3d Fluid-Particle Interaction Dynamics and Filtration Performance of Realistic Fibrous Filters Using Deep Learning and X-Ray Computed Tomography Images
Published: Jan. 1, 2025
Language: Английский
A Hybrid Physics–Machine Learning Approach for Modeling Plastic–Bed Interactions during Fluidized Bed Pyrolysis
Energy & Fuels,
Journal Year:
2025,
Volume and Issue:
39(9), P. 4549 - 4564
Published: Feb. 19, 2025
The
axial
mixing/segregation
behavior
of
single
plastic
particles
in
a
bubbling
fluidized
bed
reactor
has
been
investigated
by
noninvasive
X-ray
imaging
techniques
the
temperature
range
500–650
°C
and
under
pyrolysis
conditions.
Experimental
results
showed
that
extent
mixing
between
particle
increases
as
both
fluidization
velocity
increase.
Three
modeling
approaches
were
proposed
to
describe
particle,
i.e.,
purely
mechanistic
model,
physics-informed
neural
network
(PINN),
an
augmented
PINN
(augPINN).
former
model
is
based
on
second
law
motion.
standard
PINN,
built
simply
embedding
motion
loss
function.
third
approach
involves
introduction
new
interphase
distribution
parameter,
P,
into
model.
This
parameter
represents
relative
importance
effects
emulsion
bubble
phases
particle.
was
obtained
training
using
displacement
data.
augPINN
shown
outperform
models
describing
polypropylene
particles.
Moreover,
P
found
be
physically
interpretable.
main
novelty
this
work
show
how
different
frameworks
concept
machine
learning
can
successfully
applied
complex
real-world
hydrodynamic
data
sets.
Language: Английский
Rapid prediction of the flow fields of fluidized beds with the varying flow regimes by coupling CFD and machine learning
Chemical Engineering Science,
Journal Year:
2025,
Volume and Issue:
unknown, P. 121635 - 121635
Published: April 1, 2025
Language: Английский
Convolutional neural network based reconstruction of flow-fields from concentration fields for liquid-droplet coalescence
Communications Physics,
Journal Year:
2025,
Volume and Issue:
8(1)
Published: April 24, 2025
Language: Английский
Prediction of fluid-particle dynamics and performance in fibrous filters obtained from X-ray CT using convolutional neural network and discrete phase model
Chemical Engineering Journal,
Journal Year:
2025,
Volume and Issue:
unknown, P. 163243 - 163243
Published: April 1, 2025
Language: Английский
50 Years of International Journal of Multiphase Flow: Experimental Methods for Dispersed Multiphase Flows
International Journal of Multiphase Flow,
Journal Year:
2025,
Volume and Issue:
unknown, P. 105239 - 105239
Published: April 1, 2025
Language: Английский
Bubble Detection in Multiphase Flows Through Computer Vision and Deep Learning for Applied Modeling
Mathematics,
Journal Year:
2024,
Volume and Issue:
12(23), P. 3864 - 3864
Published: Dec. 9, 2024
An
innovative
method
for
bubble
detection
and
characterization
in
multiphase
flows
using
advanced
computer
vision
neural
network
algorithms
is
introduced.
Building
on
the
research
group’s
previous
findings,
this
study
combines
high-speed
video
capture
with
deep
learning
techniques
to
enhance
accuracy
dynamic
analysis.
In
order
further
develop
a
robust
framework
detecting
analyzing
properties
flows,
enabling
accurate
estimation
of
essential
mass
transfer
parameters,
YOLOv9-based
was
implemented
segmentation
trajectory
analysis,
achieving
high
accuracy.
Key
contributions
include
development
an
averaged
model
integrating
experimental
data,
outputs,
scaling
algorithms,
as
well
validation
proposed
methodology
through
studies,
including
imaging
comparisons
coefficients
obtained
via
sulfite
method.
By
precisely
characterizing
critical
algorithm
enables
gas
rate
calculations,
ensuring
optimal
conditions
various
industrial
applications.
The
network-based
serves
non-invasive
platform
detailed
media,
demonstrating
significantly
outperforming
traditional
techniques.
This
approach
provides
tool
real-time
monitoring
modeling
laying
foundation
novel,
methods
measure
media
properties.
Language: Английский
Optimizing Stereolithography Printing Parameters for Enhanced Microfluidic Chip Quality
Smart and Sustainable Manufacturing Systems,
Journal Year:
2024,
Volume and Issue:
8(1), P. 136 - 149
Published: Dec. 30, 2024
ABSTRACT
In
the
pursuit
of
innovative
biosensing
technologies
for
critical
applications
such
as
early
breast
cancer
detection,
development
efficient
and
portable
devices
is
crucial.
This
work
describes
a
unique
stereolithography
(SLA)-based
three-dimensional–printed
microfluidic
device
intended
particularly
optofluidic
with
just
microliter
quantities
blood,
similar
to
diabetes
monitoring
devices.
Unlike
typical
cumbersome
lab
equipment
Biacore
machine,
which
needs
large
blood
sample
volumes
laboratory
processing,
technology
allows
patient-operated,
at-home
testing,
decreasing
requirement
hospital
visits.
The
main
contribution
this
study
optimize
SLA
printing
parameters,
namely
exposure
duration,
in
order
improve
chip’s
transparency
channel
quality.
improvement
exact
immobilization
biorecognition
components
within
channels,
resulting
sensitive
biomarker
detection.
By
extending
we
considerably
increase
structural
integrity
optical
clarity
are
successful
biosignal
transduction
labeled
sensing
applications.
not
only
leads
cheaper
cost
faster
manufacturing
compared
conventional
but
also
offers
increased
performance
real
bio-sensing
Thus,
our
represents
big
step
forward
accessible,
efficient,
compact
early-stage
illness
diagnosis,
outperforming
existing
lab-based
diagnostics.
Language: Английский