Equipment Fault Detection by Parametric Identification - Application to Chemical Reactor.

Abstract

Equipment faults in industrial chemical reactors lead to variations in product quality. Due to the highly energetic potential of the reaction mass, they can in addition cause runaways or major incidents. The methodology for detecting process anomalies in a chemical reactor, is based on a parametric estimation-prediction of the reaction mixture. The recursive least square method with forgetting factor has been retained to appreciate the evolution of parameters in real time. Thus allowing us, to point out a criterion of decision based on relative prediction error between two successive vector parameters. In this paper, we consider only the stirred jacketed chemical reactor which is largely use in pharmaceutical fine chemistry. Two incidents linked to the hydrodynamic cited by Etchelles (Etchelles., 1994) as main causes of reported incidents are studied: a change in the fluid flow regime in the jacket and the immediate stop of the agitator. In each case, a dynamic simulation model, based on energetic balances, is established to represent the most accurate reactor thermal behaviour.