Engineering Research Express,
Journal Year:
2024,
Volume and Issue:
6(4), P. 045205 - 045205
Published: Sept. 24, 2024
Abstract
To
solve
the
problem
of
difficulty
in
extracting
and
identifying
fault
types
during
turbine
rotor
operation,
a
diagnosis
method
based
on
improved
subtraction
mean
optimizer
(NGSABO)
algorithm
to
optimize
variational
mode
decomposition
(VMD)
CNN-BiLSTM
neural
network
is
proposed.
Firstly,
three
improvements
are
made
average
algorithm.
Secondly,
optimal
VMD
parameter
combination
NGSABO
adaptive
selection
number
K
penalty
factor
α
used
decompose
signal,
minimum
sample
entropy
as
fitness
function
for
feature
extraction.
Combining
convolutional
bidirectional
long
short-term
memory
identify
classify
features.
Compared
with
other
methods,
this
has
outstanding
performance
single
coupled
faults.
The
accuracy
reaches
98.5714%,
which
good
practical
application
value.
Journal of Marine Science and Engineering,
Journal Year:
2024,
Volume and Issue:
12(9), P. 1589 - 1589
Published: Sept. 8, 2024
The
dual-input
single-output
(DI-SO)
cylindrical
spur
gear
system
possesses
advantages
such
as
high
load-carrying
capacity,
precise
transmission,
and
low
energy
loss.
It
is
increasingly
becoming
a
core
component
of
power
transmission
systems
in
maritime
vessels,
aerospace,
marine
engineering,
construction
machinery.
In
practical
operation,
the
stability
DI-SO
influenced
by
complex
excitations.
These
excitations
lead
to
nonlinear
vibration,
meshing
instability,
noise,
which
affect
performance
reliability
entire
equipment.
Hence,
dynamic
thoroughly
investigated
this
research.
impact
factors
on
characteristics
was
comprehensively.
A
comparative
analysis
conducted
establishing
bending–torsional
coupling
vibration
model
under
synchronous
asynchronous
conditions.
Nonlinear
periodic
time-varying
stiffness,
damping,
friction
coefficient,
arms,
load
sharing
ratio,
comprehensive
error,
backlash
were
considered
proposed
model.
Then,
effect
laws
frequency,
driving
fluctuation,
backlash,
error
analyzed.
results
indicate
that
exhibited
staged
stable
unstable
states
different
frequencies
At
medium-frequency
stage
(0.96
×
104~1.78
104
Hz),
alternating
phenomena
multi-periodic,
quasi-periodic,
chaotic
motion
observed.
Moreover,
root
mean
square
value
(RMS)
(DTE)
asynchronized
generally
higher
than
synchronized
system.
found
selecting
appropriate
condition
could
effectively
reduce
amplitude
DTE.
Additionally,
be
significantly
improved
adjusting
control
parameters
fluctuation
(0~179
N),
(0.8
10−4~0.9
10−4
m),
(7.9
10−4~9.4
m).
research
provide
theoretical
guidance
for
design
optimization
Applied Sciences,
Journal Year:
2024,
Volume and Issue:
14(18), P. 8229 - 8229
Published: Sept. 12, 2024
This
paper
combines
self-organizing
mapping
(SOM)
and
a
long
short-term
memory
network
(SOM-LSTM)
to
construct
an
audio-based
motor-fault
diagnosis
system
for
identifying
the
operating
states
of
rotary
motor.
first
uses
audio
signal
collector
measure
motor
sound
data,
fast
Fourier
transform
(FFT)
convert
actual
measured
sound–time-domain
into
frequency-domain
signal,
normalizes
calibrates
ensure
consistency
accuracy
signal.
Secondly,
SOM
is
used
further
analyze
characterized
waveforms
in
order
reveal
intrinsic
structure
pattern
data.
The
LSTM
process
secondary
data
generated
via
SOM.
Dimensional
aggregation
prediction
sequence
long-term
dependencies
accurately
identify
different
possible
abnormal
patterns.
also
experimental
design
Taguchi
method
optimize
parameters
SOM-LSTM
increase
execution
efficiency
fault
diagnosis.
Finally,
applied
real-time
monitoring
operation,
work
type
performed,
tests
under
loads
environments
are
attempted
evaluate
its
feasibility.
completion
this
provides
diagnostic
strategy
that
can
be
followed
when
it
comes
faults.
Through
system,
conditions
equipment
detected,
which
help
with
preventive
maintenance,
make
more
efficient
save
lot
time
costs,
improve
industry’s
ability
monitor
operation
information.
Engineering Research Express,
Journal Year:
2024,
Volume and Issue:
6(4), P. 045205 - 045205
Published: Sept. 24, 2024
Abstract
To
solve
the
problem
of
difficulty
in
extracting
and
identifying
fault
types
during
turbine
rotor
operation,
a
diagnosis
method
based
on
improved
subtraction
mean
optimizer
(NGSABO)
algorithm
to
optimize
variational
mode
decomposition
(VMD)
CNN-BiLSTM
neural
network
is
proposed.
Firstly,
three
improvements
are
made
average
algorithm.
Secondly,
optimal
VMD
parameter
combination
NGSABO
adaptive
selection
number
K
penalty
factor
α
used
decompose
signal,
minimum
sample
entropy
as
fitness
function
for
feature
extraction.
Combining
convolutional
bidirectional
long
short-term
memory
identify
classify
features.
Compared
with
other
methods,
this
has
outstanding
performance
single
coupled
faults.
The
accuracy
reaches
98.5714%,
which
good
practical
application
value.
