Fault diagnosis and process monitoring through model-based case based reasoning

Abstract

In this paper, we present a method for the fault detection and isolation based on the residual generation coupled with a case based reasoning approach. The main idea is to reconstruct the outputs of the system from the measurement using the extended Kalman filter. The estimations completed with qualitative information are included in a Case Based Reasoning system in order to discriminate the possible faults and to have a reliable diagnosis. The reference model is simulated by the dynamic hybrid simulator, PrODHyS. The use of this method is illustrated through an application in the field of chemical process