MATEC Web of Conferences,
Год журнала:
2024,
Номер
398, С. 01034 - 01034
Опубликована: Янв. 1, 2024
Numerous
studies
have
delved
into
anticipating
the
loadcarrying
capacity
(LC)
of
fiber-reinforced
polymer
(FRP)-confined
concrete-filled
steel
tubes
(CFST)
compression
members
(SFC)
using
limited
and
noisy
data.
However,
none
undertaken
a
comparative
assessment
accuracy
among
various
modeling
techniques
based
on
an
extensive
refined
database.
This
study
aims
to
introduce
analytical
model
for
forecasting
LC
SFC
members.
The
is
developed
utilizing
database
comprising
712
samples,
considering
mechanism
confinement
both
FRP
wraps.
By
incorporating
lateral
columns,
yields
precise
predictions.
As
per
experimental
database,
demonstrates
statistics
such
as
MAE
=
427,
MAPE
283,
R2
0.815,
RMSE
275,
a20-index
0.73,
indicating
its
effectiveness
in
providing
accurate
Scientific Reports,
Год журнала:
2024,
Номер
14(1)
Опубликована: Авг. 12, 2024
This
article
investigates
the
behavior
of
hybrid
FRP
Concrete-Steel
columns
with
an
elliptical
cross
section.
The
investigation
was
carried
out
by
gathering
information
through
literature
and
conducting
a
parametric
study,
which
resulted
in
116
data
points.
Moreover,
multiple
machine
learning
predictive
models
were
developed
to
accurately
estimate
confined
ultimate
strain
load
concrete
at
rupture
tube.
Decision
Tree
(DT),
Random
Forest
(RF),
Adaptive
Boosting
(ADAB),
Categorical
(CATB),
eXtreme
Gradient
(XGB)
techniques
utilized
for
proposed
models.
Finally,
these
visually
quantitatively
verified
evaluated.
It
concluded
that
CATB
XGB
are
standout
models,
offering
high
accuracy
strong
generalization
capabilities.
model
is
slightly
superior
due
its
consistently
lower
error
rates
during
testing,
indicating
it
best
this
dataset
when
considering
both
robustness
against
overfitting.
Structural Concrete,
Год журнала:
2025,
Номер
unknown
Опубликована: Март 4, 2025
Abstract
This
study
comprehensively
examined
the
behavior
and
performance
of
concrete‐filled
double‐skin
steel
elliptical
tubular
columns
(CFDSSETC)
subjected
to
different
loading
scenarios.
CFDSSETC
are
gaining
attention
due
their
potential
offer
enhanced
structural
efficiency
architectural
versatility
compared
traditional
columns.
research
uses
non‐linear
finite
element
analysis
machine
learning
(ML)
assess
load‐carrying
capacity
under
axial
eccentric
compression.
To
do
this,
ABAQUS
software
data
from
previous
were
used
generate
models
(FEMs)
for
eight
By
expanding
existing
parameters,
172
more
FEMs
developed
in
addition
these
8.
Parameters
such
as
ratio;
area
concrete
portion;
outer
width,
depth,
inner
yield
strength
internal
tube;
external
standard
cylinder
systematically
varied
evaluate
influence
on
response
CFDSSETC.
Additionally,
nine
ML
predict
CFDSSETC's
load‐bearing
capability
compression
utilizing
database
that
was
acquired
FEM.
work
provided
a
design
technique
determining
short
The
outcomes
revealed
raising
concrete's
area,
strength,
tubes
well
reducing
tube's
depth
or
width
load
eccentricity
capacity.
support
vector
regressor
demonstrated
superior
predictive
among
diverse
set
regression
considered.
suggested
formula
has
shown
good
prediction
accuracy,
with
99%
confidence
experimental
FEM
findings.
findings
provide
valuable
insights
into
optimization
applications
civil
engineering
structures,
contributing
advancement
sustainable
resilient
infrastructure
systems.
Scientific Reports,
Год журнала:
2025,
Номер
15(1)
Опубликована: Апрель 15, 2025
The
current
study
investigates
the
application
of
artificial
intelligence
(AI)
techniques,
including
machine
learning
(ML)
and
deep
(DL),
in
predicting
ultimate
load-carrying
capacity
strain
ofboth
hollow
solid
hybrid
elliptical
fiber-reinforced
polymer
(FRP)-concrete-steel
double-skin
tubular
columns
(DSTCs)
under
axial
loading.
Implemented
AI
techniques
include
five
ML
models
-
Gene
Expression
Programming
(GEP),
Artificial
Neural
Network
(ANN),
Random
Forest
(RF),
Adaptive
Boosting
(ADB),
eXtreme
Gradient
(XGBoost)
one
DL
model
Deep
(DNN).Due
to
scarcity
experimental
data
on
DSTCs,
an
accurate
finite
element
(FE)
was
developed
provide
additional
numerical
insights.
reliability
proposed
nonlinear
FE
validated
against
existing
results.
then
employed
a
parametric
generate
112
points.The
examined
impact
concrete
strength,
cross-sectional
size
inner
steel
tube,
FRP
thickness
both
DSTCs.The
effectiveness
assessed
by
comparing
models'
predictions
with
results.Among
models,
XGBoost
RF
achieved
best
performance
training
testing
respect
determination
coefficient
(R2),
Root
Mean
Square
Error
(RMSE),
Absolute
(MAE)
values.
provided
insights
into
contributions
individual
features
using
SHapley
Additive
exPlanations
(SHAP)
approach.
results
from
SHAP,
based
prediction
model,
indicate
that
area
core
has
most
significant
effect
followed
unconfined
strength
total
multiplied
its
elastic
modulus.
Additionally,
user
interface
platform
streamline
practical
DSTCs.
Fatigue & Fracture of Engineering Materials & Structures,
Год журнала:
2025,
Номер
unknown
Опубликована: Апрель 22, 2025
ABSTRACT
This
study
experimentally
investigates
the
fatigue
behavior
of
FRP‐concrete
structures
under
marine‐induced
corrosion.
Three
seawater
corrosion
environments
were
simulated,
with
cyclic
load
ranges
3901.8
N,
6503.0
and
9104.2
N.
Three‐stage
degradation
three‐stage
growth
models
identified
by
bond
stiffness
residual
slip
accumulation,
respectively.
Fatigue
strength
decreased
exposure,
more
severe
prolonged
exposure.
For
example,
original‐salinity
dry‐wet
cycle
condition
a
range
number
joints
cured
for
0,
30,
60,
90
days
1,763,238,
1,383,336,
1,219,779,
1,073,708,
The
relationship
between
(
N
f
)
(Δ
F
was
fitted
linear
logarithmic
curve,
assessment
model
proposed.
predicted
values
showed
maximum
relative
error
7%,
confirming
model's
effectiveness
in
predicting
