Autonomous Agents for Distributed Problem Solving in Condition Monitoring

Abstract

The application of intelligent systems for data interpretation and condition monitoring is an advancing field of research. In recent years autonomous intelligent agents and multi-agent systems have gained much attention within different real time applications. This paper introduces the novel idea of COMMAS (Condition Monitoring Multi-Agent System); a hierarchical decentralised multi-agent architecture developed for data interpretation and condition monitoring applications. It employs groups of different kinds of intelligent agents to cope with the variety of application functions by using distributed problem solving and different computational intelligence techniques. The design and functionality of the diversity of agents, along with the key issues of the multi-agent system as a whole are described. This paper demonstrates how agent technology overcomes problems associated with centralised approaches in condition monitoring, and illustrates the new opportunities agents can provide.