Entropy,
Journal Year:
2024,
Volume and Issue:
26(12), P. 1007 - 1007
Published: Nov. 22, 2024
A
convolutional
neural
network
can
extract
features
from
high-dimensional
data,
but
the
convolution
operation
has
a
high
time
complexity
and
requires
large
amount
of
computation.
For
equipment
with
sampling
frequency,
fault
diagnosis
methods
based
on
networks
cannot
meet
requirements
online
diagnosis.
To
solve
this
problem,
study
proposes
method
for
multi-source
heterogeneous
information
fusion
two-level
transfer
learning.
This
aims
to
fully
utilize
external
domain
construct
mechanism
fuse
information,
avoid
operations,
achieve
real-time
Its
main
work
is
build
feature
extraction
model
screenshots,
design
using
screenshots
deep
learning
one-dimensional
sequence
signals,
complete
network.
After
transfer,
not
only
integrates
characteristics
signals
also
avoids
operations
low
complexity.
The
effectiveness
proposed
verified
gearbox
dataset
bearing
dataset.
Foods,
Journal Year:
2025,
Volume and Issue:
14(2), P. 286 - 286
Published: Jan. 16, 2025
Tomato,
as
the
vegetable
queen,
is
cultivated
worldwide
due
to
its
rich
nutrient
content
and
unique
flavor.
Nondestructive
technology
provides
efficient
noninvasive
solutions
for
quality
assessment
of
tomatoes.
However,
processing
substantial
datasets
achieve
a
robust
model
enhance
detection
performance
nondestructive
great
challenge
until
deep
learning
developed.
The
aim
this
paper
provide
systematical
overview
principles
application
three
categories
techniques
based
on
mechanical
characterization,
electromagnetic
well
electrochemical
sensors.
Tomato
analyzed,
characteristics
different
are
compared.
Various
data
analysis
methods
explored
applications
in
tomato
using
with
also
summarized.
Limitations
future
expectations
industry
by
along
discussed.
ongoing
advancements
optical
equipment
lead
promising
outlook
agricultural
engineering.
Sensors,
Journal Year:
2025,
Volume and Issue:
25(3), P. 810 - 810
Published: Jan. 29, 2025
Fault
diagnosis
in
modern
industrial
and
information
systems
is
critical
for
ensuring
equipment
reliability
operational
safety,
but
traditional
methods
have
difficulty
effectively
capturing
spatiotemporal
dependencies
fault-sensitive
features
multi-sensor
data,
especially
rarely
considering
dynamic
between
data.
To
address
these
challenges,
this
study
proposes
DyGAT-FTNet,
a
novel
graph
neural
network
model
tailored
to
fault
detection.
The
dynamically
constructs
association
graphs
through
learnable
construction
mechanism,
enabling
automatic
adjacency
matrix
generation
based
on
time–frequency
derived
from
the
short-time
Fourier
transform
(STFT).
Additionally,
attention
(DyGAT)
enhances
extraction
of
by
assigning
node
weights.
pooling
layer
further
aggregates
optimizes
feature
representation.Experimental
evaluations
two
benchmark
detection
datasets,
XJTUSuprgear
dataset
SEU
dataset,
show
that
DyGAT-FTNet
significantly
outperformed
existing
classification
accuracy,
with
accuracies
1.0000
0.9995,
respectively,
highlighting
its
potential
practical
applications.
Sensors,
Journal Year:
2025,
Volume and Issue:
25(6), P. 1716 - 1716
Published: March 10, 2025
Manipulator
robots
hold
significant
importance
for
the
development
of
intelligent
manufacturing
and
industrial
transformation.
Manufacturers
users
are
increasingly
focusing
on
fault
diagnosis
manipulator
robots.
The
voltage,
current,
speed,
torque,
vibration
signals
often
used
to
explore
characteristics
from
a
frequency
perspective,
temperature
sound
also
represent
information
different
perspectives.
Technically,
robot
involving
human
intervention
is
gradually
being
replaced
by
new
technologies,
such
as
expert
experience,
artificial
intelligence,
digital
twin
methods.
Previous
reviews
have
tended
focus
single
type
fault,
analysis
reducers
or
joint
bearings,
which
has
led
lack
comprehensive
summary
various
methods
diagnosis.
Considering
needs
future
research,
review
types
diagnostic
provides
readers
with
clearer
reading
experience
reveals
potential
challenges
opportunities.
Such
helps
researchers
entering
field
avoid
duplicating
past
work
overview,
guiding
encouraging
commit
enhancing
effectiveness
practicality
technologies.
