Control Industrial Automation System with Large Language Model Agents

TL;DR

This paper presents a novel framework integrating large language models into industrial automation systems, enabling real-time control, adaptive responses, and natural language operation, demonstrated through a proof-of-concept implementation.

Contribution

It introduces a formal system design, structured prompting, and a dataset creation method for fine-tuning LLMs specifically for industrial control tasks.

Findings

Enables real-time event-driven control of industrial systems by LLMs.

Supports natural language interaction for easier operation and configuration.

Provides a dataset generation approach for LLM fine-tuning in industrial contexts.

Abstract

Traditional industrial automation systems require specialized expertise to operate and complex reprogramming to adapt to new processes. Large language models offer the intelligence to make them more flexible and easier to use. However, LLMs' application in industrial settings is underexplored. This paper introduces a framework for integrating LLMs to achieve end-to-end control of industrial automation systems. At the core of the framework are an agent system designed for industrial tasks, a structured prompting method, and an event-driven information modeling mechanism that provides real-time data for LLM inference. The framework supplies LLMs with real-time events on different context semantic levels, allowing them to interpret the information, generate production plans, and control operations on the automation system. It also supports structured dataset creation for fine-tuning on this downstream application of LLMs. Our contribution includes a formal system design, proof-of-concept implementation, and a method for generating task-specific datasets for LLM fine-tuning and testing. This approach enables a more adaptive automation system that can respond to spontaneous events, while allowing easier operation and configuration through natural language for more intuitive human-machine interaction. We provide demo videos and detailed data on GitHub: https://github.com/YuchenXia/LLM4IAS.