Energy Science & Engineering,
Journal Year:
2024,
Volume and Issue:
12(6), P. 2643 - 2660
Published: May 27, 2024
Abstract
In
carbonate
reservoirs
characterized
by
the
fracture‐cavity
system
as
storage
spaces,
drilling
process
is
highly
prone
to
loss
of
fluid.
This
not
only
affects
efficiency
but
can
also
lead
severe
accidents,
such
blowouts.
Therefore,
it
crucial
understand
distribution
pattern
these
fractures.
However,
formation
rock
systems,
being
controlled
various
factors,
difficult
precisely
identify.
limitation
hampers
efficient
development
types
oil
and
gas
fields.
paper
presents
a
case
study
M5
5
sub‐section
reservoir
in
Sulige
gasfield,
proposing
an
improved
You
Only
Look
Once
v5s
(YOLOv5s)
deep
learning
algorithm.
It
utilizes
enhanced
training
with
conventional
logging
data
identify
response
characteristics
fractures
reservoirs.
And
its
identification
results
have
been
confirmed
be
accurate
fracture
obtained
through
different
means,
core
samples,
cast
thin
section
photographs,
imaging
data,
seismic
attributes.
method
incorporates
Ghost
convolution
module
replace
Conv
backbone
network
YOLOv5s
model,
modifies
C3
into
Bottleneck
module,
effectively
making
model
more
lightweight.
Additionally,
Convolutional
Block
Attention
Module
integrated
Neck
network,
enhancing
model's
feature
extraction
capabilities.
Finally,
employs
Efficient
Intersection
over
Union
Loss
function
instead
Complete
Loss,
reducing
network's
regression
loss.
The
validation
using
actual
demonstrate
that
this
achieves
average
recognition
accuracy
87.3%
for
system,
which
3%
improvement
baseline
(YOLOv5s).
enhancement
beneficial
locating
fluid
positions
Processes,
Journal Year:
2023,
Volume and Issue:
11(10), P. 2823 - 2823
Published: Sept. 25, 2023
In
order
to
quantitatively
characterize
shale
pores
and
microfractures,
twelve
marine
samples
from
the
Longmaxi
Formation
in
southeastern
Sichuan
Basin
were
selected
their
NMR
T2
spectra
analyzed
under
conditions
of
full
brine
saturation,
cyclic
centrifugal
treatment
heat
treatment.
Then,
movable,
capillary
bound
unrecoverable
fluid
distinguished
porosity
full-scale
PSD
calculated.
Based
on
spectral
peak
identification,
relative
content
microfractures
was
determined
influence
factors
analyzed.
The
results
show
that
is
bimodal,
with
distributed
range
1
nm
200
5000
nm,
contents
ranges
3.44–6.79%
0.22–1.43%,
respectively.
Nanoscale
organic
are
dominant
type
pores,
while
inorganic
contribute
much
less
reservoir
space
than
pores.
cutoff
values
0.55
ms
6.73
ms,
surface
relaxivities
0.0032
µm/ms
0.0391
µm/ms.
Their
strong
correlation
TOC
suggests
matter
main
factor
controlling
pore
structure.
addition,
difference
between
He
gas
logging
used
detect
connected
also
includes
closed
microfractures.
Combined
high-temperature
pressure
displacement
experimental
facilities,
this
will
be
a
further
step
towards
studying
structure
simulated
formation
conditions.
Journal of Marine Science and Engineering,
Journal Year:
2023,
Volume and Issue:
11(11), P. 2162 - 2162
Published: Nov. 13, 2023
The
sequence
of
the
Khurmala
Formation
located
in
northeastern
Iraq
was
measured
and
sampled
to
evaluate
its
paleoenvironmental
features,
including
sedimentological
microfacies
analyses.
studied
formation
analyzed
under
an
optical
microscope
dominated
by
three
main
types
microfacies:
coralligenous–algal
wackestone,
foraminiferal–peloidal
packstone,
grainstone.
These
hosted
rarely
contain
a
non-geniculate
algae
that
insufficient
for
complete
reef-building
as
crest,
but
among
common
algae,
there
are
calcareous
geniculate
green
associated
with
benthic
foraminifera
minor
component
planktonic
basin
due
high-energetic
open
shallow-water
environmental
conditions
during
deposition
Formation.
relative
percentages
foraminifera,
both
planktonic,
plotted
on
triangular
diagrams
revealed
graphic
indicator
paleoenvironment
Detailed
examination
analyses
microfacies,
new
findings
(Acicularia
Clypeina),
based
triangle
method
standard
facies
zones,
denote
upper
part
richer
fined
grain
Acicularia
reflecting
lower
energy
than
formation,
which
represented
algal
wackestone
Clypeina
algae.
In
summary,
these
fluctuations
facies/microfacies
changes,
appearance
different
foraminiferal
content
linked
global
sea
level
fluctuation
occurred
Paleocene–Eocene
interval.
Energy Science & Engineering,
Journal Year:
2024,
Volume and Issue:
12(6), P. 2643 - 2660
Published: May 27, 2024
Abstract
In
carbonate
reservoirs
characterized
by
the
fracture‐cavity
system
as
storage
spaces,
drilling
process
is
highly
prone
to
loss
of
fluid.
This
not
only
affects
efficiency
but
can
also
lead
severe
accidents,
such
blowouts.
Therefore,
it
crucial
understand
distribution
pattern
these
fractures.
However,
formation
rock
systems,
being
controlled
various
factors,
difficult
precisely
identify.
limitation
hampers
efficient
development
types
oil
and
gas
fields.
paper
presents
a
case
study
M5
5
sub‐section
reservoir
in
Sulige
gasfield,
proposing
an
improved
You
Only
Look
Once
v5s
(YOLOv5s)
deep
learning
algorithm.
It
utilizes
enhanced
training
with
conventional
logging
data
identify
response
characteristics
fractures
reservoirs.
And
its
identification
results
have
been
confirmed
be
accurate
fracture
obtained
through
different
means,
core
samples,
cast
thin
section
photographs,
imaging
data,
seismic
attributes.
method
incorporates
Ghost
convolution
module
replace
Conv
backbone
network
YOLOv5s
model,
modifies
C3
into
Bottleneck
module,
effectively
making
model
more
lightweight.
Additionally,
Convolutional
Block
Attention
Module
integrated
Neck
network,
enhancing
model's
feature
extraction
capabilities.
Finally,
employs
Efficient
Intersection
over
Union
Loss
function
instead
Complete
Loss,
reducing
network's
regression
loss.
The
validation
using
actual
demonstrate
that
this
achieves
average
recognition
accuracy
87.3%
for
system,
which
3%
improvement
baseline
(YOLOv5s).
enhancement
beneficial
locating
fluid
positions
