High Performance Polymers,
Journal Year:
2025,
Volume and Issue:
unknown
Published: Jan. 8, 2025
Polyimide
(PI)
is
widely
used
in
modern
industry
due
to
its
excellent
properties.
Its
synthesis
methods
and
property
research
have
significantly
progressed.
However,
the
design
regulation
of
PI
structures
through
traditional
technologies
are
slow
expensive,
which
make
it
difficult
meet
practical
demand
materials.
With
rapid
development
high-throughput
computing
data-driven
technology,
machine
learning
(ML)
has
become
an
important
method
for
exploring
new
Data-driven
ML
envisaged
as
a
decisive
enabler
PIs
discovery.
This
paper
first
introduces
basic
workflow
common
algorithms
ML.
Secondly,
applications
material
properties
prediction,
assisting
computational
simulation
inverse
desired
reviewed.
Finally,
we
discuss
main
challenges
possible
solutions
research.
Chemistry of Materials,
Journal Year:
2023,
Volume and Issue:
35(13), P. 4897 - 4910
Published: June 26, 2023
Silica
aerogels
are
mesoporous
high
surface
area
materials
with
extensive
synthetic
and
processing
conditions.
To
effectively
synthesize
aerogels,
the
impact
of
pathways
on
resulting
aerogel
properties
must
be
understood
prior
to
experimental
investigation.
We
develop
an
information
architecture,
silica
graph
database
(103),
a
supervised
machine
learning
neural
network
regression
model
examine
these
relationships.
The
property
enables
rapid
queries
visualization
synthesis
conditions
final
properties.
maps
from
predict
BET
average
error
109
±
84
m2/g.
Following
validation
experiment,
was
shown
new
less
than
5%.
experiment
demonstrates
usefulness
in
prediction
through
compatibility
between
computational
results.
Both
its
current
form
further
expansion,
developed
could
reduce
dimensionality,
time,
resources,
enabling
successful
which
advantageous
for
applications
including
thermal
insulation,
sorption
media,
catalysis.
Results in Materials,
Journal Year:
2023,
Volume and Issue:
19, P. 100455 - 100455
Published: Sept. 1, 2023
Data
science
and
material
informatics
are
gaining
traction
in
alloy
design.
This
is
due
to
increasing
infrastructure,
computational
capabilities
established
open-source
composition-structure-property
databases
increasingly
becoming
available.
Additionally,
the
popularization
of
data
techniques
drive
reduce
overall
life-cycle
cost
by
∼60%
have
necessitated
increased
use
technique.
Alloy
design
a
multi-optimization
problem
hence
Edisonian
approach
no
more
viable
from
cost,
labour,
time-to-market
perspectives.
Although,
there
been
successful
application
design,
drawbacks.
review
provides
critical
assessment
limitations
associated
with
materials
discovery
property
characterization.
Among
these
false
positives,
over
–
underestimation
properties,
lack
experimental
validate
simulated
results,
state-of-the-art
facilities
most
developing
countries
uncertainty
modelling.
The
implications
areas
for
future
research
directions
highlighted.
High Performance Polymers,
Journal Year:
2025,
Volume and Issue:
unknown
Published: Jan. 8, 2025
Polyimide
(PI)
is
widely
used
in
modern
industry
due
to
its
excellent
properties.
Its
synthesis
methods
and
property
research
have
significantly
progressed.
However,
the
design
regulation
of
PI
structures
through
traditional
technologies
are
slow
expensive,
which
make
it
difficult
meet
practical
demand
materials.
With
rapid
development
high-throughput
computing
data-driven
technology,
machine
learning
(ML)
has
become
an
important
method
for
exploring
new
Data-driven
ML
envisaged
as
a
decisive
enabler
PIs
discovery.
This
paper
first
introduces
basic
workflow
common
algorithms
ML.
Secondly,
applications
material
properties
prediction,
assisting
computational
simulation
inverse
desired
reviewed.
Finally,
we
discuss
main
challenges
possible
solutions
research.
