Building a Functionnal Model from a Sequence of Alarms: The Example of APACHE

This paper aims at showing for a real case the results obtained with the stochastic approach to the analysis of a sequence of alarms produced by the Apache system, a Sachem-like system that is dedicated to monitoring, diagnosing and controlling the zinc baths used by the Arcelor Group. Sachem is the Arcelor's generic extensive large-scale real time knowledge based system designed to monitor, diagnose and control processes. The paper shows how the knowledge of the behavior of a continuous process can be formalized in terms of relations between discrete events that are deduced from a sequence of Apache's alarms by the mean ofa stochastic approach. The stochastic approach is based on the representation of a sequence of alarms under the dual form of a homogeneous Markov chain and its corresponding superposition of Poisson processes. The paper shows how a functional model can be derived from a behavioral model produced according to the stochastic approach.