Remaining Useful Life Prediction of Lithium-Ion Batteries Based on Neural Network and Adaptive Unscented Kalman Filter
Electronics,
Год журнала:
2024,
Номер
13(13), С. 2619 - 2619
Опубликована: Июль 4, 2024
Accurate
prediction
of
remaining
useful
life
(RUL)
plays
an
important
role
in
maintaining
the
safe
and
stable
operation
Lithium-ion
battery
management
systems.
Aiming
at
problem
poor
stability
a
single
model,
this
paper
combines
advantages
data-driven
model-based
methods
proposes
RUL
method
combining
convolutional
neural
network
(CNN),
bi-directional
long
short-term
memory
(Bi-LSTM),
SE
attention
mechanism
(AM)
adaptive
unscented
Kalman
filter
(AUKF).
First,
three
types
indirect
features
that
are
highly
correlated
with
decay
selected
as
inputs
to
model
improve
accuracy
prediction.
Second,
CNN-BLSTM-AM
is
used
further
extract,
select
fuse
form
predictive
measurements
identified
degradation
metrics.
In
addition,
we
introduce
AUKF
increase
uncertainty
representation
Finally,
validated
on
NASA
dataset
CALCE
compared
other
methods.
The
experimental
results
show
able
achieve
accurate
estimation
RUL,
minimum
RMSE
up
0.0030,
MAE
0.0024,
which
has
high
robustness.
Язык: Английский
State of health estimation for lithium-ion batteries using a hybrid Mixture of Gaussian and Laplacian extreme learning machine algorithm
Ionics,
Год журнала:
2025,
Номер
unknown
Опубликована: Апрель 15, 2025
Язык: Английский
The Role of Machine Learning in Enhancing Battery Management for Drone Operations: A Focus on SoH Prediction Using Ensemble Learning Techniques
Batteries,
Год журнала:
2024,
Номер
10(10), С. 371 - 371
Опубликована: Окт. 18, 2024
This
study
considers
the
significance
of
drones
in
various
civilian
applications,
emphasizing
battery-operated
and
their
advantages
limitations,
highlights
importance
energy
consumption,
battery
capacity,
state
health
batteries
ensuring
efficient
drone
operation
endurance.
It
also
describes
a
robust
testing
methodology
used
to
determine
SoH
accurately,
considering
discharge
rates
using
machine
learning
algorithms
for
analysis.
Machine
techniques,
including
classical
regression
models
Ensemble
Learning
methods,
were
developed
calibrated
experimental
UAV
data
predict
accurately.
Evaluation
metrics
such
as
Root
Mean
Squared
Error
(RMSE)
Absolute
(MAE)
assess
model
performance,
highlighting
balance
between
complexity
generalization.
The
results
demonstrated
improved
predictions
with
models,
though
complexities
may
lead
overfitting
challenges.
transition
from
simpler
intricate
methods
is
meticulously
described,
an
assessment
each
model’s
strengths
limitations.
Among
Bagging,
GBR,
XGBoost,
LightGBM,
stacking
studied.
technique
promising
results:
Flight
92
RMSE
0.03%
MAE
1.64%
observed,
while
129
was
0.66%
stood
at
1.46%.
Язык: Английский
A Novel End-to-End Provenance System for Predictive Maintenance: A Case Study for Industrial Machinery Predictive Maintenance
Computers,
Год журнала:
2024,
Номер
13(12), С. 325 - 325
Опубликована: Дек. 4, 2024
In
this
study,
we
address
the
critical
gap
in
predictive
maintenance
systems
regarding
absence
of
a
robust
provenance
system
and
specification.
To
tackle
issue,
propose
based
on
PROV-O
schema,
designed
to
enhance
explainability,
accountability,
transparency
processes.
Our
framework
facilitates
collection,
processing,
recording,
visualization
data,
integrating
them
seamlessly
into
these
systems.
We
developed
prototype
evaluate
effectiveness
our
approach
conducted
comprehensive
user
studies
assess
system’s
usability.
Participants
found
extended
structure
valuable,
with
improved
task
completion
times.
Furthermore,
performance
tests
demonstrated
that
manages
high
workloads
efficiently,
minimal
overhead.
The
contributions
study
include
design
tailored
for
specification
ensures
scalability
efficiency.
Язык: Английский