Agile conceptual design and validation based on multi-source product data and large language models: a review, framework, and outlook
Journal of Engineering Design,
Год журнала:
2025,
Номер
unknown, С. 1 - 31
Опубликована: Март 11, 2025
Язык: Английский
Data as design material: innovating smart artefacts and connected products development with the Data-Driven Design Framework (D3F)
Journal of Engineering Design,
Год журнала:
2025,
Номер
unknown, С. 1 - 49
Опубликована: Янв. 22, 2025
Язык: Английский
AI-Assisted Inheritance of Qinghua Porcelain Cultural Genes and Sustainable Design Using Low-Rank Adaptation and Stable Diffusion
Electronics,
Год журнала:
2025,
Номер
14(4), С. 725 - 725
Опубликована: Фев. 13, 2025
Blue-and-white
porcelain,
as
a
representative
of
traditional
Chinese
craftsmanship,
embodies
rich
cultural
genes
and
possesses
significant
research
value.
Against
the
backdrop
generative
AI
era,
this
study
aims
to
optimize
creative
processes
blue-and-white
porcelain
enhance
efficiency
accuracy
complex
artistic
innovations.
Traditional
methods
crafting
encounter
challenges
in
accurately
efficiently
constructing
intricate
patterns.
This
employs
grounded
theory
conjunction
with
KANO-AHP
hybrid
model
classify
quantify
core
esthetic
features
thereby
establishing
multidimensional
feature
library
its
Subsequently,
leveraging
Stable
Diffusion
platform
utilizing
Low-Rank
Adaptation
(LoRA)
technology,
artificial
intelligence
(AIGC)-assisted
workflow
was
proposed,
capable
restoring
innovating
enhances
precision
pattern
innovation
while
maintaining
consistency
original
style.
Finally,
by
integrating
principles
sustainable
design,
explores
new
pathways
for
digital
offering
viable
solutions
contemporary
reinvention
crafts.
The
results
indicate
that
AIGC
technology
effectively
facilitates
integration
modern
design
approaches.
It
not
only
empowers
inheritance
continuation
but
also
introduces
ideas
possibilities
development
craftsmanship.
Язык: Английский
Enhancing Bolt Object Detection via AIGC-Driven Data Augmentation for Automated Construction Inspection
Jie Wu,
Beilin Han,
Y.K. Zhang
и другие.
Buildings,
Год журнала:
2025,
Номер
15(5), С. 819 - 819
Опубликована: Март 5, 2025
In
the
engineering
domain,
detection
of
damage
in
high-strength
bolts
is
critical
for
ensuring
safe
and
reliable
operation
equipment.
Traditional
manual
inspection
methods
are
not
only
inefficient
but
also
susceptible
to
human
error.
This
paper
proposes
an
automated
bolt
identification
method
leveraging
AIGC
(Artificial
Intelligence
Generated
Content)
technology
object
algorithms.
Specifically,
we
introduce
application
image
generation,
focusing
on
Stable
Diffusion
model.
Given
that
quality
images
generated
directly
by
model
suboptimal,
employ
LoRA
fine-tuning
technique
enhance
model,
thereby
generating
a
high-quality
dataset
images.
then
used
train
YOLO
(You
Only
Look
Once)
algorithm,
demonstrating
significant
improvements
both
accuracy
recall
recognition.
Experimental
results
show
fine-tuned
significantly
enhances
performance
providing
efficient
accurate
solution
detection.
Future
work
will
concentrate
further
optimizing
improve
its
robustness
real-time
performance,
better
meeting
demands
practical
industrial
applications.
Язык: Английский
IXAI: generative design of automotive styling based on inception convolution with explainable AI
Journal of Engineering Design,
Год журнала:
2025,
Номер
unknown, С. 1 - 29
Опубликована: Март 24, 2025
Язык: Английский
Optimizing Design Thinking Strategy for AI-Generated Image Models: Using Logo Design as a Case Study
SHS Web of Conferences,
Год журнала:
2025,
Номер
213, С. 02006 - 02006
Опубликована: Янв. 1, 2025
In
recent
years,
the
rapid
development
of
artificial
intelligence
(AI)
has
greatly
improved
design
efficiency
and
visual
effects.
Nevertheless,
image
aspect
remains
largely
rudimentary
in
current
AI
platforms.
Looking
at
examples
logo
design,
we
see
that
most
logos
are
merely
replicas
logos.
To
fully
exploit
potential
need
to
optimize
thinking.
This
study
investigates
advantages
challenges
existing
models
applications.
It
proposes
a
training
program
improve
knowledge,
thinking,
skills,
materials
platform
database.
Deepening
specific
domain
knowledge
improves
AIGC
model’s
ability
understand
context
combining
designer’s
creative
thinking
with
AI’s
processing
power
achieve
more
results.
Additionally,
this
creates
new
model
user
participation
using
technology
collect
feedback
dynamically
adjust
scheme.
The
goal
is
enhance
use
offer
fresh
approach,
aid
creating
thought
expression,
make
generation
intelligent
varied,
boost
creativity,
brand
construction
quality.
Язык: Английский
Catalyst for future education: An empirical study on the Impact of artificial intelligence generated content on college students’ innovation ability and autonomous learning
Education and Information Technologies,
Год журнала:
2024,
Номер
unknown
Опубликована: Дек. 12, 2024
Язык: Английский
Advancing engineering design problem-exploring practice: interviews with industry professionals
Journal of Engineering Design,
Год журнала:
2024,
Номер
unknown, С. 1 - 22
Опубликована: Окт. 16, 2024
Studies
highlight
that
conceptualising
and
identifying
a
new
engineering
design
problem
(EDP)
is
vital,
as
the
solution
can
benefit
society.
However,
this
essential
activity,
referred
to
problem-exploring
(EDPE),
lacking
in
practice
design.
Design
engineers
appear
focus
on
providing
an
(EDS)
while
their
role
EDPE
rarely
practised.
A
EDP
drives
innovations
inventions,
there
need
encourage,
advance
sustain
of
EDPs.
The
aim
study
empirically
underlying
determinants
scarce
suggest
how
practice.
Interviews
were
conducted
with
32
professionals
within
community,
comprising
28
practitioners
four
specialists
–
lecturer,
inventor,
two
expert
trainers
creativity
problem-solving.
results
analyses
informed
suggested
approaches
Язык: Английский