Study on Liutex-driven reward for intelligent flow control by dynamic feature-based deep reinforcement learning
Qi Wang,
No information about this author
Xiangrui Dong,
No information about this author
Setthivoine You
No information about this author
et al.
AIP Advances,
Journal Year:
2025,
Volume and Issue:
15(5)
Published: May 1, 2025
The
issue
of
flow
separation
over
an
airfoil
under
weak
turbulent
conditions
is
addressed
and
resolved
through
the
deep
reinforcement
learning
(DRL)
strategy.
To
suppress
generation
instability
vortex
shedding
alley
airfoil,
a
novel
reward
function
named
RLiutex,
considering
suppression
rigid
rotation
intensity
core
size
vortex,
first
proposed
in
this
paper.
great
potential
Liutex-driven
for
effective
large
eddy
elimination
aerodynamic
optimization
verified
work.
Furthermore,
dynamic
feature-based
DRL
(DF-DRL)
framework
redeveloped
to
markedly
enhance
efficiency
convergence
speed.
combination
with
DF-DRL
results
exceptional
performance,
minimal
fluctuations
both
drag
lift
coefficients,
highlighting
approach
advanced
control
strategies.
Language: Английский
Optimal Jet Flow Control for Suppressing Three-Dimensional Vortex-Induced Motion in Floating Cylinders at Subcritical Reynolds Numbers
Wulong Hu,
No information about this author
Haishan Xia,
No information about this author
Lei Li
No information about this author
et al.
Published: Jan. 1, 2025
Language: Английский
Optimal Jet Flow Control for Suppressing Three-Dimensional Vortex-Induced Motion in Floating Cylinders at Subcritical Reynolds Numbers
Wulong Hu,
No information about this author
Haishan Xia,
No information about this author
Lei Li
No information about this author
et al.
Published: Jan. 1, 2025
Language: Английский
Current Review on Numerical Simulation of Synthetic Jet (SJ) Cooling
Nawal Radhiah,
No information about this author
S.M. Firdaus,
No information about this author
A. M. Yusof
No information about this author
et al.
CFD letters,
Journal Year:
2023,
Volume and Issue:
15(5), P. 1 - 17
Published: March 16, 2023
This
paper
reviews
the
working
principles
and
numerical
approach
for
synthetic
jet
cooling
in
previous
studies.
It
is
essential
to
relevant
research
within
study
scope
order
further
enhance
improvement
of
technology.
Furthermore,
can
cut
cost
save
time
compared
experimental
works.
Numerical
simulation
crucial
expedite
product
enhancement
as
it
opens
up
big
potential
electronic
device
application.
Studies
carried
out
by
many
scholars
this
publication
have
demonstrated
that
resonance
frequency
enhances
performance
jet.
Reynold
numbers
vary
with
frequency,
greater
produced
higher
heat
transfer
coefficients.
The
majority
researchers
also
chosen
cylindrical
cavity
type
because
offers
superior
velocity
output,
which
improves
performance.
According
studies,
a
smaller
diameter
leads
output
number
Language: Английский
Algorithm to Generate Liutex Core Lines Based on Forward Liutex Magnitude Gradient Lines
IntechOpen eBooks,
Journal Year:
2023,
Volume and Issue:
unknown
Published: Dec. 4, 2023
Vortex
definition
and
identification
are
extremely
important
for
the
study
of
fluid
dynamics
research.
Liutex
is
a
newly
proposed
concept
that
correctly
represents
vortex.
vector
whose
direction
local
rotation
axis
magnitude
twice
angular
speed.
To
identify
unique
structure
vortex,
method
known
as
Core
Line
has
been
developed,
which
displays
rotational
core
However,
original
manual
method,
not
practical
real
application,
an
automatic
algorithm
required
usage.
Xu
et
al.
by
selecting
best
line
from
group
candidate
lines,
progress.
In
this
chapter,
another
perspective
to
solve
problem,
new
introduced
based
on
forward
gradient
lines.
Since
lines
have
feature
they
advance
maximums,
route
will
still
result
in
line,
avoids
process
find
line.
This
achieved
some
success
Lambda
vortex
early
boundary
layer
transition.
Language: Английский