in this article, produced by The Image Factory on behalf of Genesis RTS, The University of Texas-Austin, Apache, and Chesapeake, focuses on how the Sentinel Real-Time tool helps drilling contractors and producers ensure fidelity of data stemming from all rig sensors – from the drill string, mud pumps and everything in between.

1. Plugthevalueleak:Fixyourdrillingdata
SPECIAL FOCUS: ADVANCES IN DRILLING
World Oil®
/ OCTOBER 2015 35
Today, drilling data are marred by a lack
of quality assurance, with potential costly
consequences for analytics and real-time
decisions made from faulty data. A new
system allows operators to boost efficiency
through the validation of real-time or historical
data, unlocking significant reductions in both
non-productive time and invisible lost time.
ŝŝ PRADEEPKUMARASHOK,SentinelRealTime;ADRIANAMBRUS
andERICVANOORT,TheUniversityofTexasatAustin;NATHANZENERO,
ChesapeakeEnergy;andMICHAELBEHOUNEK,ApacheCorp.
Why do drilling automation systems, real-time operating sys-
tems, and drilling analysis and design systems fail so often, or
deliver less value than expected, when analogies from other in-
dustries show that these approaches have significant, clear and
present value? The first and foremost answer is surprisingly sim-
ple—alldrillingsystemsrelyondatathataredemonstrablybad.If
we could supply our tools with the necessary and sufficient qual-
ity data, our controls, analytics and engineering would be much
more trustworthy, both in the office and in the field.
Withthecombinationofharshenvironments,complexwellge-
ometries and shrinking economic margins (especially in the U.S.
landmarket),agrowingimportanceisnowbeingplacedontheac-
curacy of data delivered from pressure, pit level, hookload, torque,
flowrate, and other equally indispensable, yet largely antiquated,
rig sensors. Another equally important, but perhaps not as well
understood opportunity is the “Big Data” movement taking root
in the industry. As we attempt to apply new, complex analytical
methods,werealizethatdataqualityisnowmuchmoreimportant.
Whereasmostconclusionscould,previously,bereachedstochasti-
cally, or through less sophisticated methods, complex drilling ana-
lyticsmustbephysicallyconsistent.Thus,itisimportanttocleanse
the data a priori, and in real time, when possible and practical.
Many E&P companies have begun to take a critical look at
this aspect of their operation; however, they have focused largely
on sensor capability and new sensor technology. What is largely
missing is a method to detect sensor faults and failures in real
time, and the ability to estimate the correct value of a measure-
ment when an error occurs in their existing sensor networks.
This article discusses an oil field-specific application of a proven
analytical technology, used in ultra-critical U.S. Office of Naval
Research systems.
The collaborative initiative takes the form of the next-gener-
ation Sentinel Real-Time (RT) system, which leverages a Bayes-
ian probabilistic network model. This provides operators with an
Recent studies suggest that many rig sensors are delivering
inaccurate data. Image: Apache Corp.
Originally appeared in World Oil
®
OCTOBER 2015 issue, pS 35-42. Posted with permission.

2. 36 OCTOBER 2015 / WorldOil.com
ADVANCES IN DRILLING
unobtrusivemethodologythathigh-gradesreal-timedatastreams,
andidentifiesexistingandimpendingsensorand/orprocessfaults.
Thus, the elevated confidence in the fidelity of real-time data sets
facilitatessounddecisionsthatfostersafer,morecost-effectivewell
delivery, with reduced instances of non-productive time (NPT)
and invisible lost time (ILT). The latter two items, together, have
been shown to account for up to 50% of total drilling time.
Specifically, the powerful data analytics engine links all sur-
face and subsurface sensors into a holistic, self-auditing network,
wherein each sensor checks off the others to determine if they are
malfunctioning, Fig. 1. Once a defect is exposed, before any infe-
rior data are fed into the real-time event detection and data ana-
lyticssoftware,itcanbereplacedwithproperlycalibrated,predic-
tive values, based on the model that links all the sensors together.
Along with the obvious, and very important, safety and
environmental safeguards (think pressure, flow and pit vol-
ume sensors used for maintaining well control), the capacity
to isolate a sensor fault makes the system ideally suited for
condition-based monitoring and maintenance. By providing
uninterrupted oversight of rig activities, be it for the rig in its
entirety or individual components, the technology provides
early alerts for equipment deficiencies, allowing ample time
for intervention before the failure of a key component and the
resulting NPT.
Moreover, due to its intrinsic redundancy and, subsequently,
higher confidence in data integrity, the patent-pending system is
well-positioned as an enabling technology for drilling automa-
tion. With the technology functioning as a virtual guard dog, it
prevents the potentially catastrophic inclusion of inferior data in
critical control algorithms.
BAD DATA EPIDEMIC
The industry’s grappling with data volumes that have reached
epic proportions has become the subject du jour these days.1
However, comparatively less focus has been placed on validating
the quality of the data sets being mined. When it comes to well
construction, which continues to rely mostly on rig sensors intro-
duced decades ago, the time-worn truism “garbage-in, garbage-
out” is particularly relevant, leaving operators little choice but to
cross their fingers and hope for the best.
Unfortunately,relyingonbest-guessscenarioscanleadtoreal-
time decisions that are based on bad data, thereby amplifying the
risks of disastrous safety and economic implications. Further, the
importance of high-integrity data has become even more magni-
fied by the increasing number of centralized operating centers
established to remotely monitor offshore and, more recently, on-
shore drilling operations.
The recent acceleration in adoption of advanced surface and
downhole sensors was intended to enhance safety and reduce
NPT, but along with higher sampling rates that make human
Fig. 1. A holistic Bayesian network of rig sensors integrates all data to identify sensor faults, defective equipment or process dysfunctions.
þ þ þ
þ þ þ
þ
þ
þ
þ
þ
þ
þ
þ
þ
þ
þ
þ
þþþ
þ
þ
þ
þ
þ
þ
þ
þ
þ
þ
þ
þ
þ
þ
þ
þ
þ
þ
þ
þ
þ
þ þ þ
þ
þ
þþþþ
þ
þþ þ
þ
þ
þ
RT 01S hole
depth previous
RT 01S bit
depth previous
RT 01S bit
depth
RT 01S block
height
RT 01S hole
depth
Calc drill
collar length
Calc string
weight
Calc bit
pressure drop
Calc friction
drill collar 2
Calc friction
HWDP
Calc friction
drill pipe
Calc friction
pressure drop
Calc friction
drill collar 1
RT 01S block
height previous
RT 01S hook
load
MR drill collar
1 unit weight
MR drill collar
2 unit weight
MR HWDP unit
weight
MR drill pipe
unit weight
MR plastic
viscosityMR NMDC 1
length
MR HWDP
length
MR drill collar
2 ID MR drill collar
1 ID
MR drill collar
2 OD
MR drill collar
1 OD
MR yield
point
MR drill
pipe ID
MR drill
pipe ODMR bit sizeMR HWDP IDMR HWDP OD
MR block
weight
RT 01S strokes
per minute 1
RT 01S pump 1
total strokes previous
RT 01S pump 2
total strokes previous
RT 01S strokes
per minute 2
RT 01S pump 2
total strokes
RT 01S pump 1
total strokes
RT 01S total
mud volume
RT 01S standpipe
pressure
RT 01S differential
pressure
RT 01S total
pump output
RT 01S
flowrate out RT 01S
surface RPM
RT 01S
surface torque
RT 01S weight
on bit
MR mud weight
MR nozzle total
flow area
MR drill collar
1 length
MR BHA
length
RT 01S total mud
volume previous
MR pump 1
liner
MR pump 1
stroke MR pump 2
stroke
MR pump 1
efficiency
MR pump 2
efficiency
MR pump 2
liner
Fig. 2. After a spike in flow out (blue line) during drilling activity
indicates a faulty flow out sensor, close approximation of the
true flow out value (green line) can be derived from the Bayesian
network.
Flagged as sensor fault–flow out sensor
2014-03-09T08:57:16Z
Sensed flow out, %
Model-derived flow out, %
Flow out trustworthiness
Total mud volume, bbl
Pump rate, gpm
0.00
300
0.00
0
0
27
27
53
53
80
80
0.33
367
470
0.00
433.00
0.00
1.00
500
1,400
2014-03-09T09:05:12Z 2014-03-09T09:13:08Z

3. 38 OCTOBER 2015 / WorldOil.com
ADVANCES IN DRILLING
real-time monitoring enormously difficult, a contagion of sub-
standard data continues to stream unabated through rig analyti-
cal software. Recent studies by Chesapeake Energy suggest that
upwards of 50% of the rig sensors in service are delivering inac-
curate data, with sensor reading variances of up to 50%, high or
low, compared to a correct, calibrated reading.
As a case-in-point, the inherent value of a technology capable
of instantly recognizing improperly calibrated data and replacing
itwiththecorrectfigureswasreinforcedbyanindependentoper-
ator’s collection of data from eight primary surface sensors, on six
rigs, in its onshore drilling fleet. What it found was average errors,
from bad calibration, of up to 60% in the case of makeup torque,
with only the RPM sensors shown to be consistently within the
proper calibration specifications, Table 1.
MODEL CONSTRUCT
The concept of developing a seamless methodology, with in-
trinsic relational redundancies to validate drilling sensor data,
was germinated within the Drilling and Rig Automation Group
of the University of Texas at Austin’s (UT Austin) Department
of Petroleum and Geosystems Engineering.2 The original version
of the holistic data validation technology was developed and ma-
turedthroughfundingbytheU.S.OfficeofNavalResearch,which
sought technology to verify the accuracy of sensor data in critical
electro-mechanical actuator systems, in submarines and ships.3
With UT researchers exploring technology transfer opportunities
in the civil, mechanical, and aerospace engineering disciplines, it
was recognized quickly that the validation software used effective-
ly in the defense sector had direct implications for improving the
safetyandeconomicperformanceofoilandgasdrillingoperations.
What resulted was a behind-the-scenes model that integrates
all rig sensor data with built-in variables capable of instantly
identifying sensor and/or process faults, as well as malfunction-
ing equipment. Since all the sensors are joined in an integrated
network, the cross-checking mechanism ensures all are in proper
working order. Specifically, the now-transferred technology is
built around a Bayesian network model of sensed parameters to
facilitate easier and complete enumeration of all the relational re-
dundancies inherent in a particular system.
Processed from commonly used WITS, Modbus, and
WITSML data transmission standards, all the information
collected is closely related with the built-in redundancies de-
tecting any anomalies, either with the individual sensor or
with the top drive, mud pump, mud motor or other rig com-
ponent. Once intertwined as a seamless network, all of the
sensors are logically linked together, thus the transmission of
independent, or unrelated, measurements would suggest one
or more of the sensors are either not relaying the proper data,
or something is amiss in the process.
For instance, if mud is flowing in at a certain rate, it also
should flow out at the same rate (assuming no kick or lost cir-
culation scenario), with any deviation from that norm likely in-
dicating a faulty flow out sensor, Fig. 2. Once the fault is identi-
fied, the Bayesian network derives a very close approximation
of what the actual flowrate should be. In that same way, the
network model would pick up process faults, such as kicks, lost
circulation and other drilling dysfunctions, and would be able
to alert the user accordingly.
Consider, for instance, the case of a process fault, such as an
unexpected tensile load, as indicated by the hookload sensor,
which degrades the process confidence level to zero. In this par-
ticular case, the software would raise an alarm of a potential over-
pull condition, representative of a pipe sticking event, rather than
a defective sensor, Fig. 3.
Mostimportantly,withthesteadilyincreasingdevelopmentof
control algorithms to advance automated drilling, tripping, and
managed pressure drilling (MPD), which key off the assimilated
data, the value of knowing if a sensed data can be trusted, cannot
be understated.4 Here, trustworthiness carries enormous weight,
considering the repercussions should automated decisions be
based on inferior data being included in the control algorithm.
As such, the new validation software continually re-processes
the data and checks whether they are trustworthy, or should be
discarded before the data can be engineered into an automated
closed-loop control routine.
Furthermore, the system’s modularity makes it extremely flex-
ible in accommodating the wide variances in number and type of
sensors used from rig to rig. The model architecture is such that it
can be easily scalable to meet individual requirements and objec-
tives,eitherforuseononlythetopdrive,fluidcirculationorother
subsystems, or a single network that encompasses all of the rig’s
surface and subsurface sensors.
While the robust system enhances the value derived from
simple surface sensors without the addition of sophisticated
downhole telemetry data, it is easily updated to include logging-
while-drilling (LWD), measurement-while-drilling (MWD) and
other downhole measurement tools.
RIG NPT MINIMIZATION
Breakdowns on the rig involving key pieces of equipment not
only can jeopardize well integrity, but also, as Fereday5 and others
have noted, represent one of the primary causes of NPT. Typi-
Table 1. Average error due to bad calibration.
Sensor Rig A Rig B Rig C Rig D Rig E Rig F
Rotary torque, % 17 17 22 24 21 18
Makeup torque, % 23 11 12 17 60 13
Rotary RPM, % 1 1 1 1 2 1
Pump rate, % 1 32 1 1 40 1
Block position, in. 6 <0.5 <0.5 72 <0.5 <0.5
Hookload, % 11 n/a 18 n/a 12 n/a
Pit volumes, % 15 12 18 16 15 22
Pump pressure, % 5 4 4 4 3 5
Source: Chesapeake Energy
Fig. 3. Judging from the actual reading shown by the hookload
sensor (blue line), the model detects a potential over-pull
situation and does not confuse this as a faulty sensor reading.
2014-03-09T
13:10:49Z
2014-03-09T
13:12:05Z
2014-03-09T
13:13:21Z
2014-03-09T
13:14:37Z
2014-03-09T
13:15:53Z
Actual hook load, klb
Model derived hook load, klb
Block height, ft
0
0
50
50
100
100
150
150
Flagged as process fault–overpull
0
16.70
33.30
50
66.70
83.30
100

4. 40 OCTOBER 2015 / WorldOil.com
ADVANCES IN DRILLING
cally, operators and contractors are at the
mercy of planned maintenance schedules
thatarebasedonthe equipment’s specified
operationallifeexpectancy,workloads,and
targeted operating environment. However,
failure risks are compounded appreciably,
when maintenance is performed in accor-
dance with parameters that may be inac-
curate or unrealistic, given ever-changing
drilling conditions, unforeseen events or
revised well objectives.
However, the continual oversight of
sensor output throughout the actual drill-
ing process delivers a proactive, condition-
based response that goes beyond data quality by flagging rig or
equipment deficiencies well before catastrophic failure occurs.
Furthermore,theadvancedalgorithmswrittenintothevalidation
model consider all the possible data generated by the system to
computationally triangulate how much useful life remains in a
particular piece of equipment. Ultimately, these decisions elimi-
nate failure-related NPT, or at least minimize the duration of
downtime for equipment repair or replacement.
Since the faults identified in different rig components also
generate different belief patterns, the holistic unification of all the
sensors enables immediate isolation of the problem area, which
would be very difficult, if not impossible, if only a single sensor
was considered, Fig. 4. Again, in the case of a flow line sensor, the
network would determine, in real time, if a fault was in the sensor,
the mud pump or the flow line (i.e. leakage). Consider also that if
the calculated real-time efficiency of the mud pump was shown
to be deviating from its nominal value, the identified efficiency
decline would strongly suggest deterioration, giving personnel
plenty of lead time to make fact-based decisions, on when to take
the mud pump off-line for repair or replacement.
DRILLING EFFICIENCY AND OPTIMIZATION
More advanced sensor arrays, employed nowadays in the
more critical drilling applications, deliver multiple sensor sam-
pling rates that are extremely difficult, if not impossible, to hu-
manly digest for real-time decisions. Therefore, at a time when
low commodity prices make operators especially keen on any
improvement that can help maximize asset value, opportunities
to optimize drilling efficiency can be overlooked. Until now, re-
al-time decisions to improve efficiency fell mostly on the most
experienced driller and the individual intimately familiar with a
particular rig and drilling theater.
Hand in hand with condition-based monitoring, the data-
validation algorithms pick up deviations that can directly im-
pair optimal efficiency, be it with the mud motor, bit and other
BHA components, or else with a drilling (process) dysfunction,
such as a sensed increase in axial, lateral or torsional vibrations.
By tracking and analyzing RPM, torque, weight-on-bit, differen-
tial pressure, and rate of penetration data, the holistic analytics
engine can isolate, for example, if the mud motor is defective,
or if there is a process fault, such as a dull bit. Through con-
tinual updating of industry-standard, Mechanical Specific En-
ergy (MSE) calculations used for performance evaluations,
the software provides objective assessments for real-time
efficiency improvements.
Along with optimizing real-time drilling efficiency, the soft-
ware also provides beneficial insight to aid in field development.
Generating reports for individual wells, the analytical software
processes historical drilling data, which are improved further
by identifying, engaging, terminating, and ultimately, replacing
faulty data with cleansed values derived from the model, Fig. 5.
Hence,operatorscanusethefinalreporttooptimizepost-drilling
performance analysis, amplify data quality for analytical purpos-
es, and enhance future well planning. Specifically, such reports
also provide indication of sensors that need to be scheduled for
re-calibration, or even require replacement.
Currently, the software is in play analyzing operator data sets,
cataloging bad data, and furthering the business case for improv-
ing data quality for increased drilling efficiency and safety.
REFERENCES
1. Eaton, C., “Oil patch works to harness a gusher of ‘Big Data,’” Houston Chronicle, May 10, 2015.
2. Ambrus, A., P. Ashok, and E. van Oort, “Drilling rig sensor data validation in the presence of real-
time process variations,” SPE paper 166387-MS, presented at the SPE Annual Technical Confer-
ence and Exhibition, New Orleans, La., Sept. 30-Oct. 2, 2013.
3. Krishnamoorthy, G., P. Ashok, and D. Tesar, “Simultaneous sensor and process fault detection and
isolation in multiple-input-multiple-output systems,” Systems Journal, IEEE, vol.9, no.2, pp. 335,
349, June 2015.
4. Ambrus, A., P. Pournazari, P. Ashok, R. Shor, and E. van Oort, “Overcoming barriers to adoption of
drilling automation: Moving towards automated well manufacturing,” SPE-IADC paper 173164-
MS, presented at the SPE/IADC Drilling Conference and Exhibition, London, UK, March 17-19,
2015.
5. Fereday, K.,BP, “Downhole drilling problems: Drilling mysteries revealed!,” presented at American
Association of Professional Landmen (AAPL) Annual Meeting, San Francisco, June 13-16, 2012.
Fig. 4. Since different faults produce different belief patterns, the data analytics engine
goes beyond data quality to isolate specific equipment and/or process deformities.
0.0
0.2
0.4
0.6
0.8
1.0
Flow sensor failure belief pattern
0.0
0.2
0.4
0.6
0.8
1.0
Mud pump failure belief pattern
0.0
0.2
0.4
0.6
0.8
1.0
Flow line failure belief pattern
Fig. 5. An example of data being cleansed by the software to
enable further processing.
8,000
8/2/2015
12:00:00 am
8/5/2015
12:00:00 am
Time
Cleansed data
Hole depth, ft
8/8/2015
12:00:00 am
6,500
4,970
3,460
1,940
430
8,000
8/2/2015
12:00:00 am
8/5/2015
12:00:00 am
Actual data
Cleansed data
Bad data
8/8/2015
12:00:00 am
6,500
4,970
3,460
1,940
430

5. World Oil®
/ OCTOBER 2015 41
PRADEEPKUMAR ASHOK is a principal in Sentinel Real
Time, LLC, a Houston-based company whose purpose is
to develop drilling data-related technologies for oil and
gas operators, and drilling contractors. He also is a
research scientist in the Rig Automation and
Performance Improvement in Drilling (RAPID) group at
the University of Texas at Austin. There, he leans on his
research experience in the robotics industry to focus on improving data
quality in the upstream petroleum space, for the purpose of advancing
drilling automation throughout the well delivery lifecycle. Dr. Ashok
received his PhD in mechanical engineering from the University of Texas
at Austin.
ADRIAN AMBRUS is a graduate research assistant in the
RAPID group at the University of Texas at Austin. After
earning BS and MS degrees in mechanical engineering
from Drexel University, he joined the University of Texas
at Austin in 2012, to pursue a PhD in mechanical
engineering. His research focus is on drilling rig sensor
data validation, event detection and design of control
algorithms for various drilling automation tasks. Mr. Ambrus is
responsible for developing the core data validation engine for Sentinel
RT.
ERIC VAN OORT is an expert in drilling and production,
who serves as a professor in the Department of
Petroleum and Geosystems Engineering at the University
of Texas at Austin. He also serves as chairman of the
board for Houston-based GenesisRTS, a real-time
systems company that empowers operators with
fit-for-purpose drilling optimization expertise, processes
and tools. He previously served 20 years at Shell, where
he was responsible for the implementation of new technology, fit-for-
purpose rig development for well manufacturing, frac spread
optimization, water management, rig automation and remote operations.
He holds four U.S. patents and five international patents on drilling
techniques and associated best practices, drilling fluids and wellbore
stability, among others. Dr. van Oort holds a PhD in chemical physics
from the University of Amsterdam.
NATHAN ZENERO is a LEAN, Six-Sigma certified drilling
engineer at Chesapeake Energy. He is co-founder of the
Operators Group on Drilling Data Quality, the SPE-
DSATS Data Quality Assurance (DQA) subcommittee
and the IADC QA/QC committee. He specializes in
applied technology, advanced analytics, real-time drilling
solutions and drilling automation systems. He has
developed innovative tools in the areas of iron roughneck calibration,
BOP testing and rig information management. He received his bachelor’s
degree from Texas A&M University.
MICHAEL BEHOUNEK is a senior drilling advisor with
Apache Corp. in Houston, working in World Wide
Drilling, supporting global operations and engineering,
and pursuing technology advancement that can be
leveraged to drive improvement and increase value to
Apache. His 33 years of expertise lie in drilling
engineering, operations, performance improvement, and
contracting in over 25 countries. Recent technology developments
include three years in drilling automation, and he now leads efforts to
improve performance leveraging data, including data quality, integration,
transformation, analytics-visual, advanced and predictive. Mr. Behounek
is a degreed mechanical engineer with a master’s degree in business.
Article copyright © 2015 by Gulf Publishing Company. All rights reserved. Printed in U.S.A.
Not to be distributed in electronic or printed form, or posted on a website, without express written permission of copyright holder.