Nondestructive Testing And Evaluation,
Journal Year:
2024,
Volume and Issue:
unknown, P. 1 - 24
Published: Feb. 5, 2024
The
dynamic
compressive
strength
(DCS)
of
frozen-thawed
rock
influences
the
stability
mass
in
cold
regions,
especially
when
masses
are
possibly
disturbed
by
loads.
Laboratory
freeze-thaw
weathering
treatment
is
usually
time-consuming,
and
test
destructive.
Therefore,
this
paper
attempts
to
quickly
predict
DCS
sandstones
using
data-driven
methods,
non-destructive
properties,
basic
environmental
parameters.
sparrow
search
algorithm
(SSA),
gorilla
troops
optimiser,
dung
beetle
optimiser
were
chosen
develop
two
hyperparameters
random
forest
(RF).
classic
RF,
back
propagation
neural
network,
support
vector
regression
models
taken
as
control
group.
These
six
developed
DCS.
Their
prediction
results
compared.
Finally,
sensitivity
analysis
was
carried
out
assess
significance
all
input
variables.
indicate
that
SSA
–
RF
model
yields
best
result,
three
optimised
have
better
performance
than
single
machine-learning
models.
Strain
rate,
dry
density,
wave
velocity
found
be
most
important
parameters
prediction,
which
further
indicates
there
also
a
strong
correlation
between
characteristic
impedance
Materials,
Journal Year:
2023,
Volume and Issue:
16(10), P. 3731 - 3731
Published: May 15, 2023
The
accurate
estimation
of
rock
strength
is
an
essential
task
in
almost
all
rock-based
projects,
such
as
tunnelling
and
excavation.
Numerous
efforts
to
create
indirect
techniques
for
calculating
unconfined
compressive
(UCS)
have
been
attempted.
This
often
due
the
complexity
collecting
completing
abovementioned
lab
tests.
study
applied
two
advanced
machine
learning
techniques,
including
extreme
gradient
boosting
trees
random
forest,
predicting
UCS
based
on
non-destructive
tests
petrographic
studies.
Before
applying
these
models,
a
feature
selection
was
conducted
using
Pearson's
Chi-Square
test.
technique
selected
following
inputs
development
tree
(XGBT)
forest
(RF)
models:
dry
density
ultrasonic
velocity
tests,
mica,
quartz,
plagioclase
results.
In
addition
XGBT
RF
some
empirical
equations
single
decision
(DTs)
were
developed
predict
values.
results
this
showed
that
model
outperforms
prediction
terms
both
system
accuracy
error.
linear
correlation
0.994,
its
mean
absolute
error
0.113.
addition,
outperformed
DTs
equations.
models
also
KNN
(R
=
0.708),
ANN
0.625),
SVM
0.816)
models.
findings
imply
can
be
employed
efficiently
Nondestructive Testing And Evaluation,
Journal Year:
2024,
Volume and Issue:
unknown, P. 1 - 24
Published: Feb. 5, 2024
The
dynamic
compressive
strength
(DCS)
of
frozen-thawed
rock
influences
the
stability
mass
in
cold
regions,
especially
when
masses
are
possibly
disturbed
by
loads.
Laboratory
freeze-thaw
weathering
treatment
is
usually
time-consuming,
and
test
destructive.
Therefore,
this
paper
attempts
to
quickly
predict
DCS
sandstones
using
data-driven
methods,
non-destructive
properties,
basic
environmental
parameters.
sparrow
search
algorithm
(SSA),
gorilla
troops
optimiser,
dung
beetle
optimiser
were
chosen
develop
two
hyperparameters
random
forest
(RF).
classic
RF,
back
propagation
neural
network,
support
vector
regression
models
taken
as
control
group.
These
six
developed
DCS.
Their
prediction
results
compared.
Finally,
sensitivity
analysis
was
carried
out
assess
significance
all
input
variables.
indicate
that
SSA
–
RF
model
yields
best
result,
three
optimised
have
better
performance
than
single
machine-learning
models.
Strain
rate,
dry
density,
wave
velocity
found
be
most
important
parameters
prediction,
which
further
indicates
there
also
a
strong
correlation
between
characteristic
impedance
