Biotechnology and Bioengineering,
Год журнала:
2024,
Номер
unknown
Опубликована: Дек. 22, 2024
ABSTRACT
In
the
biopharmaceutical
industry,
accurately
predicting
penicillin
concentration
during
fermentation
is
key
to
boosting
production
efficiency
and
quality
assurance.
This
study
leverages
PenSim
simulation
data
set
applies
various
machine
learning
deep
techniques
forecast
concentration.
Initially,
through
correlation
analysis,
nine
feature
variables
with
significant
impacts
on
were
screened,
underwent
preprocessing
standardization.
Using
grid
search,
we
systematically
optimize
hyperparameters
of
prediction
models.
Results
show
that
ridge
regression
model
excels,
achieving
a
mean
squared
error
0.0512
absolute
0.0361.
indicates
strong
linear
relationship
between
selected
features.
Our
offers
data‐driven
insights
for
intelligent
monitoring
optimization
processes.
It
also
showcases
potential
artificial
intelligence
in
enhancing
control
biotechnological
facilities,
paving
way
future
research.
Processes,
Год журнала:
2025,
Номер
13(4), С. 1118 - 1118
Опубликована: Апрель 8, 2025
The
accurate
prediction
of
hydrocracking
product
yields
is
crucial
for
optimizing
resource
allocation
and
improving
production
efficiency.
However,
the
flowrates
in
units
often
faces
challenges
due
to
insufficient
data
weak
correlations
between
input
output
variables.
This
study
proposes
a
hybrid
framework
combining
Convolutional
Neural
Network–Long
Short-Term
Memory
(CNN-LSTM)
model,
mechanism
modeling,
Particle
Swarm
Optimization
(PSO)
address
these
issues.
CNN-LSTM
captures
spatiotemporal
dependencies
operational
data,
while
model
incorporates
domain-specific
physical
constraints.
structured
both
series
parallel
configurations,
with
PSO
key
hyperparameters
enhance
its
predictive
performance.
results
demonstrate
significant
improvements
accuracy,
determination
coefficients
(R2s)
reaching
0.896
(kerosene),
0.879
(residue),
0.899
(heavy
naphtha),
0.78
(light
naphtha).
Shapley
Additive
Explanations
(SHAP)
Mutual
Information
Coefficient
(MIC)
analyses
highlight
model’s
role
feature
interpretability.
underscores
efficacy
integrating
kinetics
deep
learning,
metaheuristic
optimization
complex
industrial
processes
under
constraints,
offering
robust
approach
yield
prediction.
International Journal of Pharmaceutics,
Год журнала:
2025,
Номер
unknown, С. 125322 - 125322
Опубликована: Фев. 1, 2025
This
study
demonstrates
that
developing
interpretable,
data-driven
models
for
pharmaceutical
continuous
manufacturing
is
feasible
using
a
machine
learning
method
called
Dynamic
Mode
Decomposition
with
Control
(DMDc).
approach
facilitates
adoption
within
Good
Manufacturing
Practice
(GMP)-regulated
areas
of
the
industry.
Furthermore,
since
industry
needs
to
be
more
operationally
efficient
profitable
and
sustainable,
we
present
real-time
monitoring
strategy
framework
an
interpretable
DMDc
dynamic
model
in
design
tuning
predictive
control
(MPC)
system
granule
size
during
twin-screw
granulation
process.
exhibited
low
computational
complexity
without
requiring
first
principles
knowledge,
while
effectively
capturing
nonlinear
dynamics
this
Multiple
input
multiple
output
(MIMO)
system,
better
performance
(e.g.,
r2
>
0.93
vs.0
D50
predictions)
reconstruction
unseen
test
data
comparison
benchmark
methods
identification.
The
DMDc-MPC
was
implemented
tested
on
setpoint
tracking
disturbance
rejection
proposed
advanced
process
guaranteed
both.
Journal of Pharmaceutical Research International,
Год журнала:
2024,
Номер
36(9), С. 46 - 60
Опубликована: Авг. 29, 2024
Emerging
technologies
present
a
transformative
potential
for
pharmaceutical
process
design
and
optimization,
particularly
within
Africa’s
evolving
industries.
The
purpose
of
this
review
is
to
explore
the
impact
emerging
digital
technologies,
including
Artificial
Intelligence
(AI),
Machine
Learning
(ML),
Internet
Things
(IoT),
Robotics,
on
optimization
African
context.
Data
was
collected
through
comprehensive
literature
scholarly
articles,
industry
reports,
case
studies.
By
analyzing
recent
advancements
studies,
identifies
key
areas
where
technology
reshaping
production
processes
product
development.
It
highlights
benefits,
increased
efficiency,
improved
accuracy,
minimized
waste.
However,
also
emphasizes
significant
challenges,
infrastructural
limitations,
regulatory
barriers,
disparities
in
access
that
can
hinder
adoption
these
Africa.
An
assessment
their
manufacturing
drug
costs,
quality,
safety
reveals
enhance
operations
significantly.
findings
suggest
while
offer
substantial
opportunities
improving
operations,
successful
integration
requires
strategic
approach
involves
stakeholder
cooperation,
infrastructure
improvements,
targeted
capacity
enhancement
initiatives
continent’s
industry.
This
offers
broad
overview
current
state
technological
sector
Africa
leveraging
drive
sustainable
improvements
development
process.
