Component-based multi-model approach for fault detection and diagnosis of a centrifugal pump

A model-based approach for fault detection and diagnosis of nonlinear processes is presented. However, the supervision of nonlinear systems is often very difficult in view of the lack of accurate models. Neuro-fuzzy models may help to cope with this problem since they can be trained from measured data. In this paper the application of a multi-model approach for fault detection and diagnosis of centrifugal pumps is presented. For this purpose the process is decomposed in several sub-processes. The supervision scheme allows the detection of several faults both in the hydraulic and mechanical subsystems.