AI-driven FMEA: integration of large language models for faster and more accurate risk analysis
Ibtissam El Hassani,
No information about this author
Tawfik Masrour,
No information about this author
Nouhan Kourouma
No information about this author
et al.
Design Science,
Journal Year:
2025,
Volume and Issue:
11
Published: Jan. 1, 2025
Abstract
Failure
mode
and
effects
analysis
(FMEA)
is
a
critical
but
labor-intensive
process
in
product
development
that
aims
to
identify
mitigate
potential
failure
modes
ensure
quality
reliability.
In
this
paper,
novel
framework
improve
the
FMEA
by
integrating
generative
artificial
intelligence
(AI),
particular
large
language
models
(LLMs),
presented.
By
using
these
advanced
AI
tools,
we
aim
streamline
collaborative
work
FMEA,
reduce
manual
effort
accuracy
of
risk
assessments.
The
proposed
includes
LLMs
support
data
collection,
pre-processing,
identification,
decision-making
FMEA.
This
integration
enables
more
efficient
reliable
leverages
strengths
human
expertise
capabilities.
To
validate
framework,
conducted
case
study
where
first
used
GPT-3.5
as
proof
concept,
followed
comparison
performance
three
well-known
LLMs:
GPT-4,
GPT-4o
Gemini.
These
comparisons
show
significant
improvements
terms
speed,
accuracy,
reliability
results
compared
traditional
methods.
Our
emphasize
transformative
processes
contribute
robust
design
assurance
practices.
paper
concludes
with
recommendations
for
future
research
focusing
on
security
domain-specific
LLM
training
protocols.
Language: Английский
Addressing Uncertainty in Digital Risk Evaluation Using a Fuzzy-FMEA Methodology
Lina Naciri,
No information about this author
Safae Merzouk,
No information about this author
Maryam Gallab
No information about this author
et al.
Published: May 13, 2025
Abstract
Alongside
with
the
four
past
revolutions
that
crowned
industrial
field,
and
innovative
technologies
grows
digitalization
trend,
manufacturing
systems
are
becoming
more
complex
especially
in
automotive
industry.
Even
though
this
evolution
plays
an
important
role
enhancing
companies’
performance,
they
also
present
many
risks
to
manage,
which
leads
stakeholders
need
of
implementing
a
strong
strategy
assess
such
as
Failure
Modes
Effects
Analysis
(FMEA).
Nowadays,
flows
confronts
different
types
variables
continuously
dynamically
interacting
(social,
environmental,
financial,
political,
educational,
cultural,
etc.),
leading
uncertainty
decision-making
approach,
specifically
during
ranking
failure
severity.
Accordingly,
article
explores
how
latest
version
FMEA
(AIAG/VDA)
approach
can
be
strengthened
through
Fuzzy-logic
overcome
judgments.
It
presents
use
case
based
on
RFID
system
implemented
within
company.
Language: Английский
Integrating large language models for improved failure mode and effects analysis (FMEA): a framework and case study
Ibtissam El Hassani,
No information about this author
Tawfik Masrour,
No information about this author
Nouhan Kourouma
No information about this author
et al.
Proceedings of the Design Society,
Journal Year:
2024,
Volume and Issue:
4, P. 2019 - 2028
Published: May 1, 2024
Abstract
The
manual
execution
of
failure
mode
and
effects
analysis
(FMEA)
is
time-consuming
error-prone.
This
article
presents
an
approach
in
which
large
language
models
(LLMs)
are
integrated
into
FMEA.
LLMs
improve
accelerate
FMEA
with
human
the
loop.
discussion
looks
at
software
tools
for
emphasizes
that
must
be
tailored
to
needs
company.
Our
framework
combines
data
collection,
pre-processing
reliability
assessment
automate
A
case
study
validates
this
demonstrates
its
efficiency
accuracy
compared
Language: Английский
Data-driven machinery faults detection techniques using Artificial Intelligence in Industry 4.0 concept
Procedia Computer Science,
Journal Year:
2025,
Volume and Issue:
257, P. 404 - 411
Published: Jan. 1, 2025
Language: Английский
Encouraging Safety 4.0 to enhance industrial culture: An extensive study of its technologies, roles, and challenges
Abid Haleem,
No information about this author
Mohd Javaid,
No information about this author
Ravi Pratap Singh
No information about this author
et al.
Green Technologies and Sustainability,
Journal Year:
2024,
Volume and Issue:
unknown, P. 100158 - 100158
Published: Dec. 1, 2024
Language: Английский
Improving Analysis of Risk-Based Maintenance Management Strategies Through Reliability Centered Maintenance. Case Study : Coal Crushing Plant. Central Kalimantan. Indonesia
Gayuh Widotomo
No information about this author
Advance Sustainable Science Engineering and Technology,
Journal Year:
2023,
Volume and Issue:
6(1), P. 0240109 - 0240109
Published: Dec. 21, 2023
PT
XYZ
as
a
company
operating
in
the
coal
mining
sector
has
7
production
lines
on
in-loading
system
its
crushing
plant.
In-loading
line
no.
is
that
lowest
mechanical
availability,
therefore
it
necessary
to
search
for
systematic
method
obtain
an
appropriate
maintenance
mode
and
not
only
consider
operational
aspects
but
also
pay
attention
occupational
health
&
safety
aspects.
RCM
qualitative
analysis
(which
can
be
developed
into
quantitative
analysis)
which
formulates
task
selection
based
safety,
environmental
considerations.
From
results
of
FMEA
research,
was
found
there
were
28
failure
modes
with
6
components
had
unacceptable
risk
level
critical
"very
critical"
so
LTA
carried
out
these
obtained
tasks
each
component,
namely
scheduled
condition
(HPU
pump,
Drag
Chain,
Hydraulic
Pipe)
redesign
(Flight
bar,
Flap
Plate).
Language: Английский
Assessing the impact of quality improvement on production defectiveness: a case study on an automotive manufacturing industry
Cogent Engineering,
Journal Year:
2024,
Volume and Issue:
11(1)
Published: Aug. 18, 2024
Overall
Equipment
Efficiency
(OEE)
is
a
crucial
performance
metric
for
manufacturing
production
efficiency.
Since
the
automotive
industry
vital
to
economy,
growing
demand
from
customers
and
competition
has
further
increased
need
optimised
through
an
OEE.
The
study
evaluates
volume
target
affected
by
quality
defects,
encompassing
calculations
of
First
Time
Capability
(FTC),
assesses
relationship
between
implementation
control
tools
contribution
losses
on
OEE
in
paint
shop
plants.
applies
mixed
method,
evaluating
various
defects
at
paint-shop
section
automobile
applying
both
qualitative
quantitative
identifying
nonconformities.
was
assessed
using
visual
inspection
thickness
measurement
range
4–7
mils
gauge
data
tools.
A
correlational
research
design
adopted
techniques
determine
correlation
output
knowledge
focus
group
charge
producing
inspecting
painting
output.
results
indicated
that
does
not
meet
targets
due
defects.
also
showed
approximately
78%
shop-floor
workers
were
deficient
significance
productivity.
In
comparison,
system
current
88.7%.
identified
missing
strategies
non-compliance
with
relevant
ISO-8504
standards.
Language: Английский
A Two-Stage Risk Assessment Method in Aviation Sector
International Journal of Advances in Engineering and Pure Sciences,
Journal Year:
2023,
Volume and Issue:
35(4), P. 460 - 484
Published: Dec. 29, 2023
Globalleşen
dünyada
havacılık
sektörü
en
önemli
ulaştırma
alanlarından
biri
olup,
iyileştirilip
geliştirilmesi
için
pek
çok
çalışma
yapılmaktadır.
Havaalanları
yolcu
trafiğinin
ve
yük
taşımacılığının
sıkı
takip
edildiği,
ufak
bir
aksaklığın
sektöre
maliyetinin
ciddi
seviyede
olacağı
stratejik
bölgelerdir.
Bu
çalışmada
havaalanlarında
meydana
gelen
hata
risk
türleri
belirlenerek
önleyici
bakım
planlama
faaliyetlerinin
amaçlanmaktadır.
açıdan
türü
etkileri
analizi
(HTEA)
yaklaşımı
kullanarak
havalimanı
yetkilileri
ile
görüşülerek
alınan
bilgiler
doğrultusunda
öncelik
sayısı
(RÖS)
ölçeği
belirlenmiştir.
Buna
göre
ilgili
türlerinin
önlenmesi
faaliyetler
sıralanmıştır.
Ayrıca
HTEA
yönteminin
eksikliğini
gidermek
objektif
yöntem
olan
Entropi
yaklaşımına
dayanan
karar
verme
yöntemi
ağırlıklandırarak
sınıflandırılmıştır.
hava
alanlarında
ortaya
çıkan
tehlike
durumları
iki
aşamalı
analitik
yaklaşımla
boyutlu
değerlendirilmektedir.
Elde
edilen
sonuçların,
alanı
yöneticilerinin
öncelikle
yapması
gereken
iyileştirme
yatırım
kararları
hakkında
yol
gösterici
olması
beklenmektedir.