enhances the decision-making process to
trigger an alert.
Adding a degree of importance to
each one of the described-in-detail information tracks, it is possible to define a general-parameter status by use
of complex algorithms, resulting in a
traffic-light expression. Each data family is used as a macro or rule that specifies how a certain input sequence should
be mapped to a replacement input sequence, and how much impact it should
have on the general well status. It is
important to mention that other family data such as trajectory or cementing
data can be taken into account for the
anticipation of drilling issues and fast,
accurate alertgeneration.
Thereafter, two other well-status
screens enter the process: one that takes
into account the set of events such as
kicks, total loss, and friction and torque
issues that occurred on the correlation wells; and one that takes into account the current well-operation status.
These provide easy-to-read key information to the monitoring engineer, who is
now able to focus more on data-trend
analysis than on data validation and
data-trend identification. It is important to mention that the automated status can be edited manually by the monitoring engineers if the status shown
is not what the operator or the rigsite
staff confirms.

General RTOC Dashboard

Ironically, RTOC status reports are not

commonly available in real time. Instead, this task is performed from time
to time, depending on the operator companys interests, because it demands full
attention of monitoring engineers for
significant periods of time. All real-time
plots must be reviewed by the monitoring engineers around a specific time,
looking for deviation from the plan as
trends change for the wells being monitored at the RTOC. Combining the three
main statuses of all wells monitored at
the RTOC into a unique automated dashboard makes the status-report update
an efficient task requiring almost no
humanintervention.JPT

JPT SEPTEMBER 2013