Journal of Marine Science and Engineering,
Journal Year:
2023,
Volume and Issue:
11(9), P. 1690 - 1690
Published: Aug. 27, 2023
The
power
load
data
of
electric-powered
ships
vary
with
the
ships’
operational
status
and
external
environmental
factors
such
as
sea
conditions.
Therefore,
a
model
is
required
to
accurately
predict
ship’s
load,
which
depends
on
changes
in
marine
environment,
weather
situation.
This
study
used
an
actual
ship
ship.
research
forecasting
fluctuations
has
been
quite
limited,
existing
models
have
inherent
limitations
predicting
these
accurately.
In
this
paper,
A
multiple
feature
extraction
(MFE)-long
short-term
memory
(LSTM)
skip
connections
introduced
address
deep
learning
models.
novel
approach
enables
analysis
intricate
variations
ships,
thereby
facilitating
prediction
complex
fluctuations.
performance
was
compared
that
previous
convolutional
neural
network-LSTM
network
squeeze
excitation
(SE)
feed-forward
(DFF)
model.
metrics
for
comparison
were
mean
absolute
error,
root
squared
percentage
R-squared,
wherein
best,
average,
worst
performances
evaluated
both
proposed
exhibited
superior
predictive
models,
evidenced
by
metrics:
error
(MAE)
55.52,
(RMSE)
125.62,
(MAPE)
3.56,
R-squared
(R2)
0.86.
expected
be
during
operations.
Ocean Engineering,
Journal Year:
2023,
Volume and Issue:
280, P. 114670 - 114670
Published: May 11, 2023
This
paper
presents
a
comprehensive
review
of
the
current
regulations
and
various
technologies
as
well
decision
support
methods
for
each
technology
maritime
industry
considers
to
ensure
fleet's
sustainability.
It
covers
period
between
2010
2022,
emphasizing
last
four
years.
shows
impact
on
reduction
ship
resistance
energy
required
board,
affecting
amount
fuel
consumption
avoiding
transportation
harmful
species
around
world
achieve
smooth
transition
towards
green
shipping
by
improving
efficiency
achieving
goals
2050
plan.
The
five
main
topics:
hull
design,
propulsion
systems,
new
clean
fuels
treatment
power
systems
operation;
topic
has
different
included.
study's
findings
contribute
mapping
scientific
knowledge
in
field,
identifying
relevant
areas,
visualising
links
topics,
recognising
research
gaps
opportunities.
helps
present
holistic
approaches
future
supporting
cooperation
stakeholders
provide
more
realistic
solutions
toward
Journal of Marine Science and Engineering,
Journal Year:
2023,
Volume and Issue:
11(4), P. 835 - 835
Published: April 15, 2023
This
paper
presents
a
review
of
the
different
methods
and
techniques
used
to
optimize
ship
hulls
over
last
six
years
(2017–2022).
shows
percentages
reduction
in
resistance,
thus
fuel
consumption,
improve
ships’
energy
efficiency,
towards
achieving
goal
maritime
decarbonization.
Operational
research
machine
learning
are
common
decision
support
find
optimal
solution.
covers
four
areas
hulls,
including
hull
form,
structure,
cleaning
lubrication.
In
each
area
research,
several
computer
programs
used,
depending
on
study’s
complexity
objective.
It
has
been
found
that
no
specific
method
is
considered
optimum,
while
combination
can
achieve
more
accurate
results.
Most
work
focused
concept
stage
design,
operational
conditions
recently
taken
place,
an
improvement
efficiency.
The
finding
this
study
contributes
mapping
scientific
knowledge
technology
identifying
relevant
topic
areas,
recognizing
gaps
opportunities.
also
helps
present
holistic
approaches
future
supporting
realistic
solutions
sustainability.
Archives of Computational Methods in Engineering,
Journal Year:
2024,
Volume and Issue:
31(8), P. 4709 - 4737
Published: May 15, 2024
Abstract
This
scoping
review
assesses
the
current
use
of
simulation-based
design
optimization
(SBDO)
in
marine
engineering,
focusing
on
identifying
research
trends,
methodologies,
and
application
areas.
Analyzing
277
studies
from
Scopus
Web
Science,
finds
that
SBDO
is
predominantly
applied
to
optimizing
vessel
hulls,
including
both
surface
underwater
types,
extends
key
components
like
bows,
sterns,
propellers,
fins.
It
also
covers
structures
renewable
energy
systems.
A
notable
trend
preference
for
deterministic
single-objective
methods,
indicating
potential
growth
areas
multi-objective
stochastic
approaches.
The
points
out
necessity
integrating
more
comprehensive
multidisciplinary
methods
address
complex
challenges
environments.
Despite
extensive
there
remains
a
need
enhancing
methodologies’
efficiency
robustness.
offers
critical
overview
SBDO’s
role
engineering
highlights
opportunities
future
advance
field.
Applied Sciences,
Journal Year:
2022,
Volume and Issue:
12(5), P. 2428 - 2428
Published: Feb. 25, 2022
In
this
study,
the
hull
form
optimization
process
to
minimize
resistance
of
KCS
(KRISO
containership)
at
Fn=0.26
is
described.
The
bow
was
modified
by
varying
such
design
parameters
as
sectional
area
curve
(SAC),
section
shape,
bulb
breadth,
and
height
using
multiple
parametric
modification
curves
devised
authors.
performances
forms
were
analysed
viscous
flow
Reynolds-Averaged
Navier–Stokes
(RANS)
solver
WAVIS
ver.2.2.
With
a
view
saving
computational
time
during
iterative
analyses
in
process,
sinkage
trim
set
fixed
values
which
had
been
obtained
for
original
with
free
condition.
validity
constant
sinkage/trim
then
verified
conducting
analysis
optimal
Optimization
cost
function
total
coefficient
model
CTM
performed
sequential
quadratic
programming
(SQP),
one
gradient-based
local
methods.
Utilization
parallel
computing
led
simultaneous
calculation
gradient,
thereby
speeding
up
whole
process.
At
speed
24
knots,
yielded
reduction
1.8%,
extrapolated
3.1%
effective
power
PE
full
scale.
Journal of Marine Science and Engineering,
Journal Year:
2023,
Volume and Issue:
11(12), P. 2232 - 2232
Published: Nov. 25, 2023
The
paper
presents
the
use
of
a
supervised
active
learning
approach
for
solution
simulation-driven
design
optimization
(SDDO)
problem,
pertaining
to
resistance
reduction
destroyer-type
vessel
in
calm
water.
is
formulated
as
single-objective,
single-point
problem
with
both
geometrical
and
operational
constraints.
latter
also
considers
seakeeping
performance
at
multiple
conditions.
A
surrogate
model
used,
based
on
stochastic
radial
basis
functions
lower
confidence
bounding,
approach.
Furthermore,
multi-fidelity
formulation,
leveraging
unsteady
Reynolds-averaged
Navier–Stokes
equations
potential
flow
solvers,
used
order
reduce
computational
cost
SDDO
procedure.
Exploring
five-dimensional
space
free-form
deformation
under
limited
resources,
optimal
configuration
achieves
about
3%
escape
speed
6.4%
average
over
range.