International Journal of Pavement Engineering,
Год журнала:
2024,
Номер
25(1)
Опубликована: Окт. 23, 2024
An
essential
aspect
of
pavement
construction
sustainability
is
its
low-energy
consumption
and
emissions.
The
study
materials
workability
tests
holds
significant
importance
in
terms
achieving
well-mixed
conditions
with
consumption.
complex
components
the
material
uncertain
kinematic
behaviours
aggregates
during
mixing
make
this
process
challenging.
And,
few
studies
signal
response
have
been
found
field
civil
engineering.
For
purpose,
an
accurate
evaluation
monitoring
approach
for
are
needed.
In
paper,
a
wireless
real-time
sensing
method
used
to
monitor
dynamic
behaviour
mixing.
A
3D
digital
twin
model,
combining
data-sensing
techniques
numerical
simulation,
has
proposed
rapid
identification
material.
This
model
validated
via
data-fusion
algorithm.
application
makes
contribution
data-intensive
analysing
jobs
decision-making
tasks
Proceedings of the Institution of Civil Engineers - Construction Materials,
Год журнала:
2023,
Номер
177(4), С. 249 - 264
Опубликована: Авг. 9, 2023
The
durability
of
pavement
structures
is
influenced
by
their
dynamic
responses,
which
are
governed
factors
such
as
traffic
loads,
temperature
variations
and
material
properties.
In
this
study,
the
behaviour
asphalt
subjected
to
harmonic
rectangular
moving
loads
varying
boundary
conditions
profiles
investigated.
response
multi-layered
pavements
analysed
using
third-order
shear
deformation
plate
theory.
governing
equations
motion
in
time
domain
derived
Hamilton's
principle,
solutions
obtained
Laplace
through
Fourier
series.
Durbin's
transform
then
applied
revert
back
domain.
accuracy
proposed
approach
validated
comparisons
with
literature
data
finite-element
simulations.
results
demonstrate
that
these
significantly
influence
considered
system
excitations.
study's
key
findings
include
a
higher
observed
under
uniform
fields
compared
linear
distributions.
Harmonic
patterns
result
larger
deflections
than
profiles.
Therefore,
non-uniformity
fields,
particularly
those
patterns,
should
be
design
construction.
SAE International journal of vehicle dynamics, stability, and NVH,
Год журнала:
2023,
Номер
7(2)
Опубликована: Май 22, 2023
<div>The
operating
parameters
of
the
asphalt-paver
vibration-screed
system
(AP-VSS)
including
excitation
frequencies
tampers
and
vibratory
screed
(<i>f<sub>t</sub>
</i>
<i>f<sub>s</sub>
</i>)
angular
deviations
(<i>α</i>
<sub>1</sub>
<i>α</i>
<sub>2</sub>)
affect
not
only
pavement
quality
but
also
compaction
efficiency.
Based
on
dynamic
model
AP-VSS
interaction
tamper
hot-mixed
asphalt,
experimental
numerical
simulation
studies
are
performed
to
analyze
in
detail
influence
The
maximum
value
root-mean-square
acceleration
(<i>a<sub>r.m.s</sub>
force
(<i>F<sub>r.m.s</sub>
selected
as
objective
functions.
results
indicate
that
by
using
design
parameters,
efficiency
quite
low.
To
enhance
performance,
operation
then
optimized
multi-objective
optimization
algorithm.
optimal
result
shows
compression
energy
asphalt
is
greatly
increased
36.2%
comparison
without
optimization.
Concurrently,
both
values
<i>a<sub>r.m.s</sub>
<i>F<sub>r.m.s</sub>
uniformly
distributed
over
length
floor
surface
Therefore,
remarkably
improved.</div>
Industrial & Engineering Chemistry Research,
Год журнала:
2023,
Номер
62(43), С. 17787 - 17804
Опубликована: Окт. 19, 2023
Thermogravimetric
analysis
(TGA)
has
been
extensively
used
in
the
bitumen
literature
to
investigate
its
thermal
stability
and
various
stages
of
decomposition.
The
primary
aim
these
studies
calculate
kinetic
parameters,
such
as
activation
energy
pre-exponential
factor
each
event.
However,
our
current
paper,
we
explore
application
three
machine
learning
(ML)
techniques,
namely,
support
vector
regression
(SVR),
random
forest
(RF),
gradient
booster
(GBR),
predict
TGA
data
for
asphaltenes
extracted
from
feed
products
visbreaking
types
materials:
(i)
deasphalted
oil
(DAO),
(ii)
DAO
doped
with
5.55
wt
%
indene,
(iii)
11.11
indene.
addition
indene
was
shown
significantly
affect
free-radical
chemistry
a
previous
work,
key
contribution
work
this
paper
minimize
requirement
instrument
obtain
mass
loss
curves
by
employing
ML
techniques
on
available
experimental
data.
This
will
reduce
human
errors
involved
sample
preparation
collection
well
decrease
process
time
obtaining
compared
experimentation.
We
observed
that
based
decision
trees,
i.e.,
RF
GBR,
showed
best
performance
highest
prediction
accuracy
>0.99
predicting
obtained
reacting
feedstocks
at
reaction
times
30,
45,
60
min.
A
number
inputs
were
considered
models,
temperature
chamber
sample,
heat
supplied
time,
spent
inside
chamber.
novelty
lies
fact
no
study
reproduced
indene-added
their
visbroken
through
approaches,
believe
results
help
fastening
heavy
industry
eliminating
need
offline
measuring
instruments.
Machine
studying
is
unexpectedly
revolutionizing
the
manner
facts
analyzed
and
utilized
in
actual-time
selections.
with
aid
of
utilising
effective
algorithms,
gadget
gaining
knowledge
can
unlock
insights
from
input
statistics
greater
speedy
as
it
should
be
than
traditional
strategies.
however,
to
make
sure
its
fulfillment
effectiveness,
there
have
a
quantitative
size
procedure
assess
how
device
algorithms
are
impacting
effectiveness
information
evaluation.
This
paper
pursuits
provide
comprehensive
evaluation
cutting-edge
nation
learning
effect
on
analysis,
well
unique
techniques
degree
algorithms.
specifically,
will
observe
use
supervised
fashions,
unsupervised
reinforcement
mastering
strategies
create
efficient
correct
fashions
that
could
quickly
analyze
produce
beneficial
real-time
statistics.
Additionally,
this
talk
various
used
quantify
which
includes
predictive
accuracy,
records
function
selection,
model
interpretability.
finally,
even
discuss
challenges
destiny
issues
for
measuring
authentic
machine
analysis.
Journal of Rock Mechanics and Geotechnical Engineering,
Год журнала:
2024,
Номер
16(11), С. 4782 - 4797
Опубликована: Апрель 29, 2024
The
ultrasonic
pulse
velocity
(UPV)
correlates
significantly
with
the
density
and
pore
size
of
subgrade
filling
materials.
This
research
conducts
numerous
Proctor
UPV
tests
to
examine
how
moisture
rock
content
affect
compaction
quality.
study
measures
changes
in
across
dry
characteristics.
compacted
specimens
exhibit
distinct
microstructures
mechanical
properties
along
wet
sides
curve,
primarily
influenced
by
internal
water
molecules.
maximum
exhibits
a
positive
correlation
content,
while
optimal
demonstrates
an
inverse
relationship.
As
increases,
relative
error
measurement
rises.
follows
hump-shaped
pattern
initial
content.
Three
intelligent
models
are
established
forecast
density.
measure
PSO-BP-NN
model
quickly
assesses
IEEE Access,
Год журнала:
2024,
Номер
12, С. 100377 - 100388
Опубликована: Янв. 1, 2024
Accurate
detection
of
water
holdup
in
oil-water
two-phase
flow
is
crucial
for
optimizing
production
and
improving
crude
oil
recovery.
The
transmission
lines
method
currently
one
the
few
effective
methods
to
measure
flow.
However,
variations
temperature
mineralization
will
alter
dielectric
constant
conductivity
mixture
respectively,
posing
challenges
precise
measurement.
complex
nonlinear
relationship
between
these
factors
limits
prediction
range
accuracy
widely
used
models,
such
as
BP
neural
network
Support
Vector
Machine
(SVM).
In
order
overcome
issues,
this
paper
establishes
a
multi-sensor
indoor
experiment
system
studies
phase
shift
sensor
signal
influencing
factors.
On
basis,
proposes
combined
model
(BO-XGBoost)
Bayesian
optimization
(BO)
algorithm
extreme
gradient
boosting
(XGBoost).
results
demonstrate
that
XGBoost
outperforms
traditional
SVM
predicting
across
full
0%-100%.
average
absolute
error
BO-XGBoost
only
1.50%.
above
research
achieves
full-range,
high-precision
prediction,
providing
new
solution
oilfield
development
possessing
practical
engineering
significance.
International Journal of Pavement Engineering,
Год журнала:
2024,
Номер
25(1)
Опубликована: Окт. 23, 2024
An
essential
aspect
of
pavement
construction
sustainability
is
its
low-energy
consumption
and
emissions.
The
study
materials
workability
tests
holds
significant
importance
in
terms
achieving
well-mixed
conditions
with
consumption.
complex
components
the
material
uncertain
kinematic
behaviours
aggregates
during
mixing
make
this
process
challenging.
And,
few
studies
signal
response
have
been
found
field
civil
engineering.
For
purpose,
an
accurate
evaluation
monitoring
approach
for
are
needed.
In
paper,
a
wireless
real-time
sensing
method
used
to
monitor
dynamic
behaviour
mixing.
A
3D
digital
twin
model,
combining
data-sensing
techniques
numerical
simulation,
has
proposed
rapid
identification
material.
This
model
validated
via
data-fusion
algorithm.
application
makes
contribution
data-intensive
analysing
jobs
decision-making
tasks
