New
energy
electric
vehicles
have
seen
rapid
growth
in
recent
years
due
to
their
low
pollution,
efficiency,
and
peak
load-shifting
capabilities.
However,
evaluations
of
the
developmental
trends
new
vehicle
industry
remain
relatively
limited.
In
this
paper,
we
first
employed
nonlinear
optimization
APH
method
construct
an
indicator
system
its
weight
system,
thus
modeling
main
factors
influencing
development
vehicles.
The
method's
consistency
parameter
CR
is
order
10
-4
,
indicating
high
feasibility.
Then,
utilized
ARIMA
time
series
forecasting
multiple
linear
regression
model
predict
future
ten
years'
industry.
Evaluated
comprehensively
by
assessment
indicators
like
RMSE
F-values,
demonstrates
precision
good
fitting
effects.
Finally,
our
optimized
population
competition
innovatively
analyzed
interactive
effects
global
traditional
industries,
two
may
stabilize
after
a
period
joint
future,
dominate.
In
general,
high
power
electronic
converters
such
as
Multilevel
Inverters
(MLI),
that
find
their
use
in
many
applications,
create
difficulties
of
augmented
switch
count,
capacitor
flow
current
and
reverse
flowing
from
inductive
loads.
above
problems,
turn,
result
faults,
without
which
MLI
reliability
is
unattainable.
Therefore,
fault
classification
tolerance
strategies
are
paramount
contribute
to
keeping
inverters.
Herein
we
present
a
deep
learning
(DL)-based
approach
for
15-level
CHB
Multi-level
Inverter.
proposed
system
includes
pre-processing
based
on
Adaptive
Hilbert-Huang
filtering,
segmentation
by
Partial
Differential
Equation
(PDE),
feature
extraction
utilizing
Scale-Invariant
Feature
Transform
(SIFT),
signal
being
performed
Convolutional
Neural
Network
(CNN)
trained
with
Honey
Badger
Optimization
Algorithm
(HBOA).
MATLAB
was
applied
our
method
identifying
set
four
complex
types
purpose
measurement.
results
HBOA-optimized
CNN
have
demonstrated
highest
accuracy
rate
99.91%.
With
the
rapid
development
of
big
data
and
artificial
intelligence
(AI)
technologies,
their
wide
application
in
various
fields
has
become
possible.
Traditional
visual
design
systems
are
usually
based
on
static
rules
human
experience,
which
difficult
to
meet
personalized
needs
users,
resulting
low
universality
works.
This
article
solves
problems
existing
traditional
research
through
in-depth
interaction
AI
systems,
promotes
more
intelligent,
scientific
field
design.
takes
Generative
Adversarial
Network
(GAN)
algorithm
model
as
object,
performs
fusion
its
generative
A-VAE
(Attention-Variational
Autoencoder)
variational
autoencoders
attention
mechanisms,
proposes
a
new
algorithm.
Through
research,
it
been
found
that
merged
exhibits
better
image
generation
performance,
accuracy,
clarity,
diversity
compared
other
algorithms.
Digital
smart
highway
is
a
construction
model
that
uses
advanced
computer
technology
and
high-speed
communication
networks,
combined
with
modern
information
technology,
to
achieve
integrated
operation
of
collection,
transmission
processing.
This
research
mainly
focuses
on
the
digital
plan
based
DLP
algorithm.
First,
this
article
introduces
target
functions
design
scheme
its
performance
requirements
in
different
scenarios.
Secondly,
analyzes
content
each
part
overall
architecture
elaborates
explains
it
reference
relevant
theoretical
knowledge.
Finally,
MATLAB
software
complete
simulation
experiment
verify
optimization
effect.
The
test
results
show
system's
accuracy
identifying
vehicles
types
highways
generally
above
90%;
conditions
basically
80%,
has
better
real-time
traffic
flow
statistics.
The
traditional
digital
landscape
architecture
planning
(hereinafter
referred
to
as
DLAP)
system
has
problems
such
long
time
and
rough
details.
This
article
designs
a
DLAP
using
visualization
technology.
introduces
the
application
of
technology
in
system.
By
analyzing
concept
current
development
status
system,
role
significance
are
explored.
design
principles
methods
elaborated
detail,
case
study
is
conducted
based
on
actual
cases.
effectiveness
advantages
systems
summarized.
It
can
be
concluded
that
achieve
better
results
New
energy
electric
vehicles
have
seen
rapid
growth
in
recent
years
due
to
their
low
pollution,
efficiency,
and
peak
load-shifting
capabilities.
However,
evaluations
of
the
developmental
trends
new
vehicle
industry
remain
relatively
limited.
In
this
paper,
we
first
employed
nonlinear
optimization
APH
method
construct
an
indicator
system
its
weight
system,
thus
modeling
main
factors
influencing
development
vehicles.
The
method's
consistency
parameter
CR
is
order
10
-4
,
indicating
high
feasibility.
Then,
utilized
ARIMA
time
series
forecasting
multiple
linear
regression
model
predict
future
ten
years'
industry.
Evaluated
comprehensively
by
assessment
indicators
like
RMSE
F-values,
demonstrates
precision
good
fitting
effects.
Finally,
our
optimized
population
competition
innovatively
analyzed
interactive
effects
global
traditional
industries,
two
may
stabilize
after
a
period
joint
future,
dominate.
