Fractal and Fractional,
Год журнала:
2024,
Номер
8(12), С. 677 - 677
Опубликована: Ноя. 21, 2024
The
degree
of
rock
mass
discontinuity
is
crucial
for
evaluating
surrounding
quality,
yet
its
accurate
and
rapid
measurement
at
construction
sites
remains
challenging.
This
study
utilizes
fractal
dimension
to
characterize
the
geometric
characteristics
develops
a
data-driven
classification
(SRC)
model
integrating
machine
learning
algorithms.
Initially,
box-counting
method
was
introduced
calculate
from
excavation
face
image.
Subsequently,
parameters
affecting
quality
were
analyzed
selected,
including
strength,
discontinuity,
condition,
in-situ
stress
groundwater
orientation.
compiled
database
containing
246
railway
highway
tunnel
cases
based
on
these
parameters.
Then,
four
SRC
models
constructed,
Bayesian
optimization
(BO)
with
support
vector
(SVM),
random
forest
(RF),
adaptive
boosting
(AdaBoost),
gradient
decision
tree
(GBDT)
Evaluation
indicators,
5-fold
cross-validation,
precision,
recall,
F1-score,
micro-F1-score,
macro-F1-score,
accuracy,
receiver
operating
characteristic
curve,
demonstrated
GBDT-BO
model’s
superior
robustness
in
generalization
compared
other
models.
Furthermore,
additional
validated
intelligent
approach’s
practicality.
Finally,
synthetic
minority
over-sampling
technique
employed
balance
training
set.
Subsequent
retraining
evaluation
confirmed
that
imbalanced
dataset
does
not
adversely
affect
performance.
proposed
shows
promise
predicting
guiding
dynamic
support.
Sustainability,
Год журнала:
2025,
Номер
17(5), С. 2287 - 2287
Опубликована: Март 6, 2025
As
an
efficient
clean
backup
energy
source,
natural
gas
hydrates
have
received
high
attention
from
countries
around
the
world,
and
it
is
very
important
to
establish
models
predict
total
amount
of
regional
resources.
In
response
complexity
existing
shortcomings
current
methods
in
resource
exploration
prediction,
this
article
used
volume
method
evaluation
as
basis
for
predictions.
The
location
information
obtained
14
wells
research
area
were
data,
k-Nearest
Neighbor
interpolation
(KNN
interpolation)
was
estimate
effective
area.
Through
Kolmogorov–Smirnov
test
(KS
test),
we
found
that
parameters
hydrate
resources
roughly
follow
a
Poisson
distribution
with
coordinates.
After
using
three-dimensional
configuration,
able
characterize
overall
pattern
quantity
each
well
quantity.
Finally,
Monte
Carlo
algorithm
genetic
based
on
maximum
possible
within
entire
region.
discussion,
discussed
reasons
occurrence
negative
saturation
verified
accuracy
algorithms
analyzed
applicability
model
different
environments.
Petroleum Science and Technology,
Год журнала:
2025,
Номер
unknown, С. 1 - 27
Опубликована: Март 24, 2025
This
study
successfully
developed
a
novel
water-based
completion
fluid
with
enhanced
properties.
The
system,
incorporating
nano
clay
(1.0%–3.0%)
along
additives
like
polyanionic
cellulose,
pre-gelatinized
starch,
polyethylene
glycol
200,
sodium
formate,
and
chloride,
was
compared
to
conventional
hydroxyethyl
cellulose-based
fluid.
Viscosity
filtration
properties
were
analyzed
using
viscometer
filter
press.
core
flooding
test
Berea
sandstone
at
an
overburden
pressure
of
1000
psi
conducted
understand
the
formation
damage
potential
optimized
system.
zeta
analysis
indicated
better
PAC-based
colloidal
system
stability
(−22.2
mV)
HEC-based
(−4.7
mV).
HPHT
90
°C
500
demonstrated
lower
loss
(9
ml),
highlighting
clay's
effectiveness
in
control.
higher
surface
area
volume
ratio
&
its
capability
fit
between
other
particles,
obstructing
flow
through
them,
assist
return
permeability
value
97.3%
for
tests
on
revealed
good
control
property
Moreover,
it
also
observed
that
enhances
geomechanical
rock
samples,
indicating
borehole
