Large Language Model-based Chatbot for Improving Human-Centricity in Maintenance Planning and Operations

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Jun 27, 2024
Linus Kohl
Sarah Eschenbacher Philipp Besinger Fazel Ansari

Abstract

The recent advances on utilizing Generative Artificial Intelligence (GenAI) and Knowledge Graphs (KG) enforce a significant paradigm shift in data-driven maintenance management. GenAI and semantic technologies enable comprehensive analysis and exploitation of textual data sets, such as tabular data in maintenance databases, maintenance and inspection reports, and especially machine documentation. Traditional approaches to maintenance planning and execution rely primarily on static, non-adaptive simulation models. These models have inherent limitations in accounting for dynamic environmental changes and effectively responding to unanticipated, ad hoc events.

This paper introduces a maintenance chatbot that enhances planning and operations, offering empathetic support to technicians and engineers, boosting efficiency, decision-making, and on-the-job satisfaction. It optimizes shift scheduling and task allocation by considering technicians' skills, physical stress, and psychological state, thus reducing cognitive stress. The approach ultimately improves human performance and reliability, embodying a human-centricity in the domain of maintenance and health management.

The practical impact of the maintenance chatbot is illustrated through its application in maintenance of railway cooling systems. The presented use case demonstrates the chatbot's potential as a transformative tool in maintenance management. Finally, the paper discusses the theoretical and practical considerations, in particular in the light of regulative frameworks such as EU AI ACT, highlighting the future pathways for complying with responsible AI requirements.

How to Cite

Kohl, L., Eschenbacher, S., Besinger, P., & Ansari, F. (2024). Large Language Model-based Chatbot for Improving Human-Centricity in Maintenance Planning and Operations. PHM Society European Conference, 8(1), 12. https://doi.org/10.36001/phme.2024.v8i1.4098
Abstract 602 | PDF Downloads 265

##plugins.themes.bootstrap3.article.details##

Keywords

GenAI, Technical Language Processing, Knowledge Graph

References
Abu-Rasheed, Hasan; Abdulsalam, Mohamad Hussam; Weber, Christian; Fathi, Madjid (2024): Supporting Student Decisions on Learning Recommendations: An LLM-Based Chatbot with Knowledge Graph Contextualization for Conversational Explainability and Mentoring. Online verfügbar unter http://arxiv.org/pdf/2401.08517v3.
Agarwal, Oshin; Ge, Heming; Shakeri, Siamak; Al-Rfou, Rami (2020): Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training. Online verfügbar unter http://arxiv.org/pdf/2010.12688v2.
Alavi, Maryam; Leidner, Dorothy E.; Mousavi, Reza (2024): Knowledge Management Perspective of Generative Artificial Intelligence. In: JAIS 25 (1), S. 1–12. DOI: 10.17705/1jais.00859.
Ansari, Fazel (2019): Knowledge Management 4.0: Theoretical and Practical Considerations in Cyber Physical Production Systems. In: IFAC-PapersOnLine 52 (13), S. 1597–1602. DOI: 10.1016/j.ifacol.2019.11.428.
Ansari, Fazel (2020): Cost-based text understanding to improve maintenance knowledge intelligence in manufacturing enterprises. In: Computers & Industrial Engineering 141, S. 106319. DOI: 10.1016/j.cie.2020.106319.
Ansari, Fazel; Glawar, Robert; Nemeth, Tanja (2019): PriMa: a prescriptive maintenance model for cyber-physical production systems. In: International Journal of Computer Integrated Manufacturing 32 (4-5), S. 482–503. DOI: 10.1080/0951192X.2019.1571236.
Ansari, Fazel; Hold, Philipp; Khobreh, Marjan (2020): A knowledge-based approach for representing jobholder profile toward optimal human–machine collaboration in cyber physical production systems. In: CIRP Journal of Manufacturing Science and Technology 28, S. 87–106. DOI: 10.1016/j.cirpj.2019.11.005.
Ansari, Fazel; Kohl, Linus; Giner, Jakob; Meier, Horst (2021): Text mining for AI enhanced failure detection and availability optimization in production systems. In: CIRP Annals 70 (1), S. 373–376. DOI: 10.1016/j.cirp.2021.04.045.
Ansari, Fazel; Kohl, Linus; Sihn, Wilfried (2023): A competence-based planning methodology for optimizing human resource allocation in industrial maintenance. In: CIRP Annals 72 (1), S. 389–392. DOI: 10.1016/j.cirp.2023.04.050.
Besinger, Philipp; Vejnoska, Daniel; Ansari, Fazel (2024): Responsible AI (RAI) in Manufacturing: A Qualitative Framework. In: Procedia Computer Science 232, S. 813–822. DOI: 10.1016/j.procs.2024.01.081.
Birhane, Abeba; Kasirzadeh, Atoosa; Leslie, David; Wachter, Sandra (2023): Science in the age of large language models. In: Nat Rev Phys 5 (5), S. 277–280. DOI: 10.1038/s42254-023-00581-4.
Brown, Tom B.; Mann, Benjamin; Ryder, Nick; Subbiah, Melanie; Kaplan, Jared; Dhariwal, Prafulla et al. (2020): Language Models are Few-Shot Learners. Online verfügbar unter http://arxiv.org/pdf/2005.14165v4.
Burggräf, Peter; Dannapfel, Matthias; Adlon, Tobias; Föhlisch, Nils (2021): Adaptive assembly systems for enabling agile assembly – Empirical analysis focusing on cognitive worker assistance. In: Procedia CIRP 97, S. 319–324. DOI: 10.1016/j.procir.2020.05.244.
Eloundou, Tyna; Manning, Sam; Mishkin, Pamela; Rock, Daniel (2023): GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models. Online verfügbar unter http://arxiv.org/pdf/2303.10130v5.
Engelmann, Débora C.; Panisson, Alison R.; Vieira, Renata; Hübner, Jomi Fred; Mascardi, Viviana; Bordini, Rafael H. (2023): MAIDS — A Framework for the Development of Multi-Agent Intentional Dialogue Systems. In: Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems (AAMAS '23), S. 1209–1217.
European Commission (2023): Employment and social developments in Europe 2023. Luxembourg: Publications Office of the European Union (Employment and social developments in Europe 2023).
European Commission (2024): EU AI Act. Article 52, Transparency Obligations for Providers and Users of Certain AI Systems and GPAI Models. Online verfügbar unter https://www.euaiact.com/article/52, zuletzt geprüft am 27.03.2024.
Fensel, Dieter; Şimşek, Umutcan; Angele, Kevin; Huaman, Elwin; Kärle, Elias; Panasiuk, Oleksandra et al. (2020): Introduction: What Is a Knowledge Graph? In: Dieter Fensel, Umutcan Şimşek, Kevin Angele, Elwin Huaman, Elias Kärle, Oleksandra Panasiuk et al. (Hg.): Knowledge Graphs. Cham: Springer International Publishing, S. 1–10.
Freire, Samuel Kernan; Panicker, Sarath Surendranadha; Ruiz-Arenas, Santiago; Rusák, Zoltán; Niforatos, Evangelos (2023): A Cognitive Assistant for Operators: AI-Powered Knowledge Sharing on Complex Systems. In: IEEE Pervasive Comput. 22 (1), S. 50–58. DOI: 10.1109/MPRV.2022.3218600.
Gozalo-Brizuela, Roberto; Garrido-Merchan, Eduardo C. (2023): ChatGPT is not all you need. A State of the Art Review of large Generative AI models. Online verfügbar unter http://arxiv.org/pdf/2301.04655v1.
Han, Yu; Tao, Jingwen (2024): Revolutionizing Pharma: Unveiling the AI and LLM Trends in the Pharmaceutical Industry. Online verfügbar unter http://arxiv.org/pdf/2401.10273v2.
Huang, Xu; Liu, Weiwen; Chen, Xiaolong; Wang, Xingmei; Wang, Hao; Lian, Defu et al. (2024): Understanding the planning of LLM agents: A survey. Online verfügbar unter http://arxiv.org/pdf/2402.02716v1.
Introduction to Rasa Open Source & Rasa Pro (2024). Online verfügbar unter https://rasa.com/docs/rasa/, zuletzt aktualisiert am 22.03.2024.
Ito, Takumi; Kuribayashi, Tatsuki; Hidaka, Masatoshi; Suzuki, Jun; Inui, Kentaro (2020): Langsmith: An Interactive Academic Text Revision System. Online verfügbar unter http://arxiv.org/pdf/2010.04332v1.
Iyyer, Mohit; Yih, Wen-tau; Chang, Ming-Wei (2016): Answering Complicated Question Intents Expressed in Decomposed Question Sequences. Online verfügbar unter http://arxiv.org/pdf/1611.01242v1.
Jiang, Zhiqiu; Rashik, Mashrur; Panchal, Kunjal; Jasim, Mahmood; Sarvghad, Ali; Riahi, Pari et al. (2023): CommunityBots: Creating and Evaluating A Multi-Agent Chatbot Platform for Public Input Elicitation. In: Proc. ACM Hum.-Comput. Interact. 7 (CSCW1), S. 1–32. DOI: 10.1145/3579469.
Jing, Zhi; Su, Yongye; Han, Yikun; Yuan, Bo; Xu, Haiyun; Liu, Chunjiang et al. (2024): When Large Language Models Meet Vector Databases: A Survey. Online verfügbar unter http://arxiv.org/pdf/2402.01763v2.
Kang, Yue; Cai, Zhao; Tan, Chee-Wee; Huang, Qian; Liu, Hefu (2020): Natural language processing (NLP) in management research: A literature review. In: Journal of Management Analytics 7 (2), S. 139–172. DOI: 10.1080/23270012.2020.1756939.
Kernan Freire, Samuel; Foosherian, Mina; Wang, Chaofan; Niforatos, Evangelos (2023): Harnessing Large Language Models for Cognitive Assistants in Factories. In: Minha Lee, Cosmin Munteanu, Martin Porcheron, Johanne Trippas und Sarah Theres Völkel (Hg.): Proceedings of the 5th International Conference on Conversational User Interfaces. CUI '23: ACM conference on Conversational User Interfaces. Eindhoven Netherlands, 19 07 2023 21 07 2023. New York, NY, USA: ACM, S. 1–6.
Kohl, Linus; Ansari, Fazel (2023a): A Knowledge Graph-based Learning Assistance Systems for Industrial Maintenance, in press.
Kohl, Linus; Ansari, Fazel (2023b): Chatbots in der Instandhaltungsplanung: Industrielle Anwendungsfälle und zukünftige Perspektiven: ÖVIA Kongress.
Kostolani, David; Wollendorfer, Michael; Schlund, Sebastian (2022): ErgoMaps: Towards Interpretable and Accessible Automated Ergonomic Analysis. In: 2022 IEEE 3rd International Conference on Human-Machine Systems (ICHMS). 2022 IEEE 3rd International Conference on Human-Machine Systems (ICHMS). Orlando, FL, USA, 17.11.2022 - 19.11.2022: IEEE, S. 1–7.
Li, Yunqing; Raman, Shivakumar; Cohen, Paul; Starly, Binil (2021): Design of Knowledge Graph in Manufacturing Services Discovery. In: Volume 2: Manufacturing Processes; Manufacturing Systems; Nano/Micro/Meso Manufacturing; Quality and Reliability. ASME 2021 16th International Manufacturing Science and Engineering Conference. Virtual, Online, 21.06.2021 - 25.06.2021: American Society of Mechanical Engineers.
Listl, Franz Georg; Fischer, Jan; Weyrich, Michael (2021): Towards a Simulation-based Conversational Assistant for the Operation and Engineering of Production Plants. In: 2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA ). 2021 IEEE 26th International Conference on Emerging Technologies and Factory Automation (ETFA). Vasteras, Sweden, 07.09.2021 - 10.09.2021: IEEE, S. 1–4.
Margaria, Tiziana; Schieweck, Alexander (2019): The Digital Thread in Industry 4.0. In: Wolfgang Ahrendt und Silvia Lizeth Tapia Tarifa (Hg.): Integrated Formal Methods, Bd. 11918. Cham: Springer International Publishing (Lecture Notes in Computer Science), S. 3–24.
Mark, Benedikt G.; Rauch, Erwin; Matt, Dominik T. (2021): Worker assistance systems in manufacturing: A review of the state of the art and future directions. In: Journal of Manufacturing Systems 59, S. 228–250. DOI: 10.1016/j.jmsy.2021.02.017.
Noy, Shakked; Zhang, Whitney (2023): Experimental evidence on the productivity effects of generative artificial intelligence. In: Science (New York, N.Y.) 381 (6654), S. 187–192. DOI: 10.1126/science.adh2586.
OECD Artificial Intelligence Papers (2024).
Pan, Shirui; Luo, Linhao; Wang, Yufei; Chen, Chen; Wang, Jiapu; Wu, Xindong (2024): Unifying Large Language Models and Knowledge Graphs: A Roadmap. In: IEEE Trans. Knowl. Data Eng., S. 1–20. DOI: 10.1109/TKDE.2024.3352100.
Pokorni, Bastian; Constantinescu, Carmen (2021): Design and Configuration of Digital Assistance Systems in Manual Assembly of Variant-rich Products based on Customer Journey Mapping. In: Procedia CIRP 104, S. 1777–1782. DOI: 10.1016/j.procir.2021.11.299.
Razouk, Houssam; Liu, Xing Lan; Kern, Roman (2023): Improving FMEA Comprehensibility via Common-Sense Knowledge Graph Completion Techniques. In: IEEE Access 11, S. 127974–127986. DOI: 10.1109/ACCESS.2023.3331585.
DIN 91345, 2016: Referenzarchitekturmodell Industrie 4.0 (RAMI4.0).
Romero, David; Stahre, Johan (2021): Towards The Resilient Operator 5.0: The Future of Work in Smart Resilient Manufacturing Systems. In: Procedia CIRP 104, S. 1089–1094. DOI: 10.1016/j.procir.2021.11.183.
Rožanec, Jože M.; Lu, Jinzhi; Rupnik, Jan; Škrjanc, Maja; Mladenić, Dunja; Fortuna, Blaž et al. (2022): Actionable cognitive twins for decision making in manufacturing. In: International Journal of Production Research 60 (2), S. 452–478. DOI: 10.1080/00207543.2021.2002967.
Saboo, S.; Shekhawat, D. (2024): Enhancing Predictive Maintenance in an Oil & Gas Refinery Using IoT, AI & ML: An Generative AI Solution. In: Day 3 Wed, February 14, 2024. International Petroleum Technology Conference. Dhahran, Saudi Arabia, 12.02.2024 - 12.02.2024: IPTC.
Shin, Won; Han, Jeongyun; Rhee, Wonjong (2021): AI-assistance for predictive maintenance of renewable energy systems. In: Energy 221, S. 119775. DOI: 10.1016/j.energy.2021.119775.
Sorin, Vera; Brin, Danna; Barash, Yiftach; Konen, Eli; Charney, Alexander; Nadkarni, Girish; Klang, Eyal (2023): Large Language Models (LLMs) and Empathy – A Systematic Review.
Sun, Yicheng; Zhang, Qi; Bao, Jinsong; Lu, Yuqian; Liu, Shimin (2024): Empowering digital twins with large language models for global temporal feature learning. In: Journal of Manufacturing Systems 74, S. 83–99. DOI: 10.1016/j.jmsy.2024.02.015.
Touvron, Hugo; Martin, Louis; Stone, Kevin; Albert, Peter; Almahairi, Amjad; Babaei, Yasmine et al. (2023): Llama 2: Open Foundation and Fine-Tuned Chat Models. Online verfügbar unter http://arxiv.org/pdf/2307.09288v2.
Wang, Yuxia; Li, Haonan; Han, Xudong; Nakov, Preslav; Baldwin, Timothy (2023): Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs. Online verfügbar unter https://doi.org/10.48550/arXiv.2308.13387.
Wang, Zhuo; Bai, Xiaoliang; Zhang, Shusheng; Billinghurst, Mark; He, Weiping; Wang, Peng et al. (2022): A comprehensive review of augmented reality-based instruction in manual assembly, training and repair. In: Robotics and Computer-Integrated Manufacturing 78, S. 102407. DOI: 10.1016/j.rcim.2022.102407.
Wu, Qingyun; Bansal, Gagan; Zhang, Jieyu; Wu, Yiran; Li, Beibin; Zhu, Erkang et al. (2023): AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation. Online verfügbar unter http://arxiv.org/pdf/2308.08155v2.
Xi, Zhiheng; Chen, Wenxiang; Guo, Xin; He, Wei; Ding, Yiwen; Hong, Boyang et al. (2023): The Rise and Potential of Large Language Model Based Agents: A Survey. Online verfügbar unter http://arxiv.org/pdf/2309.07864v3.
Yu, Hong Qing (2021): Dynamic Causality Knowledge Graph Generation for Supporting the Chatbot Healthcare System. In: Kohei Arai, Supriya Kapoor und Rahul Bhatia (Hg.): Proceedings of the Future Technologies Conference (FTC) 2020, Volume 3, Bd. 1290. Cham: Springer International Publishing (Advances in Intelligent Systems and Computing), S. 30–45.
Yu, Wenhao (2022): Retrieval-augmented Generation across Heterogeneous Knowledge. In: Daphne Ippolito, Liunian Harold Li, Maria Leonor Pacheco, Danqi Chen und Nianwen Xue (Hg.): Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop. Hybrid: Seattle, Washington + Online. Stroudsburg, PA, USA: Association for Computational Linguistics, S. 52–58.
Zhao, Andrew; Huang, Daniel; Xu, Quentin; Lin, Matthieu; Liu, Yong-Jin; Huang, Gao (2023): ExpeL: LLM Agents Are Experiential Learners. Online verfügbar unter http://arxiv.org/pdf/2308.10144v2.
Zheng, Xiaochen; Lu, Jinzhi; Kiritsis, Dimitris (2022): The emergence of cognitive digital twin: vision, challenges and opportunities. In: International Journal of Production Research 60 (24), S. 7610–7632. DOI: 10.1080/00207543.2021.2014591.
Zhou, Bin; Li, Xinyu; Liu, Tianyuan; Xu, Kaizhou; Liu, Wei; Bao, Jinsong (2024): CausalKGPT: Industrial structure causal knowledge-enhanced large language model for cause analysis of quality problems in aerospace product manufacturing. In: Advanced Engineering Informatics 59, S. 102333. DOI: 10.1016/j.aei.2023.102333.
Zhu, Yinghao; Ren, Changyu; Xie, Shiyun; Liu, Shukai; Ji, Hangyuan; Wang, Zixiang et al. (2024): REALM: RAG-Driven Enhancement of Multimodal Electronic Health Records Analysis via Large Language Models. Online verfügbar unter http://arxiv.org/pdf/2402.07016v1.
Zigart, Tanja; Schlund, Sebastian (2020): Evaluation of Augmented Reality Technologies in Manufacturing – A Literature Review. In: Isabel L. Nunes (Hg.): Advances in Human Factors and Systems Interaction, Bd. 1207. Cham: Springer International Publishing (Advances in Intelligent Systems and Computing), S. 75–82.
Section
Technical Papers