Sensors,
Journal Year:
2025,
Volume and Issue:
25(8), P. 2625 - 2625
Published: April 21, 2025
This
paper
focuses
on
the
application
of
digital
twins
in
field
electric
motor
fault
diagnosis.
Firstly,
it
explains
origin,
concept,
key
technology
and
areas
twins,
compares
analyzes
advantages
disadvantages
twin
traditional
methods
diagnosis,
discusses
depth
including
data
acquisition
processing,
modeling,
analysis
mining,
visualization
technology,
etc.,
enumerates
examples
fields
induction
motors,
permanent
magnet
synchronous
wind
turbines
other
fields.
A
concept
multi-phase
generator
diagnosis
based
is
given,
challenges
future
development
directions
are
discussed.
Reliability Engineering & System Safety,
Journal Year:
2024,
Volume and Issue:
246, P. 110040 - 110040
Published: Feb. 25, 2024
Digital
twins
(DTs)
represent
an
emerging
technology
that
is
currently
leveraging
the
monitoring
of
complex
systems,
implementation
autonomous
control
and
assistance
during
accidents
emergencies
in
real
time.
However,
aspects
such
as
safety,
cybersecurity
reliability
DTs
are
still
open
issues
have
not
been
comprehensively
addressed.
These
can
offer
new
insights
to
evaluate
risk
return
obtained
from
DTs.
This
paper
presents
a
systematic
literature
review
focused
on
their
use
safety
analysis,
assessment
emergency
management.
The
aim
this
work
twofold:
(i)
point
at
latest
advancements
by
presenting
catalog
expected
functions
twinning
enabling
technologies
application
domains
interest;
(ii)
limitations
pending
challenges
for
Internet of Things,
Journal Year:
2024,
Volume and Issue:
25, P. 101094 - 101094
Published: Jan. 29, 2024
As
Industry
4.0
enablers,
digital
twins
of
manufacturing
systems
have
led
to
multiple
interaction
levels
among
processes,
systems,
and
workers
across
the
factory.
However,
open
issues
still
exist
when
addressing
cyber–physical
convergence
in
traditional
small
medium-sized
enterprises.
The
problem
for
both
operators
existing
infrastructure
is
how
adapt
knowledge
increasing
business
needs
plants
that
demand
high
efficiency,
while
reducing
production
costs.
In
this
paper,
a
framework
implements
novel
concept
Digital
Twin
Learning
Ecosystem
presented.
objective
facilitate
integration
human-machine
different
industrial
contexts
eliminate
technological
workforce
barriers.
This
adaptive
approach
particularly
important
meeting
requirements
help
enterprises
build
their
own
interconnected
Ecosystem.
contribution
work
lies
single
twin
learning
scenarios
can
from
scratch
using
light
infrastructure,
reusing
common
condition-based
methods
well-known
by
skilled
rapidly
flexibly
integrate
legacy
resources
non-intrusive
manner.
solution
was
tested
real
data
milling
machine
currently
operating
induction
furnace
with
maximum
power
12
MW
foundry
plant.
cases,
proposed
proved
its
benefits:
first,
providing
augmented
maintenance
operations
on
second,
improving
efficiency
approximately
9
percent.
Nondestructive Testing And Evaluation,
Journal Year:
2025,
Volume and Issue:
unknown, P. 1 - 29
Published: Jan. 8, 2025
Milling
tools
are
critical
to
machining
and
manufacturing
processes.
Accurate
diagnosis
identification
of
faults
occurring
in
milling
during
their
operation
utmost
importance
for
maintaining
the
reliability
availability
these
tools,
minimise
machine
downtime
overall
costs.
This
paper
presents
a
fault
network
model
based
on
acoustic
emission
signals.
The
integrates
multilayer
wavelet
CNN
(MWN)
consisting
discrete
transform
(DWT)
convolutional
neural
(CNN),
block
attention
module
(CBAM),
PatchTST
module.
MWN
uses
transformation
withdraw
multi-scale
features
from
signals,
thus
improving
sensitivity
small
variations
emission.
CBAM
improves
feature
representation
by
focusing
channels
regions,
while
self-attention
mechanism
optimise
processing
long-range
dependencies.
synergy
mechanisms
results
superior
performance,
outperforming
traditional
diagnostic
methods.
Bayesian
optimisation
is
used
select
hyperparameters,
eliminating
subjective
bias
associated
with
manual
range
setting.
Validation
experiments
using
dataset,
including
ablation
studies
comparative
tests,
demonstrated
that
achieves
an
accuracy
over
98%,
validating
its
generalisation
capability
effectiveness
diagnosing
tool
Measurement Science and Technology,
Journal Year:
2023,
Volume and Issue:
35(2), P. 022003 - 022003
Published: Nov. 23, 2023
Abstract
Health
monitoring
in
rotatory
machinery
is
a
process
of
developing
mechanism
to
determine
its
state
deterioration.
It
involves
analysing
the
presence
damage,
locating
fault,
determining
severity
problem,
and
calculating
amount
time
that
machine
can
still
be
used
effectively
by
making
use
signal
processing
methods.
The
journey
started
repair
when
fails
progressed
modern
era,
which
advanced
sensors
capture
data
conduct
on-line
methods
extract
relevant
features.
By
seamlessly
integrating
smart
sensing,
collection,
intelligent
algorithms,
technologies
have
transformed
landscape
condition-based
maintenance
for
rotary
machinery,
bridging
gap
between
fundamental
understanding
practical
engineering
applications.
In
this
review
paper,
first,
roadmap
(CBM)
briefly
introduced.
Then,
CBM
task
techniques
are
reviewed
context
manual
identification
defects,
applying
artificial
intelligence
(AI)
model
identify
defect
AI
carry
out
prognosis
remaining
useful
life.
Finally,
challenges,
issues
detect
faults
remedies
overcome
such
challenges
deeply
discussed
future
research
directions
identified
ensure
safe
operation
machinery.
Symmetry,
Journal Year:
2024,
Volume and Issue:
16(4), P. 455 - 455
Published: April 8, 2024
As
industrial
processes
grow
increasingly
complex,
fault
identification
becomes
challenging,
and
even
minor
errors
can
significantly
impact
both
productivity
system
safety.
Fault
detection
diagnosis
(FDD)
has
emerged
as
a
crucial
strategy
for
maintaining
reliability
safety
through
condition
monitoring
abnormality
recovery
to
manage
this
challenge.
Statistical-based
FDD
methods
that
rely
on
large-scale
process
data
their
features
have
been
developed
detecting
faults.
This
paper
overviews
recent
investigations
developments
in
statistical-based
methods,
focusing
probabilistic
models.
The
theoretical
background
of
these
models
is
presented,
including
Bayesian
learning
maximum
likelihood.
We
then
discuss
various
techniques
methodologies,
e.g.,
principal
component
analysis
(PPCA),
partial
least
squares
(PPLS),
independent
(PICA),
canonical
correlation
(PCCA),
Fisher
discriminant
(PFDA).
Several
test
statistics
are
analyzed
evaluate
the
discussed
methods.
In
processes,
require
complex
matrix
operation
cost
computational
load.
Finally,
we
current
challenges
future
trends
FDD.
