AIMS Mathematics,
Journal Year:
2024,
Volume and Issue:
9(11), P. 32272 - 32298
Published: Jan. 1, 2024
<p>In
this
paper,
the
neural
network
domain
with
backpropagation
Levenberg-Marquardt
scheme
(NNB-LMS)
is
novel
a
convergent
stability
and
generates
numerical
solution
of
impact
magnetohydrodynamic
(MHD)
nanofluid
flow
over
rotating
disk
(MHD-NRD)
heat
generation/absorption
slip
effects.
The
similarity
variation
in
MHD
viscous
liquid
through
explained
by
transforming
original
non-linear
partial
differential
equations
(PDEs)
to
an
equivalent
ordinary
equation
(ODEs).
Varying
velocity
parameter,
Hartman
number,
thermal
concentration
Prandtl
number
using
Runge-Kutta
4<sup>th</sup>
order
method
(RK4)
technique,
which
dataset
for
suggested
numerous
MHD-NRD
scenarios.
validity
data
tested,
processed
properly
tabulated
test
exactness
model.
recommended
model
was
compared
verification,
estimation
solutions
particular
instances
were
assessed
NNB-LMS
training,
testing,
validation
procedures.
A
regression
analysis,
mean
squared
error
(MSE)
assessment,
histogram
analysis
used
further
evaluate
proposed
NNB-LMS.
technique
has
various
applications
such
as
disease
diagnosis,
robotic
control
systems,
ecosystem
evaluation,
etc.
Some
statistical
gradient,
performance,
epoch
analyzed.
This
differs
from
reference
results,
accuracy
rating
ranging
$
{10}^{-09}
$to
{10}^{-12}
$.</p>
