Actuators,
Год журнала:
2024,
Номер
13(12), С. 516 - 516
Опубликована: Дек. 11, 2024
The
growing
diversity
and
number
of
industrial
robots
make
energy
consumption
prediction
optimization
increasingly
essential.
Current
data-driven
approaches,
particularly
those
based
on
multi-layer
perception
(MLP),
have
shown
feasibility
but
typically
overlook
the
variability
or
unknown
nature
load-related
parameters
in
real-world
applications.
This
paper
presents
a
KAN-LSTM
model
designed
to
accurately
predict
under
load
conditions,
alongside
particle
swarm
(PSO)
algorithm
for
minimizing
use.
First,
an
robot
dynamics
is
established.
Then,
trained
datasets
from
AUBO-E5
robot,
with
its
predictions
compared
alternative
network
models.
Finally,
PSO
applied
optimize
consumption.
Experimental
results
indicate
that
achieves
high
accuracy
(95.7–97.1%)
offers
substantial
potential
(53.1–64.7%).
Optimized
are
suitable
tasks
such
as
picking
palletizing
courier
industry,
saving
operational
costs
increasing
sustainability
automated
systems
logistics
environments.
Sustainability,
Год журнала:
2024,
Номер
16(12), С. 4930 - 4930
Опубликована: Июнь 8, 2024
This
study
delves
into
the
dynamic
relationship
between
artificial
intelligence
(AI)
and
environmental
performance,
with
a
specific
focus
on
greenhouse
gas
(GHG)
emissions
across
European
countries
from
2012
to
2022.
Utilizing
data
industrial
robots,
AI
companies,
investments,
we
examine
how
adoption
influences
GHG
emissions.
Preliminary
analyses,
including
ordinary
least
squares
(OLS)
regression
diagnostic
assessments,
were
conducted
ensure
adequacy
model
readiness.
Subsequently,
Elastic
Net
(ENET)
was
employed
mitigate
overfitting
issues
enhance
robustness.
Our
findings
reveal
intriguing
trends,
such
as
downward
trajectory
in
correlating
increased
investment
levels
robot
deployment.
Graphical
representations
further
elucidate
evolution
of
coefficients
cross-validation
errors,
providing
valuable
insights
sustainability.
These
offer
policymakers
actionable
for
leveraging
technologies
foster
sustainable
development
strategies.
Climate
change
has
become
an
increasingly
pressing
issue,
underscoring
the
urgent
global
need
for
energy
conservation
and
emission
reduction.
As
one
of
largest
emitters,
China
is
actively
advancing
comprehensive
efforts
to
reduce
emissions
in
pursuit
sustainable
development,
with
enterprises
playing
a
key
role
aligning
economic
growth
environmental
sustainability.
Digital
Transformation
(DT)
emerged
as
crucial
enabler
low-carbon
development.
This
study
utilizes
data
from
publicly
listed
companies
China,
spanning
period
2000
2021,
employs
two-way
fixed-effects
model
assess
impact
corporate
DT
on
Carbon
Emissions
(CE).
The
findings
reveal
that:
First,
significantly
contributes
reduction
CE;
Second,
CE
varies
across
regions,
industries,
firm
characteristics;
Third,
positive
effect
driven
by
mechanisms
such
technological
advancement,
innovation
promotion,
resource
optimization,
improved
output
efficiency.
These
results
provide
both
theoretical
insights
empirical
evidence
supporting
fostering
green,
enterprise
Scientific Reports,
Год журнала:
2025,
Номер
15(1)
Опубликована: Март 28, 2025
The
drive
of
the
rural
digital
economy
in
agricultural
development
and
enhancement
net
carbon
efficiency
are
integral
to
ensuring
quality
ecology.
To
better
understand
impact
on
ecological
quality,
this
paper
utilizes
panel
data
from
30
provinces
(municipalities,
autonomous
regions)
China
2013
2020
employs
instrumental
variable
method
analyze
efficiency.
results
reveal
that
advancement
significantly
enhances
agriculture,
finding
remains
robust
even
after
substituting
explanatory
variables
excluding
samples
direct-administered
municipalities.
Heterogeneity
analysis
indicates
aforementioned
is
more
pronounced
major
grain-producing
areas,
regions
with
high
industrial
concentration,
areas
low
government
intervention.
Further
reveals
can
enhance
through
two
primary
mechanisms:
improving
human
capital
promoting
technological
progress.
conclusions
study
have
significant
implications
for
level
optimizing
Systems,
Год журнала:
2025,
Номер
13(5), С. 333 - 333
Опубликована: Май 1, 2025
The
tourism
industry’s
explosive
growth
has
triggered
severe
carbon
emission
issues,
making
enhancing
efficiency
(TCE)
a
pressing
concern
for
achieving
sustainable
development.
widespread
application
of
artificial
intelligence
(AI)
in
presents
new
opportunities.
This
study
applies
the
Environmental
Kuznets
Curve
(EKC)
theory
to
examine
pathways
and
mechanisms
AI’s
impact
on
TCE,
with
focus
China.
findings
reveal
that
AI
significantly
enhances
where
improvements
labor
productivity,
rationalization
industry
structure,
advancements
technology
are
key
channel
mechanisms.
Heterogeneity
tests
indicate
substantially
boosts
TCE
eastern
developed
regions
areas
deficient
resource
endowments.
Furthermore,
exhibits
significant
spatial
spillover
effects,
both
local
neighboring
regions’
TCE.
These
insights
provide
crucial
policy
implications
utilizing
promote
China’s
industry.
