Méthode hybride de détection et identification des défaillances par observateurs de l'état et arbres de décision
Hybrid Method for Fault Detection and Identiﬁcation Based on State Observers and Decision Trees
In this work, we discuss the importance of techniques that can assist in the devel- opment of systems for Fault Detection and Identification (FDI) and propose a hybrid method for FDI in dynamic systems. We present a brief history to contextualize the techniques used in working environments. The detection of fault in the proposed system is based on state observers in conjunction with other statistical techniques. The principal idea is to use the observer himself, in addition to serving as an analytical redundancy, in allowing the creation of a residue. This residue is used in FDI. A signature database assists in the identification of system faults, which based on the signatures derived from trend analysis of the residue signal and its difference, performs the classification of the faults based purely on a decision tree. This FDI system is tested and validated in a simulated plant with coupled tanks and the results discussed.
Marcelo VALE, Rodrigo MARTINS, André MAITELLI
Fault Detection and Identification (FDI), Decision Trees and State Observer