Applied Mathematics and Nonlinear Sciences,
Год журнала:
2024,
Номер
9(1)
Опубликована: Янв. 1, 2024
Abstract
Improving
the
accuracy
and
stability
of
players’
stroke
speed
landing
point
maximizing
energy
conversion
have
become
important
tasks
in
table
tennis
skill
practice.
This
paper
analyzes
forces
during
ball
collision
law
its
motion
state
proposes
to
measure
identify
key
mechanical
parameters
from
aspects
batting
speed,
rotation,
angle.
The
3D
coordinates
are
reconstructed,
measured
translational
rotational
states
ball,
respectively.
UKF
estimator
is
used
construct
system
process
equations
model,
mathematical
expressions
further
derived
obtain
kinematic-based
post-collision
trajectory
prediction
model
ball.
predicting
movement
evaluated
by
distribution
error
points
it
known
through
experiments
that
range
method
this
(x±0.05,
y±0.05)
m,
which
smaller
than
estimated
traditional
physical
model’s
good.
After
analyzing
trajectories
with
different
angular
velocities,
drag
coefficients,
initial
exit
angles,
optimal
hitting
a
curved
circle
obtained
as
V=15m/s.
Applied Sciences,
Год журнала:
2025,
Номер
15(9), С. 5003 - 5003
Опубликована: Апрель 30, 2025
State-of-energy
(SOE)
estimation
helps
to
enhance
the
safety
of
battery
operation
and
predict
vehicle
range.
However,
voltage
plateau
LiFePO4
(LFP)
presents
a
significant
challenge
for
SOE
estimation.
Therefore,
this
paper
introduces
significantly
varying
mechanical
force
feature
tackle
flat
curve
in
mid-SOE
region.
A
fusion
model
that
integrates
bidirectional
long
short-term
memory
(BiLSTM)
network,
particle
swarm
optimization
(PSO),
Kalman
filter
(KF)
algorithm
is
proposed
The
BiLSTM
applied
fully
capture
temporal
dependencies
from
inputs
output
over
both
local
cycles.
Subsequently,
PSO
employed
optimize
parameters
KF,
which
utilized
smooth
results
thereby
achieving
highly
accurate
Experimental
across
different
operating
conditions
temperatures
reveal
introduction
improves
accuracy.
Compared
models
using
only
traditional
electrical
thermal
features,
with
achieves
average
improvements
67.06%,
66.38%,
66.46%
root
mean
square
error
(RMSE),
maximum
absolute
(MAXE),
(MAE),
respectively.
Moreover,
generalizability
robustness
method
are
further
confirmed
by
comparison
preload
forces.
Sensors,
Год журнала:
2025,
Номер
25(3), С. 749 - 749
Опубликована: Янв. 26, 2025
This
paper
presents
a
time-series
point-to-point
generative
adversarial
network
(TS-p2pGAN)
for
synthesizing
realistic
electric
vehicle
(EV)
driving
data.
The
model
accurately
generates
four
critical
operational
parameters—battery
state
of
charge
(SOC),
battery
voltage,
mechanical
acceleration,
and
torque—as
multivariate
Evaluation
on
70
real-world
trips
from
an
open
dataset
reveals
the
model’s
exceptional
accuracy
in
estimating
SOC
values,
particularly
under
complex
stop-and-restart
scenarios
across
diverse
initial
levels.
delivers
high
accuracy,
with
root
mean
square
error
(RMSE),
absolute
(MAE),
dynamic
time
warping
(DTW)
consistently
below
3%,
1.5%,
2.0%,
respectively.
Qualitative
analysis
using
principal
component
(PCA)
t-distributed
stochastic
neighbor
embedding
(t-SNE)
demonstrates
ability
to
preserve
both
feature
distributions
temporal
dynamics
original
data
augmentation
framework
offers
significant
potential
advancing
EV
technology,
digital
energy
management
lithium-ion
batteries
(LIBs),
autonomous
comfort
system
development.
