AI in Civil Engineering,
Год журнала:
2024,
Номер
3(1)
Опубликована: Ноя. 14, 2024
Abstract
This
study
is
primarily
aimed
at
creating
three
machine
learning
models:
artificial
neural
network
(ANN),
random
forest
(RF),
and
k-nearest
neighbour
(KNN),
so
as
to
predict
the
crippling
load
(CL)
of
I-shaped
steel
columns.
Five
input
parameters,
namely
length
column
(
L
),
width
flange
b
f
thickness
t
web
w
)
height
H
are
used
compute
(CL).
A
range
performance
indicators,
including
coefficient
determination
R
2
variance
account
factor
(VAF),
a-10
index,
root
mean
square
error
(RMSE),
absolute
(MAE)
deviation
(MAD),
assess
effectiveness
established
models.
The
results
show
that
all
ML
(machine
learning)
models
can
accurately
load,
but
ANN
superior:
it
delivers
highest
value
=
0.998
lowest
RMSE
0.008
in
training
phase,
well
0.996
smaller
0.012
testing
phase.
Additional
methods,
rank
analysis,
reliability
regression
plot,
Taylor
diagram
matrix
employed
models’
performance.
index
β
calculated
by
using
first-order
second
moment
(FOSM)
technique,
result
compared
with
actual
value.
Additionally,
sensitivity
analysis
performed
check
impact
variables
on
output
(CL),
finding
has
greatest
followed
,
order.
demonstrates
techniques
useful
for
developing
a
reliable
numerical
tool
measuring
It
found
proposed
also
be
other
kinds
failures
different
perforated
Metals,
Год журнала:
2025,
Номер
15(4), С. 408 - 408
Опубликована: Апрель 4, 2025
In
steel
structural
engineering,
artificial
intelligence
(AI)
and
machine
learning
(ML)
are
improving
accuracy,
efficiency,
automation.
This
review
explores
AI-driven
approaches,
emphasizing
how
AI
models
improve
predictive
capabilities,
optimize
performance,
reduce
computational
costs
compared
to
traditional
methods.
Inverse
Machine
Learning
(IML)
is
a
major
focus
since
it
helps
engineers
minimize
reliance
on
iterative
trial-and-error
by
allowing
them
identify
ideal
material
properties
geometric
configurations
depending
predefined
performance
targets.
Unlike
conventional
ML
that
mostly
forward
predictions,
IML
data-driven
design
generation,
enabling
more
adaptive
engineering
solutions.
Furthermore,
underlined
Explainable
Artificial
Intelligence
(XAI),
which
enhances
model
transparency,
interpretability,
trust
of
AI.
The
paper
categorizes
applications
in
construction
based
their
impact
automation,
health
monitoring,
failure
prediction
evaluation
throughout
research
from
1990
2025.
challenges
such
as
data
limitations,
generalization,
reliability,
the
need
for
physics-informed
while
examining
AI’s
role
bridging
real-world
applications.
By
integrating
into
this
work
supports
adoption
ML,
IML,
XAI
analysis
design,
paving
way
reliable
interpretable
practices.
Scientific Reports,
Год журнала:
2025,
Номер
15(1)
Опубликована: Апрель 26, 2025
Abstract
Three
push-out
specimens
were
experimentally
tested
to
investigate
the
behavior
of
tubular
steel
columns
(TSC)
with
and
without
bolted
shear
connectors
embedded
in
normal
concrete
(NC).
Each
specimen
consisted
a
column
encased
250
×
200
mm
cube
The
embedment/the
prominent
height
TSC
was
100
mm.
Foam
used
underneath
form
free
space.
study
considered
variables
such
as
presence
demountable
studs
reinforcement.
failure
modes,
load-slip
response,
peak
load/slip,
stiffness
analyzed.
Furthermore,
finite
element
model
(FEM)
developed
using
ABAQUS
software
simulate
validated
against
experimental
results.
FEM
also
employed
conduct
further
parametric
investigations.
results
indicate
that
significantly
improve
capacity,
exhibiting
217%
higher
load
than
those
studs.
Reinforcing
block
had
negligible
effect
on
but
increased
slip
by
37.7%
18.7%
compared
unreinforced
specimen.
increasing
thickness
enhances
load,
154.31%
increase
observed
increases
from
one-third
bolt
diameter
full
diameter.
Additionally,
thicknesses
greater
half
helps
prevent
bearing
failure.
Increasing
compressive
strength
25
50
MPa
leads
24.6%
while
capacity
decreases
19.77%.
For
applications
requiring
high
ductility,
excessively
high-strength
should
be
avoided,
it
reduces
capacity.
demonstrate
not
exceed
twice
web
AI in Civil Engineering,
Год журнала:
2024,
Номер
3(1)
Опубликована: Ноя. 14, 2024
Abstract
This
study
is
primarily
aimed
at
creating
three
machine
learning
models:
artificial
neural
network
(ANN),
random
forest
(RF),
and
k-nearest
neighbour
(KNN),
so
as
to
predict
the
crippling
load
(CL)
of
I-shaped
steel
columns.
Five
input
parameters,
namely
length
column
(
L
),
width
flange
b
f
thickness
t
web
w
)
height
H
are
used
compute
(CL).
A
range
performance
indicators,
including
coefficient
determination
R
2
variance
account
factor
(VAF),
a-10
index,
root
mean
square
error
(RMSE),
absolute
(MAE)
deviation
(MAD),
assess
effectiveness
established
models.
The
results
show
that
all
ML
(machine
learning)
models
can
accurately
load,
but
ANN
superior:
it
delivers
highest
value
=
0.998
lowest
RMSE
0.008
in
training
phase,
well
0.996
smaller
0.012
testing
phase.
Additional
methods,
rank
analysis,
reliability
regression
plot,
Taylor
diagram
matrix
employed
models’
performance.
index
β
calculated
by
using
first-order
second
moment
(FOSM)
technique,
result
compared
with
actual
value.
Additionally,
sensitivity
analysis
performed
check
impact
variables
on
output
(CL),
finding
has
greatest
followed
,
order.
demonstrates
techniques
useful
for
developing
a
reliable
numerical
tool
measuring
It
found
proposed
also
be
other
kinds
failures
different
perforated
