Physics-informed deep learning for structural dynamics under moving load
International Journal of Mechanical Sciences,
Journal Year:
2024,
Volume and Issue:
unknown, P. 109766 - 109766
Published: Oct. 1, 2024
Language: Английский
An advanced physics-informed neural network-based framework for nonlinear and complex topology optimization
Hyogu Jeong,
No information about this author
Chanaka Batuwatta-Gamage,
No information about this author
Jinshuai Bai
No information about this author
et al.
Engineering Structures,
Journal Year:
2024,
Volume and Issue:
322, P. 119194 - 119194
Published: Oct. 30, 2024
Language: Английский
Recent Advances in Food Drying Modeling: Empirical to Multiscale Physics‐Informed Neural Networks
Comprehensive Reviews in Food Science and Food Safety,
Journal Year:
2025,
Volume and Issue:
24(3)
Published: May 1, 2025
ABSTRACT
Food
insecurity
is
a
major
global
challenge.
preservation,
particularly
through
drying,
presents
promising
solution
to
enhance
food
security
and
minimize
waste.
Fruits
vegetables
contain
80%–90%
water,
much
of
this
removed
during
drying.
However,
structural
changes
across
multiple
length
scales
occur
compromising
stability
affecting
quality.
Understanding
these
essential,
several
modeling
techniques
exist
analyze
them,
including
empirical
modeling,
physics‐based
computational
methods,
purely
data‐driven
machine
learning
approaches,
physics‐informed
neural
network
(PINN)
models.
Although
methods
are
straightforward
implement,
their
limited
generalizability
lack
physical
insights
have
led
the
development
methods.
These
can
achieve
high
spatiotemporal
resolution
without
requiring
experimental
investigations.
complexity
costs
prompted
exploration
models
for
drying
processes,
which
involve
comparatively
lower
more
execute.
Nonetheless,
poor
predictive
ability
with
sparse
data
has
restricted
application,
leading
hybrid
approach:
PINN,
merges
techniques.
This
method
still
holds
significant
potential
advancements
in
modeling.
Therefore,
study
aims
conduct
comprehensive
literature
review
state‐of‐the‐art
conventional
techniques,
such
as
empirical,
computational,
pure
explores
PINN
approach
overcoming
limitations
associated
strategies.
Language: Английский
A two-step scaled physics-informed neural network for non-destructive testing of hull rib damage
Ocean Engineering,
Journal Year:
2024,
Volume and Issue:
319, P. 120260 - 120260
Published: Dec. 31, 2024
Language: Английский
A novel machine learning-based computational framework for predicting microscale morphological changes of plant cells during drying
Chanaka Prabuddha Batuwatta Gamage
No information about this author
Published: Jan. 1, 2024
This
thesis
proposes
a
novel
and
effective
physics-informed
machine
learning
framework
to
explore
microscale
variations
in
plant-based
foods
during
drying.
By
initiating
fundamental
numerical
investigations
at
the
cellular
level—which
significantly
influence
bulk-level
changes—this
research
highlights
framework's
robustness
flexibility
over
traditional
methods
like
FEA
meshfree
particle-based
methods.
The
work
demonstrates
considerable
potential
for
employing
this
learning-based
computational
modelling
technique
complex,
nonlinear
showcasing
its
superiority
analysing
predicting
drying
process
of
efficiently
accurately.
Language: Английский