Energies,
Journal Year:
2021,
Volume and Issue:
14(20), P. 6591 - 6591
Published: Oct. 13, 2021
In
this
article,
a
quasi-switched
boost
converter
based
on
the
switched-capacitor
technique
with
high
step-up
voltage
capability
is
dealt
and
analyzed.
The
proposed
offers
simple
structure
low
stress
semiconductor
elements
intrinsic
small
duty
cycle.
An
inductor
of
connected
in
series
input
source;
therefore,
continuous
current
ripple
attainable.
addition,
efficiency
also
improved.
A
detailed
steady-state
analysis
discussed
to
identify
salient
features
switched-capacitor-based
DC-DC
converter.
performance
compared
against
similar
existing
converters.
Finally,
investigated
by
experimental
verification.
Energies,
Journal Year:
2025,
Volume and Issue:
18(3), P. 657 - 657
Published: Jan. 31, 2025
This
study
presents
a
comprehensive
investigation
into
the
application
of
reservoir
simulation
and
machine
learning
techniques
to
improve
understanding
prediction
behavior,
focusing
on
Sarir
C-Main
field.
The
research
uses
various
data
sources
develop
robust
static
dynamic
models,
including
seismic
cubes,
well
logs,
base
maps,
check
shot
data,
production
history.
methodology
involves
quality
control,
log
interpretation,
horizon
surface
fault
gridding,
domain
conversion,
property
petrophysical
modeling,
completion,
fluid
model
definition,
rock
physics
functions.
History
matching
are
performed
using
cases,
such
as
gathering,
cleaning,
time
warping
(DTW),
long
short-term
memory
(LSTM),
transfer
applied.
results
obtained
through
Petrel
demonstrate
effectiveness
depletion
strategy,
history
matching,
completion
in
capturing
behavior.
Furthermore,
techniques,
specifically
DTW
LSTM,
exhibit
promising
predicting
oil
production.
concludes
that
approaches,
LSTM
model,
offer
distinct
advantages.
They
require
significantly
less
can
yield
reliable
predictions.
By
leveraging
power
learning,
accurate
predictions
be
achieved
efficiently
when
limited
available,
offering
more
streamlined
practical
alternative
traditional
methods.
Energies,
Journal Year:
2023,
Volume and Issue:
16(3), P. 1500 - 1500
Published: Feb. 2, 2023
Heat
dissipation
in
high-heat
flux
micro-devices
has
become
a
pressing
issue.
One
of
the
most
effective
methods
for
removing
high
heat
load
is
boiling
transfer
microchannels.
A
novel
approach
to
flow
pattern
and
recognition
microchannels
provided
by
combination
image
machine
learning
techniques.
The
support
vector
method
texture
characteristics
successfully
recognizes
patterns.
To
determine
bubble
dynamics
behavior
micro-device,
features
are
combined
with
algorithms
applied
As
result,
relationship
between
evolution
established,
mechanism
revealed.
Applied Soft Computing,
Journal Year:
2024,
Volume and Issue:
163, P. 111885 - 111885
Published: June 15, 2024
The
main
objective
of
this
paper
is
to
describe
a
methodology
that
was
developed
support
maintenance
decision-making
methods
based
on
equipment
condition.
Condition-Based
Maintenance
allows
increase
availability
and
maximize
investments.
This
mainly
due
the
prevention
unexpected
downtime.
By
avoiding
turning
on/off
industrial
equipment,
production
flows
are
more
efficient,
allowing
manufacturers
improve
quality
end-product.
industry
aims
correspond
satisfying
customer
expectations.
We
argue
in
adds
value
existing
literature,
namely
because
fact
it
possible
anticipate
state
an
without
large
amount
data.
In
other
words,
although
one
could
find
information
gaps
regarding
occurrence
failures,
accurately
assess
equipment.
approach
robust,
as
can
be
used
distinct
with
different
sensors,
making
generalizable
for
Maintenance.
presents
validation
preceding
through
case
study
drying
presses
industry.
To
do
so,
three
states
were
adopted,
namely:
"Proper
function";
"Alert
state";
"Equipment
failure".
follows
series
steps,
going
collection
values
from
vibration
imputation
using
Deep
Artificial
Neural
Networks
on-line
until
reaching
last
stage
classification
carried
out
by
Hidden
Markov
Model.
Through
optimized
observations
previous
define
hidden
Viterbi
algorithm,
which
corresponds
health
Additionally,
demonstrate
proposed
characterize
condition
data
obtained
generalized
types
