Mechanical Behavior Prediction of 3D‐Printed PLA/Wood Composites Using Artificial Neural Network and Fuzzy Logic
Polymers for Advanced Technologies,
Год журнала:
2025,
Номер
36(2)
Опубликована: Фев. 1, 2025
ABSTRACT
This
study
presents
a
novel
approach
to
optimize
and
predict
the
mechanical
properties
of
3D‐printed
polylactic
acid
(PLA)/wood
composites
through
artificial
neural
network
(ANN)
fuzzy
logic
(FL)
modeling.
The
research
addresses
critical
challenge
determining
optimal
process
parameters
in
fused
deposition
modeling
(FDM)
natural
fiber
composites.
Using
Taguchi's
L27
orthogonal
array,
experiments
were
conducted
with
five
key
printing
parameters:
layer
thickness
(100–200–300
μm),
speed
(PS)
(40–60–90
mm/s),
raster
angle
(RA)
(0°–45°–90°),
infill
density
(ID)
(30%–60%–90%),
nozzle
temperature
(NT)
(190°C–200°C–210°C).
Analysis
revealed
that
RA
PS
most
influential
parameters,
contributing
41.86%
40.92%
tensile
compressive
strengths,
respectively.
developed
ANN
model
demonstrated
exceptional
prediction
accuracy
R
2
values
99.94%
for
both
surpassing
FL
model's
performance
(
=
97.16%).
development
these
models
is
crucial
accurately
predicting
behavior,
allowing
efficient
optimization
without
extensive
physical
testing.
Both
methods
high
accuracy.
Validation
tests
maximum
errors
1.95%
2.81%
FL,
findings
contribute
valuable
insights
high‐performance
establish
foundation
future
advanced
manufacturing
processes.
Язык: Английский
A framework for data-driven decision making in advanced manufacturing systems: Development and implementation
Concurrent Engineering,
Год журнала:
2024,
Номер
32(1-4), С. 58 - 77
Опубликована: Ноя. 5, 2024
Integration
of
sophisticated
technologies
such
as
Internet
Things,
cyber
physical
systems
and
big
data
analytics
have
revolutionized
the
advanced
manufacturing
(AMS).
However,
implementation
data-driven
decision
making
in
AMS
still
remains
challenging
due
to
heterogeneity,
real-time
processing
demands,
integration
complexities.
This
paper
overcomes
this
challenge
by
presenting
a
novel
framework
for
adoption
DDDM
enhance
its
decision-making
capabilities.
consists
six
stages:
stage,
sensing
knowledge
application
stage.
The
proposed
leverages
extract
actionable
insights
from
diverse
datasets,
integrates
CPS
create
seamless
interaction
between
digital
systems,
employs
IoT
acquisition
monitoring.
is
validated
through
comprehensive
case
study
involving
CNC
milling
machine
dataset,
demonstrating
significant
improvements
operational
efficiency,
accuracy,
response
time.
involves
detailed
collection
steps,
preprocessing,
analysis,
showcasing
framework’s
practical
effectiveness.
results
show
that
addresses
existing
challenges
provides
scalable
solution
AMS.
Язык: Английский