SACHEM, a Real-Time Intelligent Diagnosis System Based on the Discrete Event Paradigm

Abstract

SACHEM is an extensive large-scale, real-time, knowledge-based system designed to monitor and diagnose complex dynamic processes such as blast furnaces. This article aims at illustrating the way the paradigm of discrete events allowed the design of SACHEM as a recursive abstraction process of discrete events. This recursive abstraction process is the basis of a “perception-based” approach of diagnosis. A first formalization of this kind of diagnosis is proposed and illustrated with the example of the perception of a “scaffolding” phenomenon. Some considerations about blast furnaces, SACHEM, and its development are also provided to argue the operational flavor of a“perception-based”approach for diagnosis.