IET Collaborative Intelligent Manufacturing,
Год журнала:
2025,
Номер
7(1)
Опубликована: Янв. 1, 2025
ABSTRACT
Shop
scheduling
and
machine
layout
are
two
important
aspects
of
discrete
manufacturing.
There
strong
coupling
relationships
between
them,
but
they
were
conducted
separately
in
the
past,
which
significantly
limits
production
performance
improvement
At
same
time,
actual
process
workshop
production,
uncertain
events
not
only
often
occur
also
may
make
existing
schemes
no
longer
suitable.
To
address
such
issues,
integrated
optimisation
shop
for
manufacturing
considering
is
proposed
this
paper,
where
minimum
material
handling
cost,
maximum
space
utilisation
rate
completion
time
selected
as
objectives.
An
improved
immune
genetic
algorithm
designed
to
solve
corresponding
mathematical
model
efficiently
by
dual‐layer
encoding,
good
at
global
optimisation.
Moreover,
multistrategy
redundancy‐aware
rescheduling
performed
respond
that
regarded
disturbances.
The
rationality
superiority
method
verified
a
numerical
case
study
wood–plastic
composite
materials
with
its
layout,
well
under
failures.
IEEE Transactions on Automation Science and Engineering,
Год журнала:
2023,
Номер
21(4), С. 6550 - 6562
Опубликована: Ноя. 1, 2023
Distributed
manufacturing
involving
heterogeneous
factories
presents
significant
challenges
to
enterprises.
Furthermore,
the
need
prioritize
various
jobs
based
on
order
urgency
and
customer
importance
further
complicates
scheduling
process.
Consequently,
this
study
addresses
practical
issue
by
tackling
distributed
hybrid
flow
shop
problem
with
multiple
priorities
of
(DHHFSP-MPJ).
The
primary
objective
is
simultaneously
minimize
total
weighted
tardiness
energy
consumption.
To
solve
DHHFSP-MPJ,
a
double
deep
Q-network-based
co-evolution
(D2QCE)
developed
four
features:
i)
global
local
searches
are
allocated
into
two
populations
balance
computational
resources;
ii)
A
heuristic
strategy
proposed
obtain
an
initialized
population
great
convergence
diversity;
iii)
Four
knowledge-based
neighborhood
structures
accelerate
converging.
Next,
Q-Network
applied
learn
operator
selection;
iv)
An
energy-efficient
presented
save
energy.
verify
effectiveness
D2QCE,
five
state-of-the-art
algorithms
compared
20
instances
real-world
case.
results
numerical
experiments
indicate
that:
D2QN
can
fast
only
consuming
few
computation
resources
select
best
operator.
Combining
vastly
improve
performance
evolutionary
for
solving
scheduling.
D2QCE
has
better
than
state-of-the-arts
DHHFSP-MPJ
Note
Practitioners
—This
paper
inspired
encountered
in
blanking
workshop
systems
within
large
engineering
equipment.
In
scenario,
come
varying
distinct
due
dates.
Balancing
these
priority
date
constraints
while
efficiently
considerable
volume
enhance
enterprise
profitability
poses
challenge.
Thus,
abstracted
jobs.
objectives
minimizing
delay
Notably,
model
never
been
studied
before.
address
this,
we've
formulated
mixed-integer
linear
programming
novel
co-evolutionary
algorithm
Q-networks
(DQN).
Our
approach
introduces
several
key
components.
First,
we
present
framework
strike
between
search
aspects.
Additionally,
devised
three
problem-specific
enhancement
strategies
expedite
convergence,
which
include
initialization,
techniques,
energy-saving
measures.
learning
process
selecting
optimal
minimal
resources,
employ
DQN.
Experimental
demonstrate
superior
our
approach,
outperforming
when
summary,
work
proposes
extended
DHHFSP
provides
case
designing
learning-assisted
algorithm.
However,
online
reinforcement
(DRL)
consumes
additional
time,
generalization
DRL
needs
be
improved.
future
research,
will
consider
dynamic
events
such
as
new
insert
change
workshop.
Moreover,
end-to-end
considered
realize
sustainable
DRL.
Computers & Industrial Engineering,
Год журнала:
2024,
Номер
189, С. 109927 - 109927
Опубликована: Янв. 23, 2024
The
challenges
of
climate
change
and
resource
scarcity
have
led
policymakers
around
the
globe
to
strengthen
concept
circular
economy.
Legislation
towards
extended
producer
responsibility
means
that
recovery
parts
material
from
end-of-life
(EOL)
products
is
increasingly
imposed
as
a
mandatory
task
for
manufacturers
across
various
industries.
Consequently,
EOL
decision-making
has
emerged
relevant
topic
in
management
science.
Recent
research
addressed
environmental
impact
operations
by
considering
energy
usage
or
carbon
emissions
variable
disassembly
sequences
options.
This
paper
deals
with
selective
planning
scheduling
multiple
dismantling
shop
considers
results
process
stage.
It
extends
previous
formulations
flexible
levels
modes.
In
multi-objective
optimization
problem,
there
trade-off
between
potential
time
savings,
ecological
process-related
emissions,
penalty
associated
damaged
parts,
unseparated
modules,
unpurified
materials.
A
mathematical
formulation
presented
demonstrated
using
case
study
engine
disassembly.
Next,
genetic
algorithm
(MOGA)
developed
tested
synthetic
problem
data.
As
shown
computational
experiments,
MOGA
outperforms
exact
model
more
complex
settings
produces
competitive
fraction
required
commercial
solver.
Artificial Intelligence Review,
Год журнала:
2024,
Номер
57(3)
Опубликована: Фев. 16, 2024
Abstract
Implementing
green
and
sustainable
development
strategies
has
become
essential
for
industrial
robot
manufacturing
companies
to
fulfill
their
societal
obligations.
By
enhancing
assembly
efficiency
minimizing
energy
consumption
in
workshops,
these
enterprises
can
differentiate
themselves
the
fiercely
competitive
market
landscape
ultimately
bolster
financial
gains.
Consequently,
this
study
focuses
on
examining
collaborative
challenges
associated
with
three
crucial
parts:
body,
electrical
cabinet,
pipeline
pack,
within
process.
Considering
during
both
active
idle
periods
of
workshop
system,
paper
presents
a
multi-stage
energy-efficient
scheduling
model
minimize
total
consumption.
Two
classes
heuristic
algorithms
are
proposed
address
model.
Our
contribution
is
restructuring
existing
complex
mathematical
programming
model,
based
structural
properties
sub-problems
across
multiple
stages.
This
reformation
not
only
effectively
reduces
variable
scale
eliminates
redundant
constraints,
but
also
enables
Gurobi
solver
tackle
large-scale
problems.
Extensive
experimental
results
indicate
that
compared
traditional
experience,
constructed
algorithm
provide
more
precise
guidance
process
workshop.
Regarding
consumption,
plans
obtained
through
our
designed
exhibit
approximately
3%
lower
than
conventional
experience-based
approaches.
