This
paper
investigates
the
key
techniques
and
model
design
for
autonomous
driving
scene
generalization.
Addressing
challenge
of
adapting
generalization
parameters
to
distribution
functions,
we
employ
various
functions
such
as
normal,
uniform,
exponential,
log-normal,
Weibull
distributions.
By
utilizing
Monte
Carlo
random
sampling,
generate
generalized
conforming
specific
Based
on
generated
parameters,
use
scenario
generation
library
data
with
uncertainty.
The
is
validated
through
simulation
using
ESmini
platform,
demonstrating
high
levels
realism.
Future
research
directions
include
expanding
selection
optimizing
processes
enhance
performance
adaptability
IEEE Sensors Journal,
Journal Year:
2023,
Volume and Issue:
23(21), P. 26269 - 26278
Published: Sept. 22, 2023
Industrial
equipment
failure
diagnosis
is
a
crucial
issue
that
impacts
the
national
industrial
manufacturing
level,
economic
cycle
development,
and
sustainable
technological
advancement.
A
multimodal
knowledge
graph
(MMKG)-based
intelligent
diagnostic
model
for
fault
proposed
to
address
issues
of
insufficient
inadequate
data
samples
encountered
when
using
single-mode
in
existing
equipment.
This
does
not
require
extensive
learning
complex
scenarios.
The
utilizes
an
improved
faster
region
with
CNN
(Faster
RCNN)
features
object
detection
module
extract
visual
information
feature
vectors
semiordered
main
nonmain
objects.
These
are
then
mapped
entity,
attribute,
relationship
cosine
similarity
correspondence
mapping.
semantic
matching
inference
performed
based
on
this
mapping,
resulting
set
triplets.
Finally,
bidirectional
autoregressive
transformers
(BARTs)
text
generation
processes
triplet
generate
texts.
Experimental
results
demonstrate
Faster
RCNN
achieves
1.2%
increase
confidence
trained
small
training
datasets.
accuracy
generated
description
texts
reaches
approximately
98%
compared
standard
presented
article
addresses
challenge
diagnosing
faults
equipment,
particularly
scenarios
limited
data,
such
as
substations.
It
enhances
target
effectively
even
scarce.
Additionally,
it
MMKG
enable
interpretable
decision-making.
Expert Systems,
Journal Year:
2024,
Volume and Issue:
41(11)
Published: July 30, 2024
Abstract
Class
imbalance
and
class
overlap
create
difficulties
in
the
training
phase
of
standard
machine
learning
algorithm.
Its
performance
is
not
well
minority
classes,
especially
when
there
a
high
significant
overlap.
Recently
it
has
been
observed
by
researchers
that,
joint
effects
are
more
harmful
as
compared
to
their
direct
impact.
To
handle
these
problems,
many
methods
have
proposed
past
years
that
can
be
broadly
categorized
data‐level,
algorithm‐level,
ensemble
learning,
hybrid
methods.
Existing
data‐level
often
suffer
from
problems
like
information
loss
overfitting.
overcome
we
introduce
novel
entropy‐based
sampling
(EHS)
method
highly
imbalanced
datasets.
The
EHS
eliminates
less
informative
majority
instances
region
during
undersampling
regenerates
synthetic
oversampling
near
borderline.
achieved
improvement
F1‐score,
G‐mean,
AUC
metrics
value
DT,
NB,
SVM
classifiers
well‐established
state‐of‐the‐art
Classifiers
performances
tested
on
28
datasets
with
extreme
ranges
Applied Sciences,
Journal Year:
2023,
Volume and Issue:
13(7), P. 4308 - 4308
Published: March 28, 2023
Pumps,
as
core
pieces
of
equipment
in
ships,
are
installed
the
engine
room
to
supply
refined
oil
engine.
Pump
failure
causes
critical
problems
for
ship
operations.
Therefore,
failure-monitoring-based
diagnosis
technology
is
an
essential
requirement
shipbuilding
industry.
For
this
purpose,
a
database
containing
information
about
states
depending
on
main
cause
cases
pump
needs
be
developed.
In
present
study,
pumps
based
actual
accident
records
were
quantitatively
analyzed.
Then,
modes
bearing,
coupling,
sealing,
and
screw,
which
parts
pump,
determined.
Test
infrastructures
developed
obtain
normal
abnormal
data
considering
diverse
operating
conditions.
Based
vibration
from
accelerometer
test
infrastructures,
frequency
was
analyzed
through
Fast
Fourier
Transform
(FFT).
addition,
more
precise
results
obtained
by
performing
Short-Time
(STFT)
FFT
that
indicated
severe
failure.
Finally,
over
200
entries
accumulated
well
The
constructed
study
expected
help
investigating
prediction
algorithm
models
management.
Measurement Science and Technology,
Journal Year:
2024,
Volume and Issue:
35(9), P. 096108 - 096108
Published: May 30, 2024
Abstract
In
practical
engineering
applications,
the
accuracy
and
stability
of
fault
identification
for
centrifugal
pump
will
be
significantly
reduced
due
to
unbalanced
distribution
between
normal
datasets,
i.e.,
number
working
samples
is
far
more
than
samples.
To
alleviate
this
bottleneck
issue,
paper
explores
based
on
Wasserstein
generative
adversarial
network
with
gradient
penalty
(WGAN-GP)
through
combining
kinematics
simulation
experimental
case.
Specifically,
ideal
vibration
datasets
from
failure
patterns
such
as
damaged
impeller
are
simulated
collected
by
prototype
ADAMS
software,
then
signals
transformed
into
2D
grey-scale
images.
Furtherly,
generated
image
feed
original
dataset
new
training
when
Nash
equilibrium
WGAN-GP
model
reached.
Eventually,
identified
using
confusion
matrix
graph.
Meanwhile,
another
public
employed
verifying
model.
Results
indicate
that
accuracies
95.07%
98.0%
both
case
obtained,
respectively,
issues
insufficient
can
overcome
effectively.
