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
Case Studies in Thermal Engineering,
Год журнала:
2024,
Номер
55, С. 104065 - 104065
Опубликована: Фев. 10, 2024
Pulsating
heat
pipe
(PHP)
is
an
implicit
technique
through
a
passive
two-stage
transfer
system.
This
paper
presents
the
experimentations
on
PHP
contrived
using
copper
with
different
inner
tube
diameters
of
1,
1.5,
2,
and
2.5
mm,
respectively.
The
accused
acetone
as
functional
liquid
filling
proportions
varying
from
50
to
90%
its
volume
increment
10%.
effects
proportion
diameter
thermal
performance
were
investigated.
evaporator
zone
electrically
heated
mica
heater
in
range
20–80
W,
condenser
area
kept
cool
by
water
circulation
method.
results
show
that
2
mm
performs
best
compared
other
diameters,
lower
rate
resistance
0.49
K/W.
Also,
enhanced
at
60%
for
all
diameters.
Further,
CFD
analysis
was
carried
out
ratios
constant
input
80
it
revealed
test
outcomes
line
results.
deviation
between
experimental
numerical
studies
Considering
optimized
parameters,
i.e.,
ratio,
work
extended
adding
SiO2
nanoparticles
base
fluid
1–5
%
mass
concentration.
showed
value
0.3
W/K
higher
coefficient
828.64
W/m2
°K
obtained
2%
concentration
SiO2.
proportional
rise
60
W
11.46,
17,
14,
4.15,
1.94%
3,
4,
5%
nanoparticles,
Hence,
operates
better
ratio
nanoparticles.
The
growing
demand
for
fiber-reinforced
polymer
(FRP)
in
industrial
applications
has
prompted
the
exploration
of
natural
fiber-based
composites
as
a
viable
alternative
to
synthetic
fibers.
Using
jute–rattan
composite
offers
potential
environmentally
sustainable
waste
material
decomposition
and
cost
reduction
compared
conventional
fiber
materials.
This
article
focuses
on
impact
different
machining
constraints
surface
roughness
delamination
during
drilling
process
FRP
composite.
Inspired
by
this
unexplored
research
area,
emphasizes
influence
various
Response
methodology
designs
experiment
using
drill
bit
material,
spindle
speed,
feed
rate
input
variables
measure
factors.
technique
order
preference
similarity
ideal
solution
method
is
used
optimize
parameters,
predicting
delamination,
two
machine
learning-based
models
named
random
forest
(RF)
support
vector
(SVM)
are
utilized.
To
evaluate
accuracy
predicted
values,
correlation
coefficient
(R2),
mean
absolute
percentage
error,
squared
error
were
used.
RF
performed
better
comparison
with
SVM,
higher
value
R2
both
testing
training
datasets,
which
0.997,
0.981,
0.985
roughness,
entry
exit
respectively.
Hence,
study
presents
an
innovative
through
learning
techniques.
Recent
studies
focus
on
enhancing
the
mechanical
features
of
natural
fiber
composites
to
replace
synthetic
fibers
that
are
highly
useful
in
building,
automotive,
and
packing
industries.
The
novelty
work
is
woven
areca
sheath
(ASF)
with
different
fraction
epoxy
has
been
fabricated
tested
for
its
tribological
responses
three-body
abrasion
wear
testing
machines
along
features.
impact
various
examined.
study
also
revolves
around
development
validation
a
machine
learning
predictive
model
using
random
forest
(RF)
algorithm,
aimed
at
forecasting
two
critical
performance
parameters:
specific
rate
(SWR)
coefficient
friction
(COF).
void
observed
vary
between
0.261
3.8%
as
incremented.
hardness
mat
rises
progressively
from
40.23
84.26
HRB.
A
fair
ascent
tensile
strength
modulus
observed.
Even
though
short
descent
flexural
seen
0
12
wt
%
composite
specimens,
they
incrementally
raised
finest
values
52.84
2860
MPa,
respectively,
pertinent
48
fiber-loaded
specimen.
progressive
rise
ILSS
perceptible.
behavior
specimens
reported.
worn
surface
morphology
studied
understand
interface
ASF
matrix.
RF
exhibited
outstanding
prowess,
evidenced
by
high
R-squared
coupled
low
mean-square
error
mean
absolute
metrics.
Rigorous
statistical
employing
paired
t
tests
confirmed
model's
suitability,
revealing
no
significant
disparities
predicted
actual
both
SWR
COF.
International Journal of Low-Carbon Technologies,
Год журнала:
2024,
Номер
19, С. 747 - 765
Опубликована: Янв. 1, 2024
Abstract
Nanotechnology
has
increased
electric
vehicle
(EV)
battery
production,
efficiency
and
use.
is
explored
in
this
car
illustration.
Nanoscale
materials
topologies
research
energy
density,
charge
time
cycle
life.
Nanotubes,
graphene
metal
oxides
improve
storage,
flow
charging/discharge.
Solid-state
lithium-air
high-energy
batteries
are
safer,
more
dense
stable
using
nanoscale
catalysts.
improves
parts.
Nanostructured
fluids
reduce
lithium
dendrite,
improving
batteries.
Nanocoating
electrodes
may
damage
extend
benefits
the
planet.
Nanomaterials
allow
parts
to
employ
ordinary,
safe
instead
of
rare,
harmful
ones.
promotes
recycling,
reducing
waste.
Change
does
not
influence
stable,
cost-effective
or
scalable
items.
Business
opportunities
for
nanotechnology-based
EV
need
research.
High-performance,
robust
environmentally
friendly
might
make
cars
popular
transportation
sustainable
with
development.
An
outline
nanotechnology
researchexamines
publication
patterns,
notable
articles,
collaborators
contributions.
This
issue
was
researched
extensively,
indicating
interest.
Research
focuses
on
anode
materials,
storage
performance.
A
landscape
assessment
demonstrates
nanotechnology’s
growth
future.
comprehensive
literature
review
examined
nanosensors
EVs.
Our
study
provides
a
solid
foundation
understanding
current
state
research,
identifying
major
trends
discovering
breakthroughs
sensors
by
carefully
reviewing,
characterizing
rating
important
papers.
Polymers,
Год журнала:
2024,
Номер
16(18), С. 2666 - 2666
Опубликована: Сен. 22, 2024
Wear
is
induced
when
two
surfaces
are
in
relative
motion.
The
wear
phenomenon
mostly
data-driven
and
affected
by
various
parameters
such
as
load,
sliding
velocity,
distance,
interface
temperature,
surface
roughness,
etc.
Hence,
it
difficult
to
predict
the
rate
of
interacting
from
fundamental
physics
principles.
machine
learning
(ML)
approach
has
not
only
made
possible
establish
relation
between
operating
but
also
helps
predicting
behavior
material
polymer
tribological
applications.
In
this
study,
an
attempt
apply
different
algorithms
experimental
data
for
prediction
specific
glass-filled
PTFE
(Polytetrafluoroethylene)
composite.
Orthogonal
array
L25
used
experimentation
evaluating
with
variations
applied
distance.
analysed
using
ML
linear
regression
(LR),
gradient
boosting
(GB),
random
forest
(RF).
R2
value
obtained
0.91,
0.97,
0.94
LR,
GB,
RF,
respectively.
GB
model
highest
among
models,
close
1.0,
indicating
almost
perfect
fit
on
data.
Pearson’s
correlation
analysis
reveals
that
load
distance
have
a
considerable
impact
compared
velocity.
