Physics of Fluids,
Год журнала:
2024,
Номер
36(12)
Опубликована: Дек. 1, 2024
The
study
of
fish
swimming
behavior
and
locomotion
mechanisms
holds
substantial
scientific
engineering
significance.
With
the
rapid
progression
artificial
intelligence,
integration
intelligence
with
high-precision
numerical
simulation
methods
presents
a
novel
highly
efficient
tool
for
investigating
behavior.
In
this
paper,
we
proposed
perception
model
that
more
closely
reflects
natural
logic.
By
introducing
individual
vision
partially
visibility
model,
physics-based
visual
system
mirrored
sensory
capabilities
live
was
developed.
Furthermore,
through
construction
flow
using
conventional
neural
networks,
enhanced
intelligent
fish's
ability
to
detect
unsteady
hydrodynamic
parameters
via
lateral
line.
validity
new
demonstrated
experiments,
which
hunts
complex
moving
targets
in
flow.
Finally,
applied
refuge/predation
behaviors
coral
reef
under
varying
pressures.
results
indicated
significantly
impact
survival
strategies
high
velocity,
environments,
shaping
distinct
evolutionary
decision-making
traits.
These
insights
may
help
understand
niche
competition
different
conditions.
Geophysical Research Letters,
Год журнала:
2024,
Номер
51(12)
Опубликована: Июнь 14, 2024
Abstract
Bedload
sediment
transport
plays
an
important
role
in
the
evolution
of
rivers,
marshes
and
deltas.
In
these
aquatic
environments,
vegetation
is
widespread,
plant
species
have
unique
morphology.
However,
impact
real
morphology
on
flow
has
not
been
quantified.
This
study
used
model
plants
with
morphology,
based
Phragmites
australis
,
Acorus
calamus
Typha
latifolia
.
The
frontal
area
increases
away
from
bed,
which
leads
to
higher
near‐bed
velocity
than
would
be
predicted
depth‐average
area.
A
coefficient
was
defined
quantify
vertically‐varied
Laboratory
experiments
confirmed
that
improved
prediction
velocity,
turbulent
kinetic
energy
bedload
rate
canopies
realistic
Plant
can
alter
rates
by
up
order
magnitude,
relative
assumption
uniform
Water Resources Research,
Год журнала:
2024,
Номер
60(7)
Опубликована: Июль 1, 2024
Abstract
River
restoration
projects
often
involve
vegetation
planting
to
retain
sediment
and
stabilize
riverbanks.
Laboratory
experiments
have
explored
the
impact
of
rigid
emergent
canopies
on
bed
morphology.
Inside
canopies,
erosion
is
attributed
vegetation‐induced
turbulent
kinetic
energy
(
TKE
).
Based
in‐canopy
local
criteria
for
movement,
a
method
established
validated
predicting
length
region.
In
bare
channel,
related
ratio
canopy
flow
adjustment
distance,
L
/
I
,
exhibits
two
trends.
At
<
1,
maximum
depth,
d
s
)
length,
region
increase
with
increasing
length.
≥
are
not
influenced
by
remain
constant.
vegetated
regions
same
plant
density,
discontinuous
(streamwise
interval
width
D
yield
weaker
than
continuous
canopies.
The
mutual
influence
between
must
be
considered
if
satisfies
3
.
These
results
provide
insights
designing
river
projects.
The
autonomous
swimming
of
fish
in
a
complex
flow
environment
is
nonlinear
and
intricate
system,
which
the
focus
challenge
various
fields.
This
study
proposed
novel
simulation
framework
for
artificial
intelligence
fish.
It
employed
high-precision
immersed
boundary-lattice
Boltzmann
coupling
scheme
to
simulate
interactions
between
real
time,
utilized
soft
actor-critic
(SAC)
deep
reinforcement
learning
algorithm
brain
decision-making
module,
was
further
divided
into
vision-based
directional
navigation
lateral
line-based
perception
modules,
each
matched
with
its
corresponding
macro-action
space.
features
were
extracted
using
neural
network
based
on
multi-classification
from
data
perceived
by
line
linked
actions.
predation
Kármán
gait
explored
terms
training,
simulation,
generalization.
Numerical
results
demonstrated
significant
advantages
convergence
speed
training
efficiency
SAC
algorithm.
Owing
closed-loop
“perceive-feedback-memory”
mode,
intelligent
can
respond
real-time
changes
fields
reward-driven
requirements
experience,
accumulated
experience
be
directly
other
fields,
adaptability,
model
efficiency,
generalization
substantially
improved.
Water Resources Research,
Год журнала:
2024,
Номер
60(7)
Опубликована: Июль 1, 2024
Abstract
Investigations
of
water
flow
movements
affected
by
vegetation
is
a
research
hotspot
in
ecological
restoration.
The
theory
and
equations
the
velocity
distribution
under
influence
rigid
are
relatively
mature.
This
study
proposes
new
drag
force
equation
that
varies
with
bending
angle
analytical
solution
profile.
Comparisons
between
model
calculation
experimental
data,
results
showed
this
proposed
produced
accurate
simulations
for
through
flexible
various
deflections.
In
addition,
was
verified
to
be
applicable
without
angle.
Moreover,
features
parameters
adopted
discussed,
empirical
these
presented.
further
improves
field
environmental
fluid
mechanics
can
serve
as
theoretical
underpinning
restoration
river
courses.
