Ontology-integrated tuning of large language model for intelligent maintenance

Peng Wang; John Karigiannis; Robert X. Gao

doi:10.1016/j.cirp.2024.04.012

Ontology-integrated tuning of large language model for intelligent maintenance

Peng Wang
, John Karigiannis
, Robert X. Gao

Producción científica: Article › revisión exhaustiva

37 Citas (Scopus)

Resumen

As new AI technologies such as Large Language Models (LLM) quickly evolve, the need for enhancing general-purpose LLMs with physical knowledge to better serve the manufacturing community has been increasingly recognized. This paper presents a method that tailors GPT-3.5 with domain-specific knowledge for intelligent aircraft maintenance. Specifically, aircraft ontology is investigated to curate maintenance logs with encoded component hierarchical structure to fine-tune GPT-3.5. Experimental results demonstrate the effectiveness of the developed method in accurately identifying defective components and providing consistent maintenance action recommendations, outperforming general-purpose GPT-3.5 and GPT-4.0. The method can be adapted to other domains in manufacturing and beyond.

Idioma original	English
Páginas (desde-hasta)	361-364
Número de páginas	4
Publicación	CIRP Annals
Volumen	73
N.º	1
DOI	https://doi.org/10.1016/j.cirp.2024.04.012
Estado	Published - ene 2024

Nota bibliográfica

Publisher Copyright:
© 2024 The Author(s)

Financiación

The authors would like to thank Dr. Jianjing Zhang from Case Western Reserve University for his valuable contributions. Support from the National Science Foundation under awards CMMI- 2237242 , CNS- 2125460 , and EEC- 2133630 (Engineering Research Center on Hybrid and Autonomous Manufacturing – Moving from Evolution to Revolution) is sincerely appreciated.

Financiadores	Número del financiador
National Science Foundation Arctic Social Science Program	CMMI- 2237242, CNS- 2125460, EEC- 2133630

ASJC Scopus subject areas

Mechanical Engineering
Industrial and Manufacturing Engineering

Acceder al documento

10.1016/j.cirp.2024.04.012

Otros archivos y enlaces

Citar esto

@article{03c998e8bd384d1c8ed1a2a774f720f6,

title = "Ontology-integrated tuning of large language model for intelligent maintenance",

abstract = "As new AI technologies such as Large Language Models (LLM) quickly evolve, the need for enhancing general-purpose LLMs with physical knowledge to better serve the manufacturing community has been increasingly recognized. This paper presents a method that tailors GPT-3.5 with domain-specific knowledge for intelligent aircraft maintenance. Specifically, aircraft ontology is investigated to curate maintenance logs with encoded component hierarchical structure to fine-tune GPT-3.5. Experimental results demonstrate the effectiveness of the developed method in accurately identifying defective components and providing consistent maintenance action recommendations, outperforming general-purpose GPT-3.5 and GPT-4.0. The method can be adapted to other domains in manufacturing and beyond.",

keywords = "Large language models, Machine learning, Maintenance",

author = "Peng Wang and John Karigiannis and Gao, \{Robert X.\}",

note = "Publisher Copyright: {\textcopyright} 2024 The Author(s)",

year = "2024",

month = jan,

doi = "10.1016/j.cirp.2024.04.012",

language = "English",

volume = "73",

pages = "361--364",

number = "1",

}

TY - JOUR

T1 - Ontology-integrated tuning of large language model for intelligent maintenance

AU - Wang, Peng

AU - Karigiannis, John

AU - Gao, Robert X.

PY - 2024/1

Y1 - 2024/1

N2 - As new AI technologies such as Large Language Models (LLM) quickly evolve, the need for enhancing general-purpose LLMs with physical knowledge to better serve the manufacturing community has been increasingly recognized. This paper presents a method that tailors GPT-3.5 with domain-specific knowledge for intelligent aircraft maintenance. Specifically, aircraft ontology is investigated to curate maintenance logs with encoded component hierarchical structure to fine-tune GPT-3.5. Experimental results demonstrate the effectiveness of the developed method in accurately identifying defective components and providing consistent maintenance action recommendations, outperforming general-purpose GPT-3.5 and GPT-4.0. The method can be adapted to other domains in manufacturing and beyond.

AB - As new AI technologies such as Large Language Models (LLM) quickly evolve, the need for enhancing general-purpose LLMs with physical knowledge to better serve the manufacturing community has been increasingly recognized. This paper presents a method that tailors GPT-3.5 with domain-specific knowledge for intelligent aircraft maintenance. Specifically, aircraft ontology is investigated to curate maintenance logs with encoded component hierarchical structure to fine-tune GPT-3.5. Experimental results demonstrate the effectiveness of the developed method in accurately identifying defective components and providing consistent maintenance action recommendations, outperforming general-purpose GPT-3.5 and GPT-4.0. The method can be adapted to other domains in manufacturing and beyond.

KW - Large language models

KW - Machine learning

KW - Maintenance

UR - https://www.scopus.com/pages/publications/85195267530

UR - https://www.scopus.com/pages/publications/85195267530#tab=citedBy

U2 - 10.1016/j.cirp.2024.04.012

DO - 10.1016/j.cirp.2024.04.012

M3 - Article

AN - SCOPUS:85195267530

SN - 0007-8506

VL - 73

SP - 361

EP - 364

JO - CIRP Annals

JF - CIRP Annals

IS - 1

ER -

Ontology-integrated tuning of large language model for intelligent maintenance

Resumen

Nota bibliográfica

Financiación

ASJC Scopus subject areas

Acceder al documento

Otros archivos y enlaces

Huella

Citar esto