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

TL;DR

This paper presents a novel framework combining Large Language Model agents with Digital Twins to autonomously handle faults in process plants, improving operational safety and efficiency.

Contribution

It introduces an integrated approach that uses LLM agents and Digital Twins for fault detection, interpretation, and correction in process plant operations.

Findings

Successfully controls a process plant mixing module autonomously.

Generates effective corrective actions with minimal prompts.

Demonstrates potential for fault handling in industrial settings.

Abstract

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.