Scientific Reports,
Journal Year:
2024,
Volume and Issue:
14(1)
Published: Nov. 21, 2024
This
research
aimed
to
increase
the
natural
frequencies
of
a
non-rotating
2D
tri-axial
braided
composite
(2DTBC)
fan
blade.
The
investigation
utilized
multidisciplinary
approach,
integrating
Artificial
Neural
Network
(ANN)
modeling,
analytical
method,
Finite
Element
(FE)
analysis,
optimization
techniques,
and
experimental
validation.
ANN
captured
complex
relationship
between
braiding
machine
structure
parameters.
mechanical
properties
2DTBC
were
determined
through
micromechanical
thin-shell
analysis
was
applied
describe
blade's
displacement
strain
characteristics.
Micromechanical
modeling
examines
material
behavior
at
microscopic
level,
thin
shell
focuses
on
analyzing
thin,
curved
structures
using
simplified
equations.
FE
method
facilitated
formulation
equation
motion
calculation
frequencies.
A
genetic
algorithm,
focused
single-objective
optimization,
employed
refine
parameters
number
layers,
thereby
enhancing
optimized
blade
subsequently
fabricated
validated
impact
hammer
modal
testing,
showing
strong
agreement
with
predictions
from
combined
ANN-analytical-FEM-GA
model.
led
significant
in
Scientific Reports,
Journal Year:
2024,
Volume and Issue:
14(1)
Published: Oct. 11, 2024
Different
forms
of
close-packed
yarns
can
be
produced
by
varying
the
number
monofilaments
in
core
region,
ranging
from
one
to
five.
Numerous
efforts
have
been
made
model
or
simulate
mechanical
response
yarns;
however,
previous
studies
predominantly
focused
on
two
core.
In
this
study,
we
propose
an
analytical
approach
that
combines
a
geometrical
with
artificial
neural
network
(ANN)
predict
tensile
behavior
containing
2
5
region.
The
novelty
hybrid
lies
not
only
accounting
for
more
than
but
also
extending
prediction
range
elastic
viscoelastic-plastic
behavior.
Validation
proposed
method
showed
excellent
agreement
between
experimental
and
theoretical
results.
Numerical
simulations
further
confirmed
results
align
predictions,
demonstrating
model's
accuracy
predicting
yarns.
This
modeling
has
potential
significantly
improve
understanding
textile
structures.
