Advancing Capability Matching in Manufacturing Reconfiguration with Large Language Models

Mo, Fan; Chaplin, Jack C.; Sanderson, David; Ratchev, Svetan

Abstract

This paper introduces an approach that integrates Natural Language Processing (NLP) and knowledge graphs with Reconfigurable Manufacturing Systems (RMS) to enhance flexibility and adaptability. We utilize a chatbot interface powered by GPT-4 and a structured knowledge base to simplify the complexities of manufacturing reconfiguration. This system not only boosts reconfiguration efficiency but also broadens accessibility to advanced manufacturing technologies. We demonstrate our methodology through an application in capability matching, showcasing how it facilitates the identification of assets for new product requirements. Our results indicate that this integrated solution offers a scalable and user-friendly approach to overcoming adaptability challenges in modern manufacturing environments.

Citation

Mo, F., Chaplin, J. C., Sanderson, D., & Ratchev, S. (2024, June). Advancing Capability Matching in Manufacturing Reconfiguration with Large Language Models. Presented at International Conference on Flexible Automation and Intelligent Manufacturing, Taichung, Taiwan

• Presentation Conference Type: Conference Paper (published)
• Conference Name: International Conference on Flexible Automation and Intelligent Manufacturing
• Start Date: Jun 23, 2024
• End Date: Jun 26, 2024
• Online Publication Date: Dec 13, 2024
• Publication Date: Jan 1, 2024
• Deposit Date: Mar 21, 2025
• Publicly Available Date: Mar 25, 2025
• Print ISSN: 2195-4356
• Electronic ISSN: 2195-4364
• Peer Reviewed: Peer Reviewed
• Pages: 215-222
• Series Title: Lecture Notes in Mechanical Engineering
• Series ISSN: 2195-4356
• Book Title: Flexible Automation and Intelligent Manufacturing: Manufacturing Innovation and Preparedness for the Changing World Order: Proceedings of FAIM 2024, June 23–26, 2024, Taichung, Taiwan, Volume 2
• ISBN: 9783031744846
• DOI: https://doi.org/10.1007/978-3-031-74485-3_24
• Public URL: https://nottingham-repository.worktribe.com/output/44824843
• Publisher URL: https://link.springer.com/chapter/10.1007/978-3-031-74485-3_24