An LLM-Assisted Multi-Agent Control Framework for Roll-to-Roll Manufacturing Systems

TL;DR

This paper introduces an AI-assisted multi-agent framework that automates control system design and adaptation in roll-to-roll manufacturing, improving efficiency, safety, and performance under uncertain conditions.

Contribution

It presents a novel multi-phase framework leveraging LLMs for automated control tuning, safety verification, and continuous adaptation in R2R manufacturing systems.

Findings

Successful tension regulation and velocity tracking demonstrated

Framework achieves performance convergence through iterative adaptation

Reduces manual tuning effort and enhances diagnostic transparency

Abstract

Roll-to-roll manufacturing requires precise tension and velocity control to ensure product quality, yet controller commissioning and adaptation remain time-intensive processes dependent on expert knowledge. This paper presents an LLM-assisted multi-agent framework that automates control system design and adaptation for R2R systems while maintaining safety. The framework operates through five phases: system identification from operational data, automated controller selection and tuning, sim-to-real adaptation with safety verification, continuous monitoring with diagnostic capabilities, and periodic model refinement. Experimental validation on a R2R system demonstrates successful tension regulation and velocity tracking under significant model uncertainty, with the framework achieving performance convergence through iterative adaptation. The approach reduces manual tuning effort while providing transparent diagnostic information for maintenance planning, offering a practical pathway for integrating AI-assisted automation in manufacturing control systems.