Research Square (Research Square),
Journal Year:
2023,
Volume and Issue:
unknown
Published: Dec. 12, 2023
Abstract
This
paper
addresses
the
robot
machining
requirements
for
large
aerospace
structural
components
and
provides
a
method
rapid
workpiece
positioning
in
systems
that
combines
ease
of
visual
measurement-based
with
precision
contact-based
positioning.
In
order
to
enhance
calibration
system,
this
introduces
utilizes
ruby
probe
as
tool
perform
sphere-to-sphere
contact
Tool
Center
Point
(TCP).
A
model
is
established,
converting
problem
into
non-linear
least
squares
optimization
problem.
To
address
challenges
multi-dimensional
non-convex
continuous
optimization,
designs
combined
LM-D
algorithm
incorporates
Levenberg-Marquardt
(L-M)
DIRECT
algorithm,
engaging
mutual
iterative
processes
obtain
global
optimum.
approach
ensuring
efficiency
while
maximizing
potential
optimum
solution.
an
convergence
termination
criterion
TCP
which
used
determine
whether
converges
globally.
also
contributes
improving
algorithm's
efficiency.
Experimental
tests
were
conducted
on
typical
industrial
robots,
results
illustrate
superior
performance
terms
both
high
iteration
compared
traditional
methods.
research
offers
promising
efficient
solution
industrial.
Applied Sciences,
Journal Year:
2025,
Volume and Issue:
15(3), P. 1033 - 1033
Published: Jan. 21, 2025
This
paper
addresses
the
machining
requirements
for
large
aerospace
structural
components
using
robotic
systems
and
proposes
a
method
rapid
workpiece
positioning
that
combines
simplicity
of
vision-based
with
precision
contact-based
methods.
To
enhance
accuracy
robot
calibration,
novel
approach
utilizing
ruby
probe
sphere-to-sphere
contact
calibration
Tool
Center
Point
(TCP)
is
introduced.
A
model
formulated,
transforming
process
into
nonlinear
least
squares
(NLS)
optimization
problem.
tackle
challenges
NLS
optimization,
hybrid
LM-D
algorithm
developed,
integrating
Levenberg–Marquardt
(L-M)
DIviding
RECTangle
(DIRECT)
algorithms
in
an
iterative
to
achieve
global
optimum.
ensures
computational
efficiency
while
maximizing
likelihood
finding
globally
optimal
solution.
An
convergence
termination
criterion
TCP
established
determine
convergence,
further
enhancing
algorithm’s
efficiency.
Experimental
validation
was
performed
on
industrial
robots,
demonstrating
proposed
superior
performance
iteration
compared
traditional
research
provides
effective
practical
solution
applications.
Energy and AI,
Journal Year:
2024,
Volume and Issue:
16, P. 100371 - 100371
Published: April 17, 2024
This
paper
proposes
an
integration
of
recent
metaheuristic
algorithm
namely
Evolutionary
Mating
Algorithm
(EMA)
in
optimizing
the
weights
and
biases
deep
neural
networks
(DNN)
for
forecasting
solar
power
generation.
The
study
employs
a
Feed
Forward
Neural
Network
(FFNN)
to
forecast
AC
output
using
real
plant
measurements
spanning
34-day
period,
recorded
at
15-minute
intervals.
intricate
nonlinear
relationship
between
irradiation,
ambient
temperature,
module
temperature
is
captured
accurate
prediction.
Additionally,
conducts
comprehensive
comparison
with
established
algorithms,
including
Differential
Evolution
(DE-DNN),
Barnacles
Optimizer
(BMO-DNN),
Particle
Swarm
Optimization
(PSO-DNN),
Harmony
Search
(HSA-DNN),
DNN
Adaptive
Moment
Estimation
optimizer
(ADAM)
Nonlinear
AutoRegressive
eXogenous
inputs
(NARX).
experimental
results
distinctly
highlight
exceptional
performance
EMA-DNN
by
attaining
lowest
Root
Mean
Squared
Error
(RMSE)
during
testing.
contribution
not
only
advances
methodologies
but
also
underscores
potential
merging
algorithms
contemporary
improved
accuracy
reliability.
IEEE Access,
Journal Year:
2024,
Volume and Issue:
12, P. 108313 - 108327
Published: Jan. 1, 2024
The
high
penetration
of
Renewable
Energy
Sources
(RES)
and
Electric
Vehicles
(EVs)
into
the
grid
introduces
new
challenges
for
Distribution
Systems
(DSs).
uncertainties
related
to
these
assets
necessitate
development
real-time
methodologies
optimize
operation
Low
Voltage
(LV)
Medium
(MV)
DSs.
This
paper
aims
fill
gap
in
literature
by
proposing
a
holistic
DS
optimization
model
that
considers
coupling
MV
LV
Specifically,
methodology
adopts
bottom-up
three-layer
approach.
At
first
layer
an
optimal
EV
Smart
Charging
Scheduling
(SCS)
is
applied
power
losses
minimization
at
DSs,
considering
characteristics
individual
households
(maximum
rated
electrical
installation,
Photovoltaic
generation,
load
charging
demand).
second
residential
controller
fully
exploits
flexibility
EVs,
minimizing
impact
forecasting
errors
while
satisfying
limitations
regarding
households'
overloading
protection.
third
involves
Network
Reconfiguration
(NR)
methodology,
transactions
between
determining
topology
through
cost-worth
analysis
loss
reduction
switch
costs.
overall
design
proposed
ensures
broader
adoption,
repeatability,
adaptability,
scalability
across
diverse
including
various
types
DSs
(residential,
commercial,
etc.)
different
configurations.
can
reduce
up
34.41%
compared
base
scenario,
which
without
employing
either
SCS
or
NR.
Sustainability,
Journal Year:
2024,
Volume and Issue:
16(19), P. 8497 - 8497
Published: Sept. 29, 2024
The
integration
of
photovoltaic
and
electric
vehicles
in
distribution
networks
is
rapidly
increasing
due
to
the
shortage
fossil
fuels
need
for
environmental
protection.
However,
randomness
disordered
charging
loads
cause
imbalances
power
flow
within
system.
These
complicate
voltage
management
economic
inefficiencies
dispatching.
This
study
proposes
an
innovative
strategy
utilizing
battery
energy
storage
system
cooperation
achieve
regulation
photovoltaic-connected
Firstly,
a
novel
pelican
optimization
algorithm-XGBoost
introduced
enhance
accuracy
prediction.
To
address
challenge
loads,
wide-local
area
scheduling
method
implemented
using
Monte
Carlo
simulations.
Additionally,
scheme
allocation
slack
are
proposed
optimize
both
available
capacity
efficiency
Finally,
we
recommend
day-ahead
real-time
control
regulate
voltage.
utilizes
multi-particle
swarm
algorithm
dispatching
between
on
side
user
during
stage.
At
stage,
superior
capabilities
prediction
errors
vehicle
reservation
defaults.
models
IEEE
33
that
incorporates
high-penetration
photovoltaics,
vehicles,
systems.
A
comparative
analysis
four
scenarios
revealed
significant
financial
benefits.
approach
ensures
devices
sides
effective
management.
it
encourages
trading
activities
these
market
establishes
foundation
sides.
