摘要
为了提高车间控制系统的柔性、开放性和全局优化性能,在分析现有车间控制体系结构的基础上,融合Agent技术,提出了一种适应性混合式车间控制系统体系结构模型。该模型利用递阶结构将控制功能设计成系统优化Agent、单元协调Agent和单实体Agent三层结构,并允许同层Agent及上下层Agent之间的协商。为了进一步提高协商效率,集成分布式协商和全局控制,设计了基于招投标机制和示例学习方法的协商机制,详细分析了包括时间约束算法和基于示例的学习方法的协商机制核心算法。在JADE(Java Agent development framework)平台上构建了原型系统。
In order to improve the flexibility, openness and global optimization of shop floor control system, an agent--based adaptive architecture for shop floor control system was presented based on the comprehensive analyses of existing shop floor control architectures. The proposed architecture was hybrid: the control function was designed in hierarchical of system optimal Agent, cell coordination Agent and individual Agent, meanwhile, horizontal as well as vertical decisions were allowed to make between various levels of Agents to further improve flexibility. In order to further improve efficiency and effectiveness of coordination among Agents, a new coordination mechanism combined with bidding and instance--based learning approach was designed. The core algorithms of the coordination mechanism, including time--constraint algorithm and instance--based learning approach, were analyzed in detail. Finally, a prototype simulation system was constructed in JADE environment.
出处
《中国机械工程》
EI
CAS
CSCD
北大核心
2010年第3期296-302,共7页
China Mechanical Engineering
基金
国家自然科学基金资助重点项目(70832005)
国家自然科学基金资助项目(70901058)
上海市教委科研创新基金资助重点项目(09ZS39)
关键词
控制体系结构
基于投标的协商机制
基于示例的学习
AGENT
JADE
control architecture
bidding-- based negotiation mechanism
instance-- based learn- ing
Agent
JADE(Java Agent development framework)