文献类型：会议论文

英文题名：Multi-agent based distributed chemical process monitoring and diagnosis

作者：Sun, JG; Yang, XB; Huang, D

机构：[1]E China Univ Sci & Technol, Branch State Engn Res Ctr Ind Automat, Shanghai 200237, Peoples R China

会议论文集：International Conference on Machine Learning and Cybernetics

会议日期：NOV 04-05, 2002

会议地点：BEIJING, PEOPLES R CHINA

语种：英文

外文关键词：multi-agents; chemical process; machine learning; distributed diagnosis

摘要：Multi-agent technology offers a number of characteristics that make it well suited for distributed process monitoring and fault diagnosis tasks. This paper describes a general architecture to implement distributed applications for chemical process monitoring and diagnosis as a set of cooperating intelligent agents. Agents in this application encapsulate different distributed hardware/software entities: a real-time process data acquisition system, auto knowledge acquisition, fuzzy and other controllers, presentation manager, hypothesis generator, etc. The agents appeared in this application are defined in ADL (Agent Description Language), a high-level specification language, and interchange data/knowledge through service requests using a common knowledge-representation language. Elements of a multi-agent framework that is being used to support this complex distributed application, and the mechanisms used for agent usability within the chemical process environment are also described.