Reactive agent mechanisms for scheduling manufacturing processes
نویسندگان
چکیده
This paper will present an agent based solution to control chemical processes in a manufacturing environment; items should undergo chemical reactions in different chemical baths to be processed by the system. Recipes for the processes only specify minimum and maximum times for each bath, and recipes depend strongly on characteristics of the item. We have applied the PACO paradigm for reactive agents to develop control software for the system, and we have designed simple physical force-like interaction mechanisms, so agents manage to fulfill their individual and global goals. We outline the problem and argue why the PACO approach suits this problem, before explaining in detail how the agents are designed and the interactions established for the planning to be successful. We conclude the paper by presenting results of the agentbased approach, based on data and scenario recipes from the real system.
منابع مشابه
Reactive scheduling using a multi-agent model: the SCEP framework
Multi-agent systems have been successfully applied to the scheduling problem for some time. However, their use often leads to poorly unsatisfactory disappointing results. A new multi-agent model, called supervisor, customers, environment, producers (SCEP), is suggested in this paper. This model, developed for all types of planning activities, introduces a dialogue between two communities of age...
متن کاملCoupling predictive scheduling and reactive control in manufacturing hybrid control architectures: state of the art and future challenges
Nowadays, industrials are seeking for models and methods that are not only able to provide efficient overall production performance, but also for reactive systems facing a growing set of unpredicted events. One important research activity in that field focuses on holonic/multi-agent control systems that couple predictive/proactive and reactive mechanisms into agents/holons. Meanwhile, not enoug...
متن کاملCoupling Predictive Scheduling and Reactive Control in Manufacturing: State of the Art and Future Challenges
Nowadays, industrials are seeking for models and methods that are not only able to provide efficient overall production performance, but also reactive facing a growing set of unpredicted events. One important research activity in that field focuses on holonic/multi-agent control systems that couple predictive/proactive and reactive mechanisms into agents/holons. Meanwhile, not enough attention ...
متن کاملManufacturing Scheduling Using Colored Petri Nets and Reinforcement Learning
Agent-based intelligent manufacturing control systems are capable to efficiently respond and adapt to environmental changes. Manufacturing system adaptation and evolution can be addressed with learning mechanisms that increase the intelligence of agents. In this paper a manufacturing scheduling method is presented based on Timed Colored Petri Nets (CTPNs) and reinforcement learning (RL). CTPNs ...
متن کاملEffects of Negotiation Mechanisms on Performance of Agent Based Manufacturing Systems
This paper proposes new inter{agent negotiation mechanisms for improving the performance of agent based or decentralized manufacturing systems. The focus of this paper is on demonstrating eeciency of diierent negotiation and collaboration schemes between agents of the same class (parts, machines, etc) and inter{class negotiations using currency metrics. The cooperation and negotiation protocols...
متن کامل