基于MAS的复杂系统分布式求解策略与推理研究  

Research on Distributed Solution and Correspond Consequence of Complex System Based on MAS

作　　者：蒋伟进[1] 王璞[2] 

机构地区：[1]湖南工业大学计算机学院,株洲412008 [2]中南大学商学院,长沙410083

出　　处：《计算机研究与发展》2006年第9期1615-1623,共9页Journal of Computer Research and Development

基　　金：国家自然科学基金项目(60473037);中国包装总公司技术创新基金项目(05ZBKJA011);湖北省自然科学基金项目(2001ABB006;2003ABA043)

摘　　要：针对复杂的连续生产线系统监测与故障诊断的动态、分布、实时和不确定特性,将多Agent及相关智能技术引入复杂故障诊断领域,提出了一种嵌套式基于消息传递的多Agent组织模型,分析了基于MAS的分布式智能故障诊断方法和过程;研究了模型系统的动态适应性和稳定性;设计了实时诊断Agent工作状态的表达机制;讨论了Agent间的协调协作机制及融合方法;给出了多Agent诊断系统诊断决策的集成描述结构;提出了任务分解与分配调度算法,以充分发挥Agent的社会性和基于场景的特点,使得在复杂系统的问题求解中能提供更为可靠的诊断结果,而且还能节约资源提高诊断效率.将其应用于某安全监控系统中,取得了与专家相似的诊断结果,克服了以往监控诊断系统存在的弊端,提高了企业的安全运行效率.与传统诊断方法相比,体现了Agent技术在复杂分布式问题求解领域的特有优势和良好前景.Aiming at monitoring the complicated sequence production line and the dynamic, distributed real-time and uncertain characteristic of fault diagnosis, multi-agent and related technology is introduced to the complicated fault diagnosis. A multi-agent model based on the transfer of message is put forward. MAS based on the distributed intelligent fault diagnosis method and process is analyzed. The adaptability and stability of the model system is studied. The expression mechanism for real-time agent＇s work status is designed. The cooperation mechanism and the amalgamation method between agents are discussed. Integrated description structure of a multi-agent diagnosis system is also given. To make full use of the characteristic of sociality and based on scene, the algorithm of decomposing a diagnosis task and distribution is put forward. And the model gives more credible diagnose results, saves resource and improves the efficiency of the diagnosis. When applied in the power enterprise＇s security monitor system, the result is similar to that of an expert system, and the efficiency of the enterprise security running is enhanced. Compared with the conventional diagnosis method, the result shows the special advantage in the distributed domain.

关 键 词：多Agent系统(MAS) 智能故障诊断 分布式问题求解 协同控制 融合算法 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置] TP181[自动化与计算机技术—控制科学与工程]