Measurement Science and Technology,
Journal Year:
2024,
Volume and Issue:
36(2), P. 026007 - 026007
Published: Dec. 23, 2024
Abstract
Tunnel
cracks
pose
a
significant
threat
to
structural
integrity,
potentially
leading
localized
collapse
of
the
infrastructure.
Traditional
manual
crack
detection
methods
are
prohibitively
expensive,
highlighting
need
for
an
efficient
and
accurate
automatic
segmentation
model.
To
address
this
challenge,
we
propose
novel
model
subway
tunnel
lining
surface
based
on
DeepLabV3+
architecture.
In
model,
design
improved
Swin
transformer
V2
Base
(SwinV2*)
as
backbone
enhance
performance.
Considering
tubular
morphology
cracks,
introduce
snake
convolution
module
better
capture
their
unique
features.
prevent
performance
degradation
when
fusing
shallow
deep
features,
incorporate
spatial
feature
calibration
that
facilitates
alignment
grouping
along
channel
dimension.
We
assess
our
model’s
effectiveness
using
thousands
images
captured
by
image
acquisition
system
designed
surfaces.
Experimental
results
show
achieves
strong
metrics:
68.96%
IoU,
84.33%
mIoU,
87.57%
PA.
Compared
original
DeepLabV3+,
approach
demonstrates
superior
performance,
with
2.89%
improvement
in
1.45%
increase
mIoU
notably,
10.39%
Journal of Rock Mechanics and Geotechnical Engineering,
Journal Year:
2024,
Volume and Issue:
unknown
Published: July 1, 2024
Understanding
the
rheology
of
bentonite
suspensions
is
crucial
for
ensuring
safety
engineering
practices.
However,
rheological
mechanisms
remain
unclear
due
to
limitations
conventional
experimental
techniques,
particularly
in
assessing
microscopic
interactions
between
clay
particles
and
their
impact
on
properties.
In
this
paper,
behaviors
Na-montmorillonite
were
studied
with
a
focus
interparticle
interactions.
Both
equilibrium
molecular
dynamics
(MD)
non-equilibrium
MD
simulations
conducted
understand
physical
properties
under
zero
shear
various
rates,
respectively.
The
interaction
two
parallel
was
determined
simulations,
indicating
that
classical
Darjaguin-Landau-Verwey-Overbeek
(DLVO)
theory
underestimates
small
separation
distance.
exhibits
typical
thinning
behavior
shearing.
as
water
content
increases,
it
begins
behave
more
like
liquid
water.
yield
stress
montmorillonite,
by
Bingham
model,
found
be
linearly
related
pressures
particles.
Besides
microstructure
suspension
further
quantified
using
distance
incline
angle
non-parallel
Based
results
structure,
model
developed
estimate
montmorillonite
considering
influence
factors,
including
electrolyte
concentration,
temperature,
solid
fraction.
Finally,
from
comparison
calculated
data,
confirm
good
performance
proposed
model.
These
findings
provide
significant
insights
understanding
soil
evaluating
suspensions.
