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.
Sensors,
Journal Year:
2025,
Volume and Issue:
25(3), P. 913 - 913
Published: Feb. 3, 2025
Wind
turbine
gearbox
fault
diagnosis
is
critical
to
guarantee
working
efficiency
and
operational
safety.
However,
the
current
diagnostic
methods
face
enormous
restrictions
in
handling
nonlinear
noise
signals
intricate
compound
patterns.
Herein,
a
method
based
on
modified
signal
quality
coefficient
(MSQC)
versatile
residual
shrinkage
network
(VRSN)
proposed
resolve
these
issues.
In
detail,
MSQC
designed
remove
components
irrelevant
wind
operation
status,
it
has
ability
balance
denoised
effect
fidelity.
The
VRSN
constructed
for
diagnosis,
consists
of
two
heterogeneous
networks.
former
count
number
faults,
latter
adopted
identify
single
or
pattern.
Finally,
self-built
test
rig
verify
method’s
effectiveness.
results
demonstrate
that
competitive
terms
accuracy.
International Journal of Aeroacoustics,
Journal Year:
2025,
Volume and Issue:
unknown
Published: March 17, 2025
High-speed
on/off
valve
(HSV)
generates
noise
and
vibration
due
to
high-frequency
collisions
between
internal
components
fluid
pressure
impacts.
In
order
reveal
the
principle
characteristics
of
HSV
generation,
this
study
establishes
transient
acoustic
field
model
in
motion
by
considering
coupling
effects
electromagnetic
force,
spring
force.
First,
excitation
force
with
spool
displacement
are
analyzed.
Second,
under
analyzed,
most
intense
part
is
identified.
Finally,
sound
modeled
using
response
as
a
boundary
condition,
This
characteristic
can
provide
an
indirect
measure
displacement.
The
experimental
results
show
that
difference
simulation
experiment
less
than
3%.
Sensors,
Journal Year:
2025,
Volume and Issue:
25(6), P. 1851 - 1851
Published: March 17, 2025
With
the
improvement
in
industrial
equipment
intelligence
and
reliability
requirements,
bearing
fault
diagnosis
has
become
a
key
technology
to
ensure
stable
operation
of
mechanical
equipment.
Traditional
methods
are
ineffective
diagnosing
complex
faults
mostly
rely
on
manual
adjustment
hyperparameters.
To
this
end,
paper
proposes
domain
adversarial
migratory
learning
model
incorporating
structural
modules.
First,
pre-trained
source
is
applied
target
dataset
through
an
adaptation
technique.
Then,
network
depth
width
dynamically
adjusted
Optuna
optimization
framework
accommodate
more
types
domain.
Finally,
performance
further
improved
by
automatically
optimizing
The
experimental
results
show
that
exhibits
high
accuracy
different
types,
especially
face
variable
environments,
demonstrating
strong
adaptability
robustness.
method
provides
effective
solution
for
intelligent
devices.
Journal of Computational Design and Engineering,
Journal Year:
2024,
Volume and Issue:
11(5), P. 99 - 124
Published: Aug. 31, 2024
Abstract
In
the
field
of
industrial
production,
machine
failures
not
only
negatively
affect
productivity
and
product
quality,
but
also
lead
to
safety
accidents,
so
it
is
crucial
accurately
diagnose
in
time
take
appropriate
measures.
However,
machines
cannot
operate
with
faults
for
extended
periods,
diversity
fault
modes
results
limited
data
collection,
posing
challenges
building
accurate
prediction
models.
Despite
recent
advancements,
intelligent
diagnosis
methods
based
on
traditional
sampling
learning
have
shown
notable
progress.
Nonetheless,
these
heavily
rely
human
expertise,
making
challenging
extract
comprehensive
feature
information.
To
address
challenges,
numerous
imbalance
generative
adversarial
networks
(GANs)
emerged,
GANs
can
generate
realistic
samples
that
conform
distribution
original
data,
showing
promising
diagnosing
imbalances
critical
components
such
as
bearings
gears,
despite
their
great
potential,
GAN
face
including
difficulties
training
generating
abnormal
samples.
whether
GAN-based
resampling
technology
or
technology,
there
are
fewer
reviews
noise-containing
imbalance,
intra-
inter-class
dual
multi-class
series
other
problems
small
samples,
a
lack
more
summary
solutions
above
problems.
Therefore,
purpose
this
paper
deeply
explore
under
various
failure
modes,
review
analyze
research
basis.
By
suggesting
future
directions,
aims
provide
guidance
reference
production
maintenance.
