Advanced Energy and Sustainability Research,
Journal Year:
2024,
Volume and Issue:
unknown
Published: Dec. 1, 2024
Bottom
ash
(BA)
and
steel
slag
(SS)
wastes
are
generated
in
large
quantities
primarily
recycled
as
raw
materials
for
concrete.
However,
the
influx
of
expansive
components
can
cause
pop‐outs
concrete
reduce
mechanical
properties
concrete,
prompting
need
alternative
recycling
methods.
Herein,
a
new
method
BA
SS,
an
electrically
insulating
thermally
conductive
thermal
interface
material
(TIM)
is
proposed
by
incorporating
or
SS
filler
into
polymer.
CaO,
which
has
historically
been
obstacle
to
efficient
found
improve
conductivity
TIMs.
The
resulting
TIMs
exhibit
both
effective
electrical
insulation
(<2.99
×
10
−9
S
m
−1
)
dissipation
(3.64
W
K
properties.
based
on
contribute
development
low‐cost,
insulating,
heat‐dissipating
Materials,
Journal Year:
2025,
Volume and Issue:
18(6), P. 1236 - 1236
Published: March 11, 2025
This
study
utilizes
machine
learning
(ML)
techniques
to
predict
the
performance
of
slag-based
cemented
tailings
backfill
(CTB)
activated
by
soda
residue
(SR)
and
calcium
carbide
slag
(CS).
An
experimental
database
consisting
240
test
results
is
utilized
thoroughly
evaluate
accuracy
seven
ML
in
predicting
properties
filling
materials.
These
include
support
vector
(SVM),
random
forest
(RF),
backpropagation
(BP),
genetic
algorithm
optimization
BP
(GABP),
radial
basis
function
(RBF)
neural
network,
convolutional
network
(CNN),
long
short-term
memory
(LSTM)
network.
The
findings
reveal
that
RBF
SVM
models
demonstrate
significant
advantages,
achieving
a
coefficient
determination
(R2)
approximately
0.99,
while
R2
for
other
ranges
from
0.86
0.98.
Additionally,
dynamic
growth
model
strength
developed
using
techniques.
accurately
predicts
time
required
materials
reach
specified
strength.
In
contrast,
BP,
SVM,
CNN
show
delays
this
curing
age,
RF,
GABP,
LSTM
tend
overestimate
material
when
it
approaches
or
fails
2
MPa.
Finally,
employed
perform
coupling
analysis
on
with
various
mix
ratios
ages.
effectively
changes
over
different
ages
raw
contents,
offering
valuable
scientific
design
