IMPROVING FRACKING POWER & EFFICIENCY
Top: This fl owchart illustrates the steps
for optimizing a frac operation using
Shell’s integrated platform .
Bottom: A recommendation “card”
displays the suggested change along
with contextual information to assist
engineers in real-time decision making .
Additional details about the system
are available in SPE 209127, “Effi ciency
and Effectiveness – A Fine Balance: An
Integrated System to Improve Deci-
sions in Real-Time Hydraulic Fracturing
Operations.” in the form of a “card” that can be dis-
played on the user interface. This card
includes the suggested change, as well as
contextual information to assist engineers
in decision making, such as average pres-
sure, predicted pressure and estimated
savings. While he did not provide exact
figures, Dr Mondal said the estimated sav-
ings is typically in the thousands of dollars
per recommendation.
The platform restricts the frequency of
recommendations given within a particu-
lar time frame, both to ensure engineers
have time to implement the recommenda-
tions already given and to see the response
to any optimization action taken before a
new one is generated.
Dr Mondal stressed that the model is
purely a recommendation tool. Engineers
at the frac site must decide whether to
implement the optimization action. “The
idea here is not to replace the human. It’s
to provide the human making the decision
with the tools they need and the data they
need to make the best decision without
having to rely solely on experience or
recall at a given moment,” he said.
System limitations
While specific results from initial field
testing were not discussed, Dr Mondal said
the software has consistently identified
optimization opportunities and augment-
ed decision making that led to cost sav-
ings while preserving frac effectiveness.
However, there are limitations. Frequently,
the team saw scenarios during testing
where the pressure became negatively
correlated to the proppant or showed non-
linear dynamics due to wellbore complexi-
S tep 1
Identify potential
operating states
S tep 5
S tep 2
Generate Estimate
optimization pressure response
S tep 4
S tep 3
Calculate Select
cost/time impact
valid states
ty. Since the pressure response model used
in testing was a linear model, the system’s
ability to predict effectively became lim-
ited under those scenarios. When the team
increased the prediction time frame from
1 minute to 3 minutes during these sce-
narios, the model became insufficient at
modeling the complexities of the system.
To help remedy this issue, the team
explored the possibility of incorporating a
gradient boosting, or “learning tree,” model
into the pressure response. In a gradi-
ent boosting model, a base model trains
additional models sequentially to try to
reduce error. This model leverages histori-
cal data and contextual data, such as stage
depth. Shell structured the model to input
all variables available at a given time and
contextual information about the well and
stage, such as the depth or formation type.
This model showed impressive predic-
tive power, Dr Mondal said, as it was able
to predict the pressure response up to 3
minutes ahead of an event with reasonable
accuracy. However, like with the linear
model, this model struggled to accurately
predict an event in the early ramp phase of
the frac stage because there was too much
variability. Shell is currently investigating how to
integrate a gradient boosting model into
the software platform, which is a challeng-
ing task because a large gradient boosting
model requires hosting a sizeable number
of parameters associated with it. A host
would also need to be developed that can
cover all possible well types, which is an
exhaustive process.
“This model is computationally very
heavy,” Dr Mondal said. “You have to keep
an evergreen training set, which is very
time consuming, and this set needs to con-
stantly update the model. We are trying
to keep a balance between the practical
implementation challenges and having
optimal model accuracy.” DC
D R I L L I N G C O N T R AC T O R • M A R C H/A P R I L 202 2
39