Journal of Polymer Science,
Journal Year:
2024,
Volume and Issue:
unknown
Published: Dec. 25, 2024
ABSTRACT
The
discovery
of
high‐performance
shape
memory
polymers
(SMPs)
with
enhanced
glass
transition
temperatures
(Tg)
is
paramount
importance
in
fields
such
as
geothermal
energy,
oil
and
gas,
aerospace,
other
high‐temperature
applications,
where
materials
are
required
to
exhibit
effect
at
extremely
conditions.
Here,
we
employ
a
novel
machine
learning
framework
that
integrates
transfer
variational
autoencoders
(VAE)
efficiently
explore
the
chemical
design
space
SMPs
identify
new
candidates
high
Tg
values.
We
systematically
investigate
different
latent
dimensions
on
VAE
model
performance.
Several
models
then
trained
predict
Tg.
find
SVM
demonstrates
highest
predictive
accuracy,
R
2
values
exceeding
0.87
mean
absolute
percentage
error
low
6.43%
test
set.
Through
systematic
molar
ratio
adjustments
VAE‐based
fingerprinting,
discover
SMP
between
190°C
200°C,
suitable
for
applications.
These
findings
underscore
effectiveness
combining
VAEs
discovery,
offering
scalable
efficient
method
identifying
tailored
thermal
properties.
Advanced Functional Materials,
Journal Year:
2025,
Volume and Issue:
unknown
Published: May 16, 2025
Abstract
The
evolution
of
electronic
technology,
such
as
high‐speed,
high‐frequency,
and
high‐density
integrated
circuits,
imposes
higher
performance
requirements
on
advanced
functional
materials
like
polyimides.
However,
the
prolonged
development
cycle
linked
with
conventional
trial‐and‐error
methods
results
in
a
noticeable
gap
between
material
research
its
practical
application.
Here,
genome
approach
is
proposed
to
accelerate
discovery
polyimides
exhibiting
exceptional
dielectric
properties
under
elevated
temperatures
high
frequencies.
To
address
scarcity
data,
theoretical
high‐frequency
are
derived
by
employing
Havriliak‐Negami
relaxation
model
complement
experimental
data.
With
augmented
data
polyimides,
multi‐task
learning
hierarchical
neural
networks
for
glass
transition
temperature.
Structural
design
via
genetic
algorithms
implemented
engineer
polyimide
structures
enhanced
properties.
Several
comprehensive
generated,
validation
conducted.
Shapley
additive
explanations
analysis
reveals
crucial
structural
elements
influencing
performance.
framework
established
this
work
can
guide
other
polymeric
materials.
Advanced Science,
Journal Year:
2024,
Volume and Issue:
unknown
Published: Dec. 16, 2024
Abstract
Vitrimer
is
a
new,
exciting
class
of
sustainable
polymers
with
healing
abilities
due
to
their
dynamic
covalent
adaptive
networks.
However,
limited
choice
constituent
molecules
restricts
property
space
and
potential
applications.
To
overcome
this
challenge,
an
innovative
approach
coupling
molecular
dynamics
(MD)
simulations
novel
graph
variational
autoencoder
(VAE)
model
for
inverse
design
vitrimer
chemistries
desired
glass
transition
temperature
(
T
g
)
presented.
The
first
diverse
dataset
one
million
curated
8,424
them
calculated
by
high‐throughput
MD
calibrated
Gaussian
process
model.
proposed
VAE
employs
dual
encoders
latent
dimension
overlapping
scheme
which
allows
individual
representation
multi‐component
vitrimers.
High
accuracy
efficiency
the
framework
are
demonstrated
discovering
vitrimers
desirable
beyond
training
regime.
validate
effectiveness
in
experiments,
generated
target
=
323
K.
By
incorporating
chemical
intuition,
311–317
K
synthesized,
experimentally
demonstrating
healability
flowability.
offers
tool
polymer
chemists
synthesize
novel,
various
Digital Discovery,
Journal Year:
2024,
Volume and Issue:
unknown
Published: Jan. 1, 2024
We
benchmark
the
performance
of
space-filling
and
active
learning
algorithms
on
classification
problems
in
materials
science,
revealing
trends
optimally
data-efficient
algorithms.
Journal of Polymer Science,
Journal Year:
2024,
Volume and Issue:
unknown
Published: Dec. 25, 2024
ABSTRACT
The
discovery
of
high‐performance
shape
memory
polymers
(SMPs)
with
enhanced
glass
transition
temperatures
(Tg)
is
paramount
importance
in
fields
such
as
geothermal
energy,
oil
and
gas,
aerospace,
other
high‐temperature
applications,
where
materials
are
required
to
exhibit
effect
at
extremely
conditions.
Here,
we
employ
a
novel
machine
learning
framework
that
integrates
transfer
variational
autoencoders
(VAE)
efficiently
explore
the
chemical
design
space
SMPs
identify
new
candidates
high
Tg
values.
We
systematically
investigate
different
latent
dimensions
on
VAE
model
performance.
Several
models
then
trained
predict
Tg.
find
SVM
demonstrates
highest
predictive
accuracy,
R
2
values
exceeding
0.87
mean
absolute
percentage
error
low
6.43%
test
set.
Through
systematic
molar
ratio
adjustments
VAE‐based
fingerprinting,
discover
SMP
between
190°C
200°C,
suitable
for
applications.
These
findings
underscore
effectiveness
combining
VAEs
discovery,
offering
scalable
efficient
method
identifying
tailored
thermal
properties.
