Knowledge extraction for additive manufacturing process via named entity recognition with LLMs

Simple item page
dc.contributor.authorLiu, Xuan
dc.contributor.authorErkoyuncu, John Ahmet
dc.contributor.authorFuh, Jerry Ying Hsi
dc.contributor.authorLu, Wen Feng
dc.contributor.authorLi, Bingbing
dc.date.accessioned2024-12-13T11:36:04Z
dc.date.available2024-12-13T11:36:04Z
dc.date.freetoread2024-12-13
dc.date.issued2025-06-01
dc.date.pubOnline2024-11-21
dc.description.abstractThis paper proposes a novel NER framework, leveraging the advanced capabilities of Large Language Models (LLMs), to address the limitations of manually defined taxonomy. Our framework integrates the expert knowledge internalized in both academic materials and LLMs through retrieval-augmented generation (RAG) to automatically customize taxonomies for specific manufacturing processes and adopts two distinct strategies of using LLMs — In-Context Learning (ICL) and fine-tuning to complete manufacturing NER tasks with minimal training data. We demonstrate the framework efficiency through its superior ability to define precise taxonomies, identify and classify process-level entities related to the most popular additive manufacturing process fused deposition modeling (FDM) as case study, achieving a high F1 score of 0.9192.
dc.description.journalNameRobotics and Computer-Integrated Manufacturing
dc.description.sponsorshipDirectorate for Computer & Information Science & Engineering, United States Department of Energy
dc.description.sponsorshipThis research is funded by the U.S. Department of Energy (DOE) Office of Manufacturing and Energy Supply Chains (DE-EE0009726). We acknowledge Prof. Larry Smarr and Prof. Thomas DeFanti from University of California San Diego for HyperCluster computing support of San Diego Supercomputer Center (SDSC) National Research Platform (NRP) Nautilus sponsored by the U.S. National Science Foundation (NSF) (2100237, 2120019).
dc.identifier.citationLiu X, Erkoyuncu JA, Fuh JYH, et al., (2025) Knowledge extraction for additive manufacturing process via named entity recognition with LLMs. Robotics and Computer-Integrated Manufacturing, Volume 93, June 2025, Article number 102900
dc.identifier.elementsID559286
dc.identifier.issn0736-5845
dc.identifier.paperNo102900
dc.identifier.urihttps://doi.org/10.1016/j.rcim.2024.102900
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/23263
dc.identifier.volumeNo93
dc.languageEnglish
dc.language.isoen
dc.publisherElsevier
dc.publisher.urihttps://www.sciencedirect.com/science/article/pii/S073658452400187X?via%3Dihub
dc.rightsAttribution-NonCommercial 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/
dc.subject4605 Data Management and Data Science
dc.subject46 Information and Computing Sciences
dc.subject4014 Manufacturing Engineering
dc.subject40 Engineering
dc.subjectIndustrial Engineering & Automation
dc.subject40 Engineering
dc.subject46 Information and computing sciences
dc.titleKnowledge extraction for additive manufacturing process via named entity recognition with LLMs
dc.typeArticle
dc.type.subtypeJournal Article
dcterms.dateAccepted2024-11-06

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Knowledge_extraction_for_additive_manufacturing_process-2024.pdf
Size:
2.28 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Plain Text
Description:
Download

Collections

Staff publications (SATM)