Resource
scheduling
can
enhance
production
productivity
and
decrease
costs
by
optimizing
the
resource
assignment
in
each
process.
Currently,
static
optimization
model
remains
primary
method
for
precast
applications,
without
considering
real-time
demand
various
processes.
In
this
paper,
a
condition-based
dynamic
is
proposed
to
optimize
assignment,
aiming
pursue
on-time
delivery
of
components
while
minimizing
costs.
First,
different
conditions
was
quantified
analyzing
operation
status.
On
basis,
workers
with
competence
levels
are
dynamically
assigned
satisfy
Subsequently,
synergistically
adjusted
account
changes
processing
time
caused
quantities
types
newly
resources.
Finally,
comparisons
conducted
traditional
methods
under
constant
demonstrate
superiority
model.
The
results
show
that
mitigate
potential
imbalance
between
supply
reduce
conclusions
drawn
from
research
provide
insights
into
management.
Buildings,
Journal Year:
2024,
Volume and Issue:
14(10), P. 3173 - 3173
Published: Oct. 5, 2024
Precast
concrete
components
have
attracted
a
lot
of
attention
due
to
their
efficient
production
on
off-site
lines.
However,
in
the
precast
component
process,
unreasonable
sequence
and
mold
layout
will
reduce
efficiency
affect
workload
balance
between
each
process.
Due
multi-species
small-lot
characteristics
components,
number
molds
corresponding
is
generally
limited.
In
this
paper,
optimization
model
for
assembling
under
limited
proposed,
aiming
improve
comprehensive
utilization
tables
process
components.
order
obtain
better
richer
combination
schemes,
multi-objective
teaching-learning-based
algorithm
based
Pareto
dominance
relation
developed,
an
enhancement
mechanism
embedded
proposed
algorithm.
To
verify
superior
performance
enhanced
improving
balancing
various
processes,
three
different
sizes
cases
are
designed.
The
research
results
show
that
can
help
managers
efficiently
formulate
more
reasonable
especially
those
enterprises
struggling
production.
International Journal of Production Research,
Journal Year:
2024,
Volume and Issue:
unknown, P. 1 - 18
Published: Oct. 23, 2024
The
existing
scheduling
methods
of
wafer
fabs
focus
on
single
area,
achieving
local
optimisation
while
failing
to
realise
global
due
neglecting
the
coordination
multi-area.
Therefore,
it
is
necessary
consider
complex
opposing
relationships
between
multi-area
caused
by
constraints
such
as
batch
processing,
re-entrance,
and
multiple
residency
times
within
areas
conduct
integrated
shorten
production
cycle
time.
For
this
issue,
paper
proposes
a
cooperative
multi-agent
reinforcement
learning
for
scheduling.
Aiming
at
dynamic
batching
considering
arrival
lots
in
multi-area,
algorithm
presented
learn
optimal
policy
firstly.
Subsequently,
framework
raised
achieve
Furthermore,
an
adaptive
exploration
strategy
constructed
enhance
capability
solution
space
time
re-entrant
property.
Moreover,
share
enhanced
Double
DQN
employed
improve
generalisation
adaptability
multi-agent.
Finally,
experiments
demonstrate
that
proposed
method
has
better
comprehensive
performance
compared
previous
area-separated
methods.
