Rule-based ARIMA models for FMS

There are many mathematically-precise solutions available for FMS scheduling but most of them have not considered real-time changes or interruptions in the FMS such as machine breakdown, shortages of materials, rescheduling, etc. A more feasible solution to the above problem is to construct stochastic models that can describe the dynamics of the interruptions. The purpose of this paper is to investigate the methodology of using time-varying models, ARIMA (Autoregressive-Integrated-Moving-Average) models, to analyze the FMS interruptions. These models can be used to formulate the production rule-base of the FMS scheduler. Management can use this integrated approach to describe and predict the dynamic behavior of a complex FMS. (C) 1997 Elsevier Science S.A.