Applied Sciences,
Год журнала:
2021,
Номер
11(19), С. 9095 - 9095
Опубликована: Сен. 29, 2021
A
rolling
element
signal
has
a
long
transmission
path
in
the
acquisition
process.
The
fault
feature
of
is
more
difficult
to
be
extracted.
Therefore,
novel
weak
extraction
method
using
optimized
variational
mode
decomposition
with
kurtosis
mean
(KMVMD)
and
maximum
correlated
deconvolution
based
on
power
spectrum
entropy
grid
search
(PGMCKD),
namely
KMVMD-PGMCKD,
proposed.
In
proposed
KMVMD-PGMCKD
method,
VMD
Then
an
adaptive
parameter
selection
for
MCKD,
PGMCKD,
determine
period
T
filter
order
L.
complementary
advantages
KMVMD
PGMCKD
are
integrated
construct
model
(KMVMD-PGMCKD).
Finally,
employed
deal
obtained
by
effectively
implement
extraction.
Bearing
signals
Case
Western
Reserve
University
actual
data
selected
prove
validity
KMVMD-PGMCKD.
experiment
results
show
that
can
extract
features
bearing
elements
accurately
diagnose
faults
under
variable
working
conditions.
Computational Intelligence and Neuroscience,
Год журнала:
2022,
Номер
2022, С. 1 - 10
Опубликована: Янв. 21, 2022
In
order
to
improve
the
teaching
efficiency
of
English
teachers
in
classroom
teaching,
target
detection
algorithm
deep
learning
and
monitoring
information
from
are
used,
Single
Shot
MultiBox
Detector
(SSD)
is
optimized,
optimized
Mobilenet-Single
(Mobilenet-SSD)
designed.
After
analyzing
Mobilenet-SSD
algorithm,
it
recognized
that
has
shortcomings
large
amount
basic
network
parameters
poor
small
detection.
The
deficiencies
following
partThrough
related
experiments
student
behaviour
analysis,
average
accuracy
reached
82.13%,
speed
23.5
fps
(frames
per
second).
Through
experiments,
achieved
81.11%
detecting
students’
writing
behaviour.
This
proves
proposed
improved
recognition
without
changing
operation
traditional
algorithm.
designed
more
advantages
compared
with
previous
algorithms.
improves
which
beneficial
provide
modern
technical
support
for
understand
status
students
strong
practical
significance
improving
teaching.
Applied Sciences,
Год журнала:
2022,
Номер
12(11), С. 5604 - 5604
Опубликована: Май 31, 2022
For
the
uncertainty
caused
by
time-varying
modeling
parameters
with
sailing
speed
in
course
control
of
underactuated
ships,
a
novel
identification
method
based
on
an
adaptive
neural
fuzzy
model
(ANFM)
is
proposed
to
approximate
inverse
dynamic
characteristics
ship
this
paper.
This
adjusts
both
its
own
structure
and
as
it
learns,
able
automatically
partition
input
space,
determine
number
membership
functions
rules.
The
trained
ANFM
used
controller,
parallel
fractional-order
PIλDμ
controller
for
ships.
Meanwhile,
sine
wave
curve
sawtooth
are
considered
learning
samples
ANFM,
respectively,
dynamics
simulation
experiments
carried
out.
Two
different
structures
obtained,
which
connected
respectively
ship.
results
show
that
can
effectively
overcome
influence
parameters,
track
desired
quickly
effectively,
has
good
effect.
Finally,
comparative
four
controllers
out,
FO
using
advantages
small
overshoot,
short
adjustment
time,
precise
control.
Discrete Dynamics in Nature and Society,
Год журнала:
2022,
Номер
2022(1)
Опубликована: Янв. 1, 2022
This
paper
provides
an
in‐depth
analysis
and
study
of
the
spatial
effects
financial
support
economic
growth
with
help
nonlinear
generalized
complex
systems.
Taking
industrial
sector
as
research
object
combining
relevant
contents
neoclassical
investment
theory,
information
economics,
institutional
this
clearly
defines
argues
that
main
feature
current
policy
is
constraint
rather
than
inhibition
based
on
understanding
theoretical
connotation
rationality
and,
a
premise,
further
analyzes
causing
excessive
capital
mismatch
in
corporate
sector.
It
mechanism
role
policies
overinvestment
conducts
empirical
tests
from
three
perspectives
measuring
efficiency,
output
efficiency
investment,
allocation
industry
capital,
behavior
microenterprises,
finally
puts
forward
recommendations
conjunction
evaluation
policies.
selects
dimensions
system,
namely,
structure,
scale,
studies
adaptability
between
these
development
real
economy,
respectively,
then
uses
different
methods
to
analyze
dynamic
economy
system
explores
way
economy.
medium
micro
basis
new
evidence
for
importance
reform
also
opens
up
space
exploring
exit
path
constraints
using
interest
rate
marketization
general
grip
reasonably
guide
resources
achieve
transformation
upgrading
sustainable
healthy
through
supporting
high‐quality
more
interprovincial
level
data
analysis,
so
it
comprehensive
detailed
previous
scholars’
studies.
The
examination
Computational Intelligence and Neuroscience,
Год журнала:
2021,
Номер
2021(1)
Опубликована: Янв. 1, 2021
With
the
advent
of
era
economic
globalization,
world
capital
market
is
also
facing
financial
risks.
It
necessary
to
have
a
corresponding
management
early
warning
model
reduce
losses.
This
paper
uses
combination
ant
colony
algorithm
and
neural
network
build
improved
by
model.
By
setting
relevant
assumptions,
statements
annual
report
texts
are
predicted
analyzed
compared
with
original
static
data
forecasting
Compared
traditional
methods,
time
series
sequencing
analysis
used
in
this
makes
result
prediction
more
accurate.
allows
one
year’s
be
predict
for
next
two
years.
research
can
provide
reference
optimization
system.
Applied Sciences,
Год журнала:
2021,
Номер
11(19), С. 9095 - 9095
Опубликована: Сен. 29, 2021
A
rolling
element
signal
has
a
long
transmission
path
in
the
acquisition
process.
The
fault
feature
of
is
more
difficult
to
be
extracted.
Therefore,
novel
weak
extraction
method
using
optimized
variational
mode
decomposition
with
kurtosis
mean
(KMVMD)
and
maximum
correlated
deconvolution
based
on
power
spectrum
entropy
grid
search
(PGMCKD),
namely
KMVMD-PGMCKD,
proposed.
In
proposed
KMVMD-PGMCKD
method,
VMD
Then
an
adaptive
parameter
selection
for
MCKD,
PGMCKD,
determine
period
T
filter
order
L.
complementary
advantages
KMVMD
PGMCKD
are
integrated
construct
model
(KMVMD-PGMCKD).
Finally,
employed
deal
obtained
by
effectively
implement
extraction.
Bearing
signals
Case
Western
Reserve
University
actual
data
selected
prove
validity
KMVMD-PGMCKD.
experiment
results
show
that
can
extract
features
bearing
elements
accurately
diagnose
faults
under
variable
working
conditions.