Quantcast

Multiagent-based scheduling optimization for Intelligent Manufacturing System

Research paper by Qing-lin Guo, Ming Zhang

Indexed on: 12 Dec '08Published on: 12 Dec '08Published in: The International Journal of Advanced Manufacturing Technology



Abstract

Multiagent-based scheduling is a new intelligent scheduling method based on the theories of multiagent system (MAS) and distributed artificial intelligence (DAI). Multiagent-based scheduling can dynamically and flexibly schedule manufacturing processes by means of cooperation and coordination among the agents. It has been considered that the Agent technology is an important method to build the model of distributed industrial system, the most natural way to design and implement the distributed Intelligent Manufacturing environment, and one of the significant technologies to construct the manufacturing system of next generation. On the basis of briefly summarizing the technology of Agent and Multiagent system, the architecture of Intelligent Manufacturing System based on Multiagent is put forward, among which, Agent represents the basic processing entity. The control strategy and scheduling optimization algorithm of Intelligent Manufacturing is provided, which is feasible proved by the result of stimulation experiment. Compared with the traditional artificial scheduling, it has distinct advantages. Finally, the model of communication and negotiation between Agents in the Intelligent Manufacturing System is studied, which utilizes the features of Agent such as autonomy, social interaction, response capability, preliminary capability, etc so that Intelligent Manufacturing System could make distributed decisions. The cooperation of system is completed by communication and negotiation. During the process of interaction, Agent is endowed with a role to meet the demand of flexibility of building models in the complicated process of Intelligent Manufacturing, as well as to construct an extended frame for reusable components. Experiments do prove that it is feasible to use the method to develop an Intelligent Manufacturing System, which is valuable for further study in more depth.