A review on properties and multi-objective performance predictions of concrete based on machine learning models
Materials Today Communications,
Год журнала:
2025,
Номер
unknown, С. 112017 - 112017
Опубликована: Фев. 1, 2025
Язык: Английский
Physics-based probabilistic analysis of corrosion initiation in alkali-activated slag concrete assisted by machine learning
Construction and Building Materials,
Год журнала:
2025,
Номер
471, С. 140661 - 140661
Опубликована: Март 8, 2025
Язык: Английский
Deep learning–based prediction of compressive strength of eco-friendly geopolymer concrete
Environmental Science and Pollution Research,
Год журнала:
2024,
Номер
31(28), С. 41246 - 41266
Опубликована: Июнь 7, 2024
The
greenhouse
gases
cause
global
warming
on
Earth.
cement
production
industry
is
one
of
the
largest
sectors
producing
gases.
geopolymer
produced
with
synthesized
by
reaction
an
alkaline
solution
and
waste
materials
such
as
slag
fly
ash.
use
eco-friendly
concrete
decreases
energy
consumption
In
this
study,
f
Язык: Английский
Sustainable Utilization of Waste Carbon Black in Recycled Steel Fibre Substituted Ultra High-Performance Concrete
R. Rajiv Gandhi,
B. Saritha
Iranian Journal of Science and Technology Transactions of Civil Engineering,
Год журнала:
2025,
Номер
unknown
Опубликована: Фев. 24, 2025
Язык: Английский
Sustainable Catalysts: Advances in Geopolymer-Catalyzed Reactions and Their Applications
Journal of Molecular Structure,
Год журнала:
2025,
Номер
unknown, С. 142017 - 142017
Опубликована: Март 1, 2025
Язык: Английский
Intelligent evaluation of interference effects between tall buildings based on wind tunnel experiments and explainable machine learning
Journal of Building Engineering,
Год журнала:
2024,
Номер
96, С. 110449 - 110449
Опубликована: Авг. 13, 2024
Язык: Английский
AI-based non-linear models for mechanical and toughness properties of sustainable fiber-reinforced geopolymer concrete (FRGPC)
Mechanics of Advanced Materials and Structures,
Год журнала:
2024,
Номер
unknown, С. 1 - 25
Опубликована: Окт. 31, 2024
The
incorporation
of
fibers
into
geopolymer
concrete
(GPC)
produces
FRGPC
which
mitigates
brittle
failure
and
restrains
macro
crack
propagation;
however,
research
on
predicting
the
mechanical
toughness
properties
remains
limited.
This
study
addresses
this
gap
by
developing
prediction
models
for
compressive
strength
(CS),
flexural
(FS),
(FT),
fracture
(FR).
A
dataset
600
data
points
was
compiled
from
published
literature,
encompassing
various
constituent
proportions,
fiber
shapes,
dosages,
aspect
ratios,
curing
conditions.
Employing
an
artificial
neural
network
(ANN)
methodology,
10
independent
variables
(g1,
g2,
….,
g10)
were
utilized
to
predict
four
dependent
(CS,
FS,
FT,
FR),
resulting
in
development
eight
non-linear
ANN
both
straight
(SFs)
hooked
(HFs).
Each
model
has
shown
a
higher
R2
value
lower
root
mean
square
error
(RMSE)
training
(70%),
testing
(15%),
validation
(15%)
datasets.
CS
with
HFs
(CS-HF)
SF
(CS-SF)
showed
values
0.983
0.973,
RMSE
2.088
2.435
MPa
highlighting
accuracy
models.
Similarly,
comparative
analysis
FR
exhibited
0.997
0.987,
0.045
Mpa
√m
0.032
FR-HF
FR-SF,
that
addition
strongly
impacts
improving
properties.
To
identify
most
influential
variable(s),
sensitivity
revealed
g10,
g1,
g8,
g9
as
parameters
SFs.
For
HFs,
g3
properties,
g9,
g10
toughness.
also
presented
mathematical
formulation
developed
better
interpretability
facilitate
optimal
economical
mix
design
selection,
potential
AI-based
advancing
sustainable
construction
materials.
Язык: Английский
Prediction and optimization framework of shear strength of reinforced concrete flanged shear wall based on machine learning and non-dominated sorting genetic algorithm-II
Advances in Structural Engineering,
Год журнала:
2024,
Номер
unknown
Опубликована: Сен. 10, 2024
Reinforced
concrete
(RC)
flanged
shear
wall
has
good
lateral
strength
and
stiffness,
which
been
widely
used
in
building
structures.
Due
to
the
coupling
effect
of
many
factors
such
as
section
shape,
span
ratio,
so
performance
evaluation
is
still
very
limited.
This
paper
proposed
a
prediction
framework
for
capacity
RC
walls.
A
database
containing
14
input
variables,
1
output
variable
153
samples
was
constructed
evaluate
accuracy
11
existing
design
methods.
The
Pearson
coefficient
preliminarily
analyze
correlation
between
variables.
grid
search
optimize
hyperparameters
4
machine
learning
models,
six
statistical
indicators
(
R
2
,
R,
RMSE,
SD,
MAE,
MAPE)
were
comprehensively
compare
results
ML
models
determine
best
model.
On
this
basis,
SHapley
Additive
exPlanations
(SHAP)
enhance
interpretability
mechanism
variables
on
quantified.
graphical
user
interface
(GUI)
guide
engineering
design.
multi-objective
model
(MOO)
established
trade-off
cost,
thereby
determining
optimal
scheme.
show
that
better
than
XGB
performance,
with
RMSE
are
0.99,
118.96,
respectively.
SHAP
method
can
effectively
t
w
l
f
′
c
key
parameters
affecting
wall.
Язык: Английский