A knowledge-based system for reactive scheduling decision-making in FMS

This paper describes research into the development of an intelligent simula tion environment. The environment was used to analyze reactive scheduling s cenarios in a specific flexible manufacturing systems (FMS) configuration. Using data from a real FMS, simulation models were created to study the rea ctive scheduling problem and this work led to the concept of capturing inst antaneous FMS status data as snapshot data for analysis. Various intelligen t systems were developed and tested to asses their decision-making capabili ties. The concepts of "History Logging" and expert system "learning" is pro posed and these ideas are implemented into the environment to provide decis ion-making and control across a FMS schedule lifetime. This research propos es an approach for the analysis of reactive scheduling in an FMS. The appro ach and system that was subsequently developed was based on the principle o f automated intelligent decision-making via knowledge elicitation from FMS status data, together with knowledge base augmentation to facilitate a lear ning ability based on past experiences.