應用多代理人技術於彈性製造系統單元控制器之設計

Using Multi-Agent Technique in Cell Controller Design of Flexible Manufacturing System

張凱鈞(Kai-Jyun Chang)

指導教授 ： 陳凱瀛

國立臺北科技大學/管理學院/工業工程與管理研究所/碩士(2008年)

摘要

彈性製造系統隨著需求的增加，日漸變的龐大，傳統的控制方式漸漸的出現了許多的問題。近年來資訊技術(Information Technology, IT)的快速進步，促進了人工智慧(Artificial Intelligence, AI)的蓬勃發展，出現了許多將資訊技術應用於製造系統的應用，如以代理人(Agent)為基礎之製造系統(Agent-Based Manufacturing System)。代理人擁有自主(Autonomous)、協調(Negotaition)、合作(Cooperation)、反應(Reactive)等特點，以協調與溝通的方式，來達成即時的決策。而多代理人彈性製造系統(Multi-Agent Flexible Manufacturing System)是一以代理人為基礎之製造系統，將代理人之精神引入彈性製造系統之中，結合代理人與彈性製造系統的設備與資源。本研究中所設計之多代理人彈性製造系統，建構在JADE平台之上，透過模組化的設計讓每一機台設備與代理人結合產生設備代理人，使代理人能夠獲得現場的即時資訊，經由預先設定的行為模式進行活動。在本研究中，當代理人的活動發生衝突時，經由合約式網路來進行協調，尋求整體的最大利益。經由本研究發現，多代理人彈性製造系統對各種生產情況能夠有良好的適應性。

關鍵字

彈性製造系統 ； 代理人 ； JADE

並列摘要

Due to increasing demands, FMS becomes enormous and traditional controlling ways gradually have many problems. In recent year, AI has great influence on controlling manufacturing system, like the Agent-Based Manufacturing System. An Agent has the feature of autonomous, negotiation, cooperation and reactive. It cooperates with other agents in order to making-decision. The MAFMS based on the Multi-Agent paradigm, combined the resource and equipments of manufacturing system and agents. In this thesis, we model a manufacturing system as a multi-agent system built on JADE platform where agents are subject to an adjustable autonomy. The autonomy of an agent refers to its capability to make and influence decisions within a multi-agent system. Adjustable autonomy means changing the autonomy of the agents during runtime as a response to changes in the environment. If agents conflict with others, they negotiate by contract net to benefit manufacturing activities. By this paper, we are prove the MAFMS can be adapt production.

並列關鍵字

Flexible Manufacturing System ； Agent ； JADE

參考文獻

[1] Mikell, P.G., Automation, Production Systems, and Computer-Integrated Manufacturing, Second Edition, U.S.A., Prentice-Hall, Inc., 2001

[2] Viswanadham, N., Narahari, Y., Performance modeling of aytomated manufacturing systems, India, Prentice-Hall, 1992

[3] Bellifemine, F., Caire, G., Greenwood, D., developing multi-agent systems with JADE, England, Wiley, 2007

[6] Ferber, J., Multi-Agent Systems – An Introduction to Distributed Artificial Intelligence, Addison-Wesley, 1999

[7] Nagarjuna, N., Mahesh O., Rajagopal K., “A heuristic based on multi-stage programming approach for machine-loading problem in a flexible manufacturing system”, Robotics and Computer-Integrated Manufacturing, vol.22, no.4, pp.342-352, 2006