Open this publication in new window or tab >>Show others...
2024 (English)In: Sustainable Production through Advanced Manufacturing, Intelligent Automation and Work Integrated Learning / [ed] Joel Andersson, Shrikant Joshi, Lennart Malmsköld, Fabian Hanning, IOS Press, 2024, Vol. 52, p. 27-38Conference paper, Published paper (Refereed)
Abstract [en]
Companies must enhance total maintenance effectiveness to staycompetitive, focusing on both digitalization and basic maintenance procedures.Digitalization offers technologies for data-driven decision-making, but manymaintenance decisions still lack a factual basis. Prioritizing efficiency andeffectiveness require analyzing equipment history, facilitated by usingComputerized Maintenance Management Systems (CMMS). However, CMMS dataoften contains unstructured free-text, leading to manual analysis, which is resourceintensiveand reactive, focusing on short time periods and specific equipment. Twoapproaches are available to solve the issue: minimizing free-text entries or usingadvanced methods for processing them. Free-text allows detailed descriptions butmay lack completeness, while structured reporting aids automated analysis but maylimit fault description richness. As knowledge and experience are vital assets forcompanies this research uses a hybrid approach by combining Natural LanguageProcessing with domain specific ontology and Large Language Models to extractinformation from free-text entries, enabling the possibility of real-time analysis e.g.,identifying recurring failure and knowledge sharing across global sites.
Place, publisher, year, edition, pages
IOS Press, 2024
Series
Advances in Transdisciplinary Engineering, ISSN 2352-751X, E-ISSN 2352-7528
Keywords
Industrial Maintenance, Artificial Intelligence, Natural Language Processing, Large Language Models, Experience Reuse
National Category
Information Systems
Identifiers
urn:nbn:se:liu:diva-203173 (URN)10.3233/ATDE240151 (DOI)001229990300003 ()2-s2.0-85191305248 (Scopus ID)9781643685106 (ISBN)9781643685113 (ISBN)
Conference
The 11th Swedish Production Symposium, Trollhättan, Sweden, April 23–26, 2024
Funder
Vinnova, 2019-05589
Note
Funding Agencies|Adapt 2030 project (Adaptive lifecycle design by applying digitalization and AI techniques to production) under Vinnova (Sweden's innovation agency) [2019-05589]; XPRES
2024-05-012024-05-012024-08-28Bibliographically approved