Abstract
This
review
exploits
the
crucial
role
of
computational
methods
in
discovering
and
optimizing
materials
for
redox
flow
batteries
(RFBs).
Integration
high‐throughput
screening
(HTCS)
machine
learning
(ML)
accelerates
discovery,
guided
by
algorithms
categorizing
RFBs.
A
collaborative
exploration,
spanning
macroscopic
to
mesoscopic
scales,
combines
quantum
with
reinforcement
learning,
transfer
time
series
analysis,
Bayesian
optimization,
active
various
generative
models.
The
integration
ML
techniques
experimental
methods,
anchored
experimentally
validated
Density
Functional
Theory
(DFT)
calculations
molecular
dynamics
(MD)
simulations,
proves
indispensable
cost‐effective
Data
collection
feature
engineering
are
explored,
emphasizing
optimization
goals
precise
data
within
framework.
Feature
analysis
importance
is
highlighted,
utilizing
such
as
filter,
embedded,
wrapper
deep
efficient
energy
exploration.
Computational
perspectives
on
features
operating
conditions
encompass
membrane
characteristics,
fluid
dynamics,
temperature
dependence
pressure
sensitivity.
Time‐dependent
ML‐generated
insights
understanding
cycling
performance
intricacies,
providing
a
comprehensive
RFB
materials.
RSC Advances,
Год журнала:
2025,
Номер
15(5), С. 3155 - 3167
Опубликована: Янв. 1, 2025
This
study
uses
various
ML
algorithms,
including
artificial
neural
networks,
random
forest,
k
-nearest
neighbors,
and
decision
tree,
based
on
experimental
studies
to
predict
the
specific
capacitance
characteristics
of
CNT-based
SC
electrodes.
Physica Scripta,
Год журнала:
2023,
Номер
99(2), С. 026001 - 026001
Опубликована: Дек. 27, 2023
Abstract
Energy
storage
devices
and
systems
with
better
performance,
higher
reliability,
longer
life,
wiser
management
strategies
are
needed
for
daily
technology
advancement.
Among
these
devices,
the
supercapacitor
is
most
preferable
due
to
its
high-limit
capacitance
that
esteems
more
than
different
capacitors.
Today,
it
considered
a
significant
challenge
design
high-performance
materials
supercapacitors
by
exploring
interaction
between
characteristics
structural
features
of
materials.
Because
this,
essential
predict
when
assessing
material’s
potential
use
in
constructing
supercapacitor-electrode
applications.
Machine
learning
(ML)
can
significantly
speed
up
computation,
capture
complex
mechanisms
enhance
accuracy
prediction
make
best
choices
based
on
detailed
status
data.
We
aimed
develop
new
strategy
assisted
applying
ML
analyze
relationship
porous
carbon
(PCMs)
using
hundreds
experimental
data
literature.
In
present
study,
Linear
Regression
(LR),
Tree
(RT),
Adaptive
Neuro-Fuzzy
Inference
System
(ANFIS)
were
used
estimate
supercapacitor’s
capacitance.
The
effectiveness
models
was
evaluated
terms
root
mean
square
error
(RMSE),
absolute
(MAE),
correlation
expected
yield
system-provided
yield.
developed
ANFIS
model,
RMSE,
MAE,
R
values
22.8,
39.7647,
0.90004,
respectively,
compares
favourably
regarding
performance
other
built
this
purpose.
