Structural Control and Health Monitoring,
Journal Year:
2024,
Volume and Issue:
2024(1)
Published: Jan. 1, 2024
Machine
learning
(ML)
methods
have
become
increasingly
prominent
for
predicting
material
and
structural
performance
in
civil
engineering.
However,
these
often
require
repetitive
iterations
optimizations
by
professionals
to
obtain
an
optimal
model,
which
are
time‐consuming
challenging
nonexpert
users.
In
this
paper,
we
propose
automated
ML
(Auto‐ML)
model
using
the
tree‐based
pipeline
optimization
tool
(TPOT)
address
limitations
streamline
prediction
process.
TPOT
leverages
genetic
programming
optimize
various
models,
including
DT,
RF,
GBDT,
LightGBM,
XGBoost,
search
possible
models
that
fits
a
particular
dataset,
cuts
most
tedious
parts
of
ML.
To
demonstrate
effectiveness
TPOT‐based
Auto‐ML,
two
case
studies
presented
Auto‐ML
algorithms
construct
compressive
strength
recycled
micropowder
mortar,
punching
shear
bearing
capacity/failure
mode
RC
slab‐column
joints.
explain
“black
box”
Shapley
Additive
Explanation
(SHAP)
is
introduced
interpret
best
predictive
rank
importance
influencing
factors,
providing
basis
design.
Finally,
user
interface
(UI)
engineering
applications
developed
enables
end‐to‐end
automation
from
data
preprocessing
results
presentation.
Developments in the Built Environment,
Journal Year:
2024,
Volume and Issue:
19, P. 100494 - 100494
Published: July 1, 2024
This
research
explores
the
use
of
machine
learning
to
predict
mechanical
properties
cementitious
materials
enhanced
with
carbon
nanotubes
(CNTs).
Specifically,
study
focuses
on
estimating
elastic
modulus
and
flexural
strength
these
novel
composite
materials,
potential
significantly
impact
construction
industry.
Seven
key
variables
were
analyzed
including
water-to-cement
ratio,
sand-to-cement
curing
age,
CNT
aspect
content,
surfactant-to-CNT
sonication
time.
Artificial
neural
network,
support
vector
regression,
histogram
gradient
boosting,
used
properties.
Furthermore,
a
user-friendly
formula
was
extracted
from
network
model.
Each
model
performance
evaluated,
revealing
be
most
effective
for
predicting
modulus.
However,
boosting
outperformed
all
others
in
strength.
These
findings
highlight
effectiveness
employed
techniques,
accurately
CNT-enhanced
materials.
Additionally,
extracting
formulas
provides
valuable
insights
into
interplay
between
input
parameters
Matéria (Rio de Janeiro),
Journal Year:
2025,
Volume and Issue:
30
Published: Jan. 1, 2025
ABSTRACT
Utilization
of
Nano-structure
pyrolytic
carbon
(NSPC)
particles
holds
significant
potential
in
developing
nanocomposites.
Consequently,
compressive
strength
is
a
crucial
characteristic
which
stipulates
the
efficiency
NSPC
cementitious
composites.
Nevertheless,
predicting
this
nanocomposite
challenge
due
to
distorted
responses
and
complex
structures.
The
main
novelty
research
predict
developed
nanocomposite.
Therefore,
machine
learning
(ML)
model
first-time
proposed
for
mortar
incorporated
with
various
dosages
particles.
In
addition,
bound
water
determined
understand
hydration
process.
This
work
highlights
comprehensive
comparison
six
ML
algorithms,
such
as
linear
regression,
random
forest
extra
trees,
gradient
boost
regressor,
extreme
boost,
LightGBM,
prediction
accuracy
Furthermore,
it
evaluated
through
multiple
statistical
error
analysis.
Seventeen
parameters
were
considered
input
variables
mortar.
According
coefficient
determination
analysis,
regressor
attained
highest
R2
value
0.87,
while
trees
achieved
values
0.86
0.85,
respectively.
low
mean
absolute
3.229
was
earned
boost.
Overall,
reliable
performed
better
mapping
interplay
between
strength.
Energies,
Journal Year:
2024,
Volume and Issue:
17(23), P. 6046 - 6046
Published: Dec. 1, 2024
This
paper
thoroughly
examines
the
latest
developments
and
diverse
applications
of
Carbon
Capture,
Utilization,
Storage
(CCUS)
in
civil
engineering.
It
provides
a
critical
analysis
technology’s
potential
to
mitigate
effects
climate
change.
Initially,
comprehensive
outline
CCUS
technologies
is
presented,
emphasising
their
vital
function
carbon
dioxide
(CO2)
emission
capture,
conversion,
sequestration.
Subsequent
sections
provide
an
in-depth
capture
technologies,
utilisation
processes,
storage
solutions.
These
serve
as
foundation
for
architectural
framework
that
facilitates
design
integration
efficient
systems.
Significant
attention
given
inventive
application
building
construction
industry.
Notable
examples
such
include
using
(C)
cement
promoting
sustainable
production.
Economic
analyses
financing
mechanisms
are
reviewed
assess
commercial
feasibility
scalability
projects.
In
addition,
this
review
technological
advances
innovations
have
occurred,
providing
insight
into
future
course
progress.
A
environmental
regulatory
environments
conducted
evaluate
compliance
with
policies
technology
deployment.
Case
studies
from
real
world
provided
illustrate
effectiveness
practical
applications.
concludes
by
importance
continued
research,
policy
support,
innovation
developing
fundamental
component
engineering
practices.
tenacious
stride
toward
neutrality
underscored.
