DI G ITAL TR AN S FOR MATION
over two years. This will serve as a testing
ground for the viability of storing CO 2 in a
saline aquifer and will involve geophysical
studies of the drilling of injection wells in
the aquifer. Petrobras says it anticipates
receiving government approval to proceed
with the project later this year.
Because of projects like these, the regu-
latory environment in Brazil will be crit-
ical in helping Petrobras meet its CCS
goals, Mr Mendes said. He noted that an
expansion into industrial CCS represents
a departure from the traditional role of
the national oil company; as such, the
company’s statute, which is established
by the Brazilian government, does not
include a regulatory framework or busi-
ness model for CCS. The bulk of the CO 2
that Petrobras stored last year came from
the development of pre-salt fields, but the
CCS hub includes plans for the company to
find industrial partners to provide CO 2 for
storage. In 2022, Petrobras sponsored a bill
that would regulate economic activities
related to the permanent storage of carbon
dioxide. That bill is still under discussion
in the Brazilian Senate.
“Collaboration is essential to a sustain-
able energy transition,” Mr Mendes said.
“By working together, businesses, gov-
ernments and regulators can scale up
the actions that enable the low-carbon
energy ecosystem. Latin America is well
positioned with regards to these energy
projects. It’s a good location to develop
energy ecosystems.” DC
“Chevron support center,”
continued from page 26
The DSC’s performance pods, formed in
2019, combine engineering support with
data, digital tools and modeling software
to develop performance-enhancing work-
flows that target issues such as major
nonproductive time. Ms Baker pointed
to one example of a win for reduced
cycle times in unconventional wells in
the Permian Basin, when DSC analysis
of longer lateral drilling found a direct
correlation between friction factors while
tripping out of the hole with a bottomhole
assembly and the probability of getting
casing to bottom.
“Now our operations engineers are cre-
ating the models, watching our real-time
friction factors and communicating with
the rig sites when our wellbore is clean
enough that we know we will get casing
to bottom,” Ms Baker said. “This is just
one example of the type of fit-for-purpose
engineering support that we can provide
based on the challenges that we see in
each business unit.”
She cited another example of success in
the deepwater space, where the DSC has
been able to monitor high-temperature
wells to determine which parameters are
contributing the most to wellbore cooling
efforts, and then create alarms around
those parameters. This alerts opera-
tions engineers when those thresholds
approach. “Now they know what parameters they
can effectively change to mitigate the tem-
peratures,” Ms Baker said. “At the end of
the day, we’re looking at each business
unit and each asset class to develop solu-
tions that fit those needs.” DC
“Digital twin,”
continued from page 27
twin that can accurately incorporate the
complexities of riser motion.
such as strain and acceleration, to recon-
struct the motion of the riser, as well as
fatigue, over time.
The third prong involved using another
neural network, DeepONet, to map a sepa-
rate set of input parameters (inflow veloc-
ity, riser bending, stiffness and tension as
a function of water depth) against various
output parameters (strain and amplitude).
This network served as the predictive
mechanism within the digital twin, actu-
ally predicting the occurrence and ampli-
tude of VIVs in a given environment.
Taken together, the three-pronged
approach demonstrate how machine learn-
ing algorithms and deep learning neural
networks can infer riser dynamics from
disparate sources of data, Dr Triantafyllou
said. This enables the creation of a digital
Next steps
“This is especially beneficial in our
unconventional business units where rig
counts are high and operations are not
monitored by our real-time operators.”
Fit-for-purpose engineering
support The researchers are currently working
with the operator members of the con-
sortium to create demo digital twins of
marine risers from current E&P projects,
customizing the algorithms to fit each
operator’s specific needs.
“Every company involved here has a
different niche application that they want
the digital twin to address. You’ve got
companies that are more interested in the
artificial intelligence, and they want to
see if the algorithms are suitable for other
applications in addition to the marine ris-
ers,” Dr Triantafyllou said. “Another com-
pany is using instrumented risers, and
they want to use the digital twin to update
the predictive models that they’re using
for those sensors. The demonstration will
For more information, see SPE 32443, “Evolution
of a Wells Decision Support Center as a Hub
for Operational Excellence,” presented at the
2023 OTC on 1 May.
give every stakeholder an opportunity to
apply the digital twin the way they want.”
ABS, which has published several guides
and recommended practices on marine
riser systems, will provide classification
and technical services for the researchers
as they customize the design of each riser
in the digital twin. The goal is for each
operator to begin using the algorithms in
their workflows either by the end of this
year or early next year.
“The design and functionality of this
digital twin has changed by the year, so
we expect to see more changes as we talk
to the companies and incorporate their
designs into our system,” Dr Triantafyllou
said, explaining that ABS will provide
guidance to both the researchers and oper-
ators on how to certify certain methodolo-
gies that will be used to create the digital
twins. “By the time this is ready, we should
have something really powerful.” DC
D R I L L I N G C O N T R AC T O R • J U LY/AU G U ST 2023
29