iScience,
Год журнала:
2024,
Номер
27(12), С. 111306 - 111306
Опубликована: Ноя. 5, 2024
As
rail
transit
continues
to
develop,
expanding
railway
networks
increase
the
demand
for
sustainable
energy
supply
and
intelligent
infrastructure
management.
In
recent
years,
advanced
self-powered
technology
has
rapidly
progressed
toward
artificial
intelligence
internet
of
things
(AIoT).
This
review
primarily
discusses
self-sensing
systems
in
transit,
analyzing
their
current
characteristics
innovative
potentials
different
scenarios.
Based
on
this
analysis,
we
further
explore
an
IoT
framework
supported
by
sensing
including
device
nodes,
network
communication,
platform
deployment.
Additionally,
technologies
about
cloud
computing
edge
deployed
enable
more
effective
utilization.
The
algorithms
such
as
machine
learning
(ML)
deep
(DL)
can
provide
comprehensive
monitoring,
management,
maintenance
environments.
Furthermore,
study
explores
research
other
cross-disciplinary
fields
investigate
potential
emerging
analyze
trends
future
development
transit.
Triboelectric
nanogenerators
(TENGs)
offer
a
convenient
means
to
convert
mechanical
energy
from
human
movement
into
electricity,
exhibiting
the
application
prospects
in
behavior
monitoring.
Nevertheless,
present
methods
improve
device
monitoring
effect
are
limited
design
of
triboelectric
material
level
(control
electron
gain
and
loss
ability).
As
compared
with
reported
work,
we
TENG-based
tactile
sensors
by
optimizing
structure
electrode/triboelectric
interface
multiple
strains
mechanism.
Cu@Ni
double-clad
waste
woven
fabrics
used
as
electrodes,
which
characterized
large
number
pores
formed
between
fibers,
greatly
increasing
specific
surface
area
electrode
generating
dynamic
strain
under
differentiated
stress
fields
because
their
different
elastic
modulus.
To
be
exact,
resin
layer
undergoes
deformation
0.64-4.47
kPa
external
new
generates
at
induced
slip
4.47-63.84
stress,
resulting
accumulation
charges
on
PDMS
surface.
The
establishment
further
facilitates
generation
distinct
signal
waveforms
that
easily
distinguishable
its
amplitude
peak
form.
Besides,
combined
deep
machine
learning
effect,
an
open
setting,
identification
accuracy
five
behaviors
approaches
100%.
This
provides
pathway
for
enhancing
sensor.
ACS Applied Materials & Interfaces,
Год журнала:
2025,
Номер
unknown
Опубликована: Март 12, 2025
With
the
increasing
development
of
metaverse
and
human-computer
interaction
(HMI)
technologies,
artificial
intelligence
(AI)
applications
in
virtual
reality
(VR)
environments
are
receiving
significant
attention.
This
study
presents
a
self-sensing
facial
recognition
mask
(FRM)
utilizing
triboelectric
nanogenerators
(TENG)
machine
learning
algorithms
to
enhance
user
immersion
interaction.
Various
TENG
negative
electrode
materials
evaluated
improve
sensor
performance,
efficacy
single
is
confirmed.
For
accurate
movement
emotion
detection,
different
assessed,
leading
selection
an
advanced
data
processing
method
with
two-layer
long
short-term
memory
model,
which
achieves
99.87%
accuracy.
The
practical
FRM
system
reality,
including
psychotherapy
HMI
scenarios,
validated
through
mathematical
models.
Additionally,
digital
twin-based
monitoring
platform
developed
using
5G,
database,
visualization
technologies
oversee
status.
Overall,
these
innovative
approaches
overcome
limitations
existing
face
environmental
interference
high
cost,
compared
other
technologies.
Triboelectric
nanogenerators
(TENGs)
are
emerging
as
transformative
technologies
for
sustainable
energy
harvesting
and
precision
sensing,
offering
eco-friendly
power
generation
from
mechanical
motion.
They
harness
while
enabling
self-sustaining
sensing
self-powered
devices.
However,
challenges
such
material
optimization,
fabrication
techniques,
design
strategies,
output
stability
must
be
addressed
to
fully
realize
their
practical
potential.
Artificial
intelligence
(AI),
with
its
capabilities
in
advanced
data
analysis,
pattern
recognition,
adaptive
responses,
is
revolutionizing
fields
like
healthcare,
industrial
automation,
smart
infrastructure.
When
integrated
TENGs,
AI
can
overcome
current
limitations
by
enhancing
output,
stability,
adaptability.
This
review
explores
the
synergistic
potential
of
AI-driven
TENG
systems,
optimizing
materials
embedding
machine
learning
deep
algorithms
intelligent
real-time
sensing.
These
advancements
enable
improved
harvesting,
predictive
maintenance,
dynamic
performance
making
TENGs
more
across
industries.
The
also
identifies
key
future
research
directions,
including
development
low-power
algorithms,
materials,
hybrid
robust
security
protocols
AI-enhanced
solutions.
