Proceedings of the Institution of Mechanical Engineers Part J Journal of Engineering Tribology,
Год журнала:
2025,
Номер
unknown
Опубликована: Янв. 15, 2025
Tribological
properties
of
materials
exhibit
complex
and
non-linear
correlation
with
working
conditions
under
mixed
lubrication.
Selecting
an
appropriate
data-driven
method
to
predict
tribological
is
important
for
accelerating
material
design
preparation.
This
paper
investigates
the
performance
wear
mechanisms
QBe2
beryllium
bronze
7075-T6
aluminum
alloy
pairs
grease
lubrication
by
using
pin-on-disk
friction
tests.
The
different
further
predicted
four
machine
learning
algorithms:
K-nearest
Neighbors
(KNN),
Support
Vector
Machine
(SVM),
Artificial
Neural
Network
(ANN),
Random
Forest
(RF).
experimental
results
both
show
that
reciprocating
frequency
has
most
significant
influence.
dominant
include
ploughing
adhesive
wear.
Furthermore,
among
models,
SVM
model
performs
best
in
predicting
Buildings,
Год журнала:
2024,
Номер
14(3), С. 637 - 637
Опубликована: Фев. 28, 2024
The
quality
of
natural
lighting
within
secondary
school
classrooms
can
significantly
affect
the
physical
and
mental
well-being
both
teachers
students.
While
numerous
studies
have
explored
various
aspects
daylighting
performance
its
related
factors,
there
is
no
universal
standard
for
predicting
optimizing
from
a
design
perspective.
In
this
study,
method
was
developed
that
combines
measurements
simulations
to
enhance
parameters
associated
with
performance.
This
approach
facilitates
determination
precise
ranges
multiple
allows
efficient
attainment
optimal
Daylight
glare
probability
(DGP),
point-in-time
illuminance
(PIT),
daylight
factor
(DF),
energy
consumption
were
simulated
based
on
existing
control
operational
classrooms.
simulation
results
then
validated
using
field
measurements.
Genetic
algorithms
(GAs)
employed
optimize
parameters,
yielding
set
solutions
improving
differences
between
indicators
corresponding
solution
those
basic
model
compared
test
optimized
parameters.
proposed
robust
process
GAs,
which
not
only
enhances
but
also
offers
scientifically
grounded
guidelines
phase.
It
valuable
framework
creating
healthier
more
productive
educational
environments
Proceedings of the Institution of Mechanical Engineers Part J Journal of Engineering Tribology,
Год журнала:
2025,
Номер
unknown
Опубликована: Янв. 15, 2025
Tribological
properties
of
materials
exhibit
complex
and
non-linear
correlation
with
working
conditions
under
mixed
lubrication.
Selecting
an
appropriate
data-driven
method
to
predict
tribological
is
important
for
accelerating
material
design
preparation.
This
paper
investigates
the
performance
wear
mechanisms
QBe2
beryllium
bronze
7075-T6
aluminum
alloy
pairs
grease
lubrication
by
using
pin-on-disk
friction
tests.
The
different
further
predicted
four
machine
learning
algorithms:
K-nearest
Neighbors
(KNN),
Support
Vector
Machine
(SVM),
Artificial
Neural
Network
(ANN),
Random
Forest
(RF).
experimental
results
both
show
that
reciprocating
frequency
has
most
significant
influence.
dominant
include
ploughing
adhesive
wear.
Furthermore,
among
models,
SVM
model
performs
best
in
predicting
