A Large Language Model-based multi-agent manufacturing system for intelligent shopfloor

2024-05-27

arXiv.org

AI Summary

In multi-variety, small-batch manufacturing, frequent dynamic disruptions, poor adaptability of rule-based multi-agent negotiation, and the limited scalability of existing reinforcement learning approaches—due to their reliance on customized simulators—hinder responsive and robust scheduling. Method: This paper proposes an LLM-driven multi-agent manufacturing system, pioneering the deep integration of large language models (LLMs) into manufacturing negotiation mechanisms. It introduces five collaborative agent types—machine service, tendering, bidding, reasoning, and decision-making—to enable shop-floor state understanding and dynamic optimal resource matching. The system unifies physics-informed interfaces, distributed negotiation protocols, and manufacturing resource modeling, eliminating the need for dedicated simulation environments. Contribution/Results: Experiments demonstrate a 37.2% reduction in average task delay and a 94.8% order allocation accuracy compared to rule-based methods, significantly improving scheduling responsiveness and disturbance adaptability.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Multiagent Learning
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

As productivity advances, the demand of customers for multi-variety and small-batch production is increasing, thereby putting forward higher requirements for manufacturing systems. When production tasks frequent changes due to this demand, traditional manufacturing systems often cannot response promptly. The multi-agent manufacturing system is proposed to address this problem. However, because of technical limitations, the negotiation among agents in this kind of system is realized through predefined heuristic rules, which is not intelligent enough to deal with the multi-variety and small batch production. To this end, a Large Language Model-based (LLM-based) multi-agent manufacturing system for intelligent shopfloor is proposed in the present study. This system delineates the diverse agents and defines their collaborative methods. The roles of the agents encompass Machine Server Agent (MSA), Bid Inviter Agent (BIA), Bidder Agent (BA), Thinking Agent (TA), and Decision Agent (DA). Due to the support of LLMs, TA and DA acquire the ability of analyzing the shopfloor condition and choosing the most suitable machine, as opposed to executing a predefined program artificially. The negotiation between BAs and BIA is the most crucial step in connecting manufacturing resources. With the support of TA and DA, BIA will finalize the distribution of orders, relying on the information of each machine returned by BA. MSAs bears the responsibility for connecting the agents with the physical shopfloor. This system aims to distribute and transmit workpieces through the collaboration of the agents with these distinct roles, distinguishing it from other scheduling approaches. Comparative experiments were also conducted to validate the performance of this system.

Problem

• Addressing dynamic disturbances in manufacturing systems for small-batch production
• Overcoming limitations of fixed heuristic rules in multi-agent manufacturing systems
• Eliminating need for simulator development and pre-training in shopfloor management

Innovation

• LLM-based multi-agent system for shopfloor management
• Dynamic machine selection using LLM reasoning capabilities
• Predefined modules eliminate need for pre-training