REVIEWS ON ADVANCED MATERIALS SCIENCE,
Journal Year:
2024,
Volume and Issue:
63(1)
Published: Jan. 1, 2024
Abstract
This
research
integrated
glass
powder
(GP),
marble
(MP),
and
silica
fume
(SF)
into
rubberized
mortar
to
evaluate
their
effectiveness
in
enhancing
compressive
strength
(
fc′
{f}_{\text{c}}^{^{\prime}
}
).
Rubberized
cubes
were
produced
by
replacing
fine
aggregates
with
shredded
rubber
varying
proportions.
The
decrease
mortar’s
was
controlled
substituting
cement
GP,
MP,
SF.
Although
many
literature
studies
have
evaluated
the
suitability
of
industrial
waste,
such
as
SF,
construction
material,
no
yet
included
combined
effect
these
wastes
on
mortar.
study
aims
provide
complete
insight
waste
By
cement,
SF
added
different
proportions
from
5
25%.
Furthermore,
artificial
intelligence
prediction
models
developed
using
experimental
data
assess
determined
that
optimal
substitution
levels
for
15,
10,
15%,
respectively.
Similarly,
partial
dependence
plot
analysis
suggests
GP
a
comparable
machine
learning
demonstrated
significant
resemblance
test
results.
Two
individual
techniques,
support
vector
random
forest,
generate
R
2
values
0.943
0.983,
Scientific Reports,
Journal Year:
2025,
Volume and Issue:
15(1)
Published: Feb. 10, 2025
The
increasing
demand
for
sustainable
construction
materials
has
led
to
the
incorporation
of
Palm
Oil
Fuel
Ash
(POFA)
into
concrete
reduce
cement
consumption
and
lower
CO₂
emissions.
However,
predicting
compressive
strength
(CS)
POFA-based
remains
challenging
due
variability
input
factors.
This
study
addresses
this
issue
by
applying
advanced
machine
learning
models
forecast
CS
POFA-incorporated
concrete.
A
dataset
407
samples
was
collected,
including
six
parameters:
content,
POFA
dosage,
water-to-binder
ratio,
aggregate
superplasticizer
curing
age.
divided
70%
training
30%
testing.
evaluated
include
Hybrid
XGB-LGBM,
ANN,
Bagging,
LSSVM,
GEP,
XGB
LGBM.
performance
these
assessed
using
key
metrics,
coefficient
determination
(R2),
root
mean
square
error
(RMSE),
normalized
means
(NRMSE),
absolute
(MAE)
Willmott
index
(d).
XGB-LGBM
model
achieved
maximum
R2
0.976
lowest
RMSE,
demonstrating
superior
accuracy,
followed
ANN
with
an
0.968.
SHAP
analysis
further
validated
identifying
most
impactful
factors,
ratio
emerging
as
influential.
These
predictive
offer
industry
a
reliable
framework
evaluating
concrete,
reducing
need
extensive
experimental
testing,
promoting
development
more
eco-friendly,
cost-effective
building
materials.
