Natural Language Control System for Automated Manufacturing Plant
DOI:
https://doi.org/10.17979/ja-cea.2026.47.13862Keywords:
Large Language Models, Manufacturing plant control, Intelligent manufacturing systems, Intelligent interfaces, Human-centered automation and design, Programmable logic controllers, Industrial communication protocols.Abstract
Thanks to the appearance and rise in popularity of Large Language Models (LLMs), new systems capable of interaction with industrial processes through natural language have started to emerge, complementing traditional interfaces and making control systems more versatile. This article develops a system that uses LLMs as part of an autonomous agent, which is capable of controlling different parts of an automated manufacturing plant by voice. The agent is able to interact with a SQL database, and can also access Programmable Logic Controller (PLC) inputs and outputs via the industrial protocol OPC-UA. Finally, the system was implemented and tested in a physical manufacturing plant within Instituto de Automática e Informática Industrial of Universitat Politécnica de València, where a success rate of 98.5 % was achieved for simple instructions and 81 % for complex ones, with an average response time less than 12.5 seconds.
References
Ball, T., Chen, S., Herley, C., 2024. Can we count on llms? the fixed-effect fallacy and claims of gpt-4 capabilities. Microsoft Research. DOI: 10.48550/arXiv.2409.07638
Fu, T., Ferrando, R., Conde, J., Arriaga, C., Reviriego, P., 2023. Why do large language models (llms) struggle to count letters? Association for Computing Machinery. DOI: 10.48550/arXiv.2412.18626
Hernández, J., Barrios, E. J., Diaz-Aleman, S. A. T., 2025. Aplicación de grandes modelos de lenguaje en diagnóstico de glaucoma. Jornadas de Automática, 46. DOI: 10.17979/ja-cea.2025.46.12085
Hofmanna, B., Piechuleka, N., Kreitleina, S., Frankea, J., Br¨undl, P., 2025. Beyond touch-based human-machine interface: Control your machines in natural language by utilizing large language models and opc ua. Manufacturing Review. DOI: 10.48550/arXiv.2510.11300
Menéndez, E., Garcia-Haro, J. M., Martínez, S., Balaguer, C., 2025. Integración modular de herramientas gestionadas por llms en el robot tiago++. Jornadas de Automática, 46. DOI: 10.17979/ja-cea.2025.46.12229
Merino-Fidalgo, S., Zalama, E., Gómez-García-Bermejo, J., Duque-Domingo, J., 2025. Generación y ajuste dinámico de behavior trees mediante llms para el control de un robot social. Jornadas de Automática, 46. DOI: 10.17979/ja-cea.2025.46.12071
Mohammadjafari, A., Maida, A. S., Gottumukkala, R., 2025. From natural language to sql: Review of llm-based text-to-sql systems. Cornell University. DOI: 10.48550/arXiv.2410.01066
San Emeterio de la Parte, M., Wang, Y., Martínez-Ortega, J. F., Martínez, N. L., 2026. A secure and efficient llm-based system for natural language query-to-sql translation in iot data management. IEEE Access. DOI: 10.1109/ACCESS.2026.3665980
Sarkar, S., Ghorbanpour, S., Guti´errez, R. L., Guill´en-P´erez, A., Gundecha, V., Babu, A. R., Naug, A., 2025. Review of llm based control. Hewlett Packard Labs at Hewlett Packard Enterprise. DOI: 10.13140/RG.2.2.28595.54567
Velesaca, H. O., Holgado-Terriza, J. A., 2025. Opc-ua in artificial intelligence: a systematic review of the integration of data mining and nlp in industrial processes. Manufacturing Review. DOI: 10.1051/mfreview/2025003
Xia, Y., Jazdi, N., Weyrich, M., 2024. Applying large language models for intelligent industrial automation. Universidad de Stuttgart. DOI: 10.17560/atp.v66i6-7.2739
Xia, Y., Jazdi, N., Weyrich, M., 2025. Control industrial automation system with large language model agents. IEEE International Conference on Emerging Technologies and Factory Automation. DOI: 10.48550/arXiv.2409.18009
Zhao, L., Liu, S., Xin, T., Tan, J., Wang, X., Li, Y., Bian, Z., Chen, Y., Kong, F., Bian, J., Qian, C., Zhang, Z., 2026. Ai agent in healthcare: applications, evaluations, and future directions. npj Artificial Intelligence. DOI: 10.1038/s44387-026-00076-4
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Daniel Quesada-Lobo, Francisco Blanes-Noguera, Juan Carlos Brenes-Torres
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
