Journal of Elastomers & Plastics,
Год журнала:
2024,
Номер
unknown
Опубликована: Дек. 6, 2024
This
paper
reports
on
a
data
driven
machine
learning
(ML)
approach
to
analyze
and
predict
the
erosion
behavior
of
titanium
oxide
(titania)
filled
ramie-epoxy
composites.
ML
models
are
extensively
used
in
recent
years
mimic
human
decisions
various
industries.
After
fabrication
well-designed
trials
following
design
experiments,
experimental
is
critically
analyzed
examine
effect
each
input
factor
(erodent
temperature,
striking
angle,
velocity
filler
content)
output
that
wear
rate.
It
found
rate
increases
with
increase
angle
decreases
content.
The
further
feed
five
different
models.
performance
adequacy
compared
using
metrics.
noticed
although
all
techniques
effectively
predicted
rate,
Gradient
boosting
(GBM)
model
exhibited
superior
an
R
2
value
0.9486.
feature
importance
plot
confirms
the,
content,
played
major
role
predicting
hybrid
Chemistry Technology and Application of Substances,
Год журнала:
2024,
Номер
7(1), С. 221 - 229
Опубликована: Июнь 1, 2024
The
physical
and
mechanical
properties
of
epoxy
composites
filled
with
copper-plated
polyamide
granules
were
investigated.
Physico-mechanical
evaluated
based
on
the
results
tensile
impact
toughness
studies.
It
is
shown
that
obtained
have
high
strength
properties,
which
are
preserved
at
level
unfilled
matrix.
was
established
presence
a
copper
shell
surface
has
little
effect
change
in
composites.
An
attempt
made
to
explain
using
values
adhesive
layer
formed
between
matrix
filler,
different
nature.
Materials and Manufacturing Processes,
Год журнала:
2024,
Номер
39(15), С. 2166 - 2182
Опубликована: Авг. 29, 2024
To
improve
the
abrasive
waterjet
drilling
procedure
for
yttrium-stabilized
zirconia-coated
Inconel
718
superalloy,
this
study
suggests
an
integrated
approach
using
machine
learning
and
evolutionary
algorithm.
The
objective
is
to
simultaneously
minimize
erosion
diameter
taper
angle
of
drilled
holes
by
identifying
best
combination
parameters
such
as
stand-off
distance,
flow
rate,
pressure,
impact.
models
are
developed
random
forest
algorithm
after
tuning
its
hyperparameters
predict
angle.
multi-verse
optimization
(MVO)
used
identify
parameters.
comparison
results
proved
efficacy
MVO
over
other
algorithms.
Confirmation
experiment
also
in
line
with
MVO,
since
percentage
deviation
meager.
This
integrative
has
capability
significantly
improving
aerospace
industrial
operations.
Proceedings of the Institution of Mechanical Engineers Part E Journal of Process Mechanical Engineering,
Год журнала:
2024,
Номер
unknown
Опубликована: Окт. 7, 2024
The
current
research
investigates
the
effect
of
boron
carbide
(B
4
C)
reinforcement
on
mechanical
and
sliding
wear
behaviour
Al-Fe-Si
(AA8011)
composites,
fabricated
using
an
ultrasonic-assisted
stir-casting
technique
with
varying
B
C
weight
fractions
from
0%
to
10%.
Microstructural
analysis,
including
SEM
EDS,
confirmed
presence
reinforcement,
improved
particle
dispersion,
grain
refinement.
study
found
that
density
AA8011–B
composites
decreases
while
porosity
increases
higher
content.
Notably,
AA8011-6
wt.%B
composite
exhibited
a
significant
improvement
in
properties,
yield
strength,
tensile
hardness
rising
by
91%,
55%,
38%,
respectively,
compared
unreinforced
alloy.
optimisation
test
parameters
wt.%
Taguchi-grey
relational
analysis
variance,
revealed
lower
coefficient
friction
were
achieved
at
load
30
N,
disc
velocity
5
m/s,
distance
1000
m.
95.67%
grey
grade
within
95%
predicted
confidence
interval.
Journal of Elastomers & Plastics,
Год журнала:
2024,
Номер
unknown
Опубликована: Дек. 6, 2024
This
paper
reports
on
a
data
driven
machine
learning
(ML)
approach
to
analyze
and
predict
the
erosion
behavior
of
titanium
oxide
(titania)
filled
ramie-epoxy
composites.
ML
models
are
extensively
used
in
recent
years
mimic
human
decisions
various
industries.
After
fabrication
well-designed
trials
following
design
experiments,
experimental
is
critically
analyzed
examine
effect
each
input
factor
(erodent
temperature,
striking
angle,
velocity
filler
content)
output
that
wear
rate.
It
found
rate
increases
with
increase
angle
decreases
content.
The
further
feed
five
different
models.
performance
adequacy
compared
using
metrics.
noticed
although
all
techniques
effectively
predicted
rate,
Gradient
boosting
(GBM)
model
exhibited
superior
an
R
2
value
0.9486.
feature
importance
plot
confirms
the,
content,
played
major
role
predicting
hybrid
