Leveraging LLM Agents and Digital Twins for Fault Handling in Process Plants

Advances in Automation and Artificial Intelligence continue to enhance the autonomy of process plants in handling various operational scenarios. However, certain tasks, such as fault handling, remain challenging, as they rely heavily on human expertise. This highlights the need for systematic, knowl...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE International Conference on Emerging Technologies and Factory Automation) s. 1 - 8
Hlavní autoři: Gill, Milapji Singh, Vyas, Javal, Markaj, Artan, Gehlhoff, Felix, Mercangoz, Mehmet
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 09.09.2025
Témata:
Artificial Intelligence
Autonomy
Digital twins
Fault Handling
Knowledge based systems
Knowledge engineering
Large language models
LLM Agents
Manufacturing automation
Process control
Process Plants
Systematics
ISSN:1946-0759
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Advances in Automation and Artificial Intelligence continue to enhance the autonomy of process plants in handling various operational scenarios. However, certain tasks, such as fault handling, remain challenging, as they rely heavily on human expertise. This highlights the need for systematic, knowledge-based methods. To address this gap, we propose a methodological framework that integrates Large Language Model (LLM) agents with a Digital Twin environment. The LLM agents continuously interpret system states and initiate control actions, including responses to unexpected faults, with the goal of returning the system to normal operation. In this context, the Digital Twin acts both as a structured repository of plant-specific engineering knowledge for agent prompting and as a simulation platform for the systematic validation and verification of the generated corrective control actions. The evaluation using a mixing module of a process plant demonstrates that the proposed framework is capable not only of autonomously controlling the mixing module, but also of generating effective corrective actions to mitigate a pipe clogging with only a few reprompts.
ISSN:1946-0759
DOI:10.1109/ETFA65518.2025.11205597