Structural Health Monitoring,
Journal Year:
2024,
Volume and Issue:
unknown
Published: Nov. 25, 2024
Intelligent
fault
diagnosis
based
on
multisensor
data
fusion
techniques
and
two-dimensional
convolutional
neural
network
(CNN)
has
been
widely
developed
achieved
numerous
excellent
results.
Existing
studies
usually
develop
multi-input
models
to
facilitate
fusion,
lacking
schemes
for
realizing
the
in
process
of
data-to-image.
Traditional
methods
that
convert
signals
grayscale
maps
concatenate
them
into
RGB
images
lose
temporal
correlation
are
susceptible
interference.
Besides,
few
integrated
favorable
features
at
different
stages
CNN
diagnosis,
which
limits
diagnostic
performance.
To
this
end,
article
proposes
a
multisource
signal-to-image
method
called
multidimensional
distance
matrix
(MDM)
multi-scale
adaptive
feature
(MAFFCNN).
First,
MDM
emphasize
interrelationships
between
points
moments
time
series
preserve
correlation.
Then,
conv
block
MAFFCNN
can
extract
scales
image,
its
attention
branch
better
aggregate
location
information.
Also,
introduces
efficient
cross-spatial
learning
generate
learnable
weights
importance
achieve
fusion.
Finally,
above
is
validated
using
established
gear
dataset
public
bearing
dataset.
The
experimental
results
demonstrate
effectiveness
proposed
their
robustness
complex
environments.
Machines,
Journal Year:
2025,
Volume and Issue:
13(2), P. 125 - 125
Published: Feb. 7, 2025
Power
transformers
(PTs)
play
a
vital
role
in
the
electrical
power
system.
Assessing
their
health
to
predict
remaining
useful
life
is
essential
optimise
maintenance.
Scheduling
right
maintenance
for
equipment
at
time
ultimate
goal
of
any
system
utility.
Optimal
has
number
benefits:
human
and
social,
by
limiting
sudden
service
interruptions,
economic,
due
direct
indirect
costs
unscheduled
downtime.
PT
now
produces
large
amounts
easily
accessible
data
increasing
use
IoT,
sensors,
connectivity
between
physical
assets.
As
result,
transformer
prognostics
management
(PT-PHM)
methods
are
increasingly
moving
towards
artificial
intelligence
(AI)
techniques,
with
several
hundreds
scientific
papers
published
on
topic
PT-PHM
using
AI
techniques.
On
other
hand,
world
undergoing
new
evolution
third
generation
models:
large-scale
foundation
models.
What
current
state
research
PT-PHM?
trends
challenges
where
do
we
need
go
management?
This
paper
provides
comprehensive
review
art
analysing
more
than
200
papers,
mostly
journals.
Some
elements
guide
given
end
document.
Sensors,
Journal Year:
2025,
Volume and Issue:
25(4), P. 1189 - 1189
Published: Feb. 15, 2025
Intelligent
fault
diagnosis
(IFD)
for
mechanical
equipment
based
on
small
and
imbalanced
datasets
has
been
widely
studied
in
recent
years,
with
transfer
learning
emerging
as
one
of
the
most
promising
approaches.
Existing
learning-based
IFD
methods
typically
use
data
from
different
operating
conditions
same
source
target
domains
process.
However,
practice,
it
is
often
challenging
to
find
identical
obtain
domain
when
diagnosing
faults
equipment.
These
strict
assumptions
pose
significant
limitations
application
techniques
real-world
industrial
settings.
Furthermore,
temporal
characteristics
time-series
monitoring
are
inadequately
considered
existing
methods.
In
this
paper,
we
propose
a
cross-machine
method
residual
full
convolutional
neural
network
(ResFCN)
model,
which
leverages
features
data.
By
incorporating
sliding
window
(SW)-based
segmentation,
pretraining,
model
fine-tuning,
proposed
effectively
exploits
fault-associated
general
learns
domain-specific
patterns
that
better
align
domain,
ultimately
achieving
accurate
We
design
implement
three
sets
experiments
using
two
used
public
datasets.
The
results
demonstrate
outperforms
approaches
terms
accuracy
robustness.
