Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Integrating large language models for improved failure mode and effects analysis (FMEA) : a framework and case study

El Hassani, Ibtissam ; Masrour, Tawfik ; Kourouma, Nouhan ; Motte, Damien LU orcid and Tavčar, Jože LU (2024) 18th International Design Conference, DESIGN 2024 In Proceedings of the Design Society 4. p.2019-2028
Abstract
The manual execution of failure mode and effects analysis (FMEA) is time-consuming and error-prone. This article presents an approach in which large language models (LLMs) are integrated into FMEA. LLMs improve and accelerate FMEA with human in the loop. The discussion looks at software tools for FMEA and emphasizes that the tools must be tailored to the needs of the company. Our framework combines data collection, pre-processing and reliability assessment to automate FMEA. A case study validates this framework and demonstrates its efficiency and accuracy compared to manual FMEA.
Please use this url to cite or link to this publication:
author
; ; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Failure mode and effect analysis, FMEA, Large language models, LLM, Generative AI, Product quality, Knowledge management
host publication
Proceedings of the Design Society. International Design Conference, DESIGN 2024 20-24 May 2024, Dubrovnik, Croatia
series title
Proceedings of the Design Society
volume
4
pages
2019 - 2028
publisher
Cambridge University Press
conference name
18th International Design Conference, DESIGN 2024
conference location
Dubrovnik, Croatia
conference dates
2024-05-20 - 2024-05-24
external identifiers
  • scopus:85194055333
ISSN
2732-527X
DOI
10.1017/pds.2024.204
language
English
LU publication?
yes
id
7ffa6f5a-a076-4f36-a3a3-2be834489485
date added to LUP
2024-05-25 15:45:35
date last changed
2024-06-14 15:03:29
@inproceedings{7ffa6f5a-a076-4f36-a3a3-2be834489485,
  abstract     = {{The manual execution of failure mode and effects analysis (FMEA) is time-consuming and error-prone. This article presents an approach in which large language models (LLMs) are integrated into FMEA. LLMs improve and accelerate FMEA with human in the loop. The discussion looks at software tools for FMEA and emphasizes that the tools must be tailored to the needs of the company. Our framework combines data collection, pre-processing and reliability assessment to automate FMEA. A case study validates this framework and demonstrates its efficiency and accuracy compared to manual FMEA.}},
  author       = {{El Hassani, Ibtissam and Masrour, Tawfik and Kourouma, Nouhan and Motte, Damien and Tavčar, Jože}},
  booktitle    = {{Proceedings of the Design Society. International Design Conference, DESIGN 2024 20-24 May 2024, Dubrovnik, Croatia}},
  issn         = {{2732-527X}},
  keywords     = {{Failure mode and effect analysis; FMEA; Large language models; LLM; Generative AI; Product quality; Knowledge management}},
  language     = {{eng}},
  pages        = {{2019--2028}},
  publisher    = {{Cambridge University Press}},
  series       = {{Proceedings of the Design Society}},
  title        = {{Integrating large language models for improved failure mode and effects analysis (FMEA) : a framework and case study}},
  url          = {{https://lup.lub.lu.se/search/files/187654730/ElHassani_al_Design2024.pdf}},
  doi          = {{10.1017/pds.2024.204}},
  volume       = {{4}},
  year         = {{2024}},
}