Fault detection and diagnosis system for power multicell converter using MLP Neural Networks based on sliding mode observer

A Power multicell converter are considered the basic building blocks of industrial electrical drive systems that are widely used for various applications. are generally exposed to the possibility of outbreak open-phase faults because of troubles with the switching devices. the failure of electronic switches mainly affects the constancy of these converter. In this paper, A model of the converter is developed to synthesize the hybrid observer by sliding mode. The second part of this work, we discussed the diagnosis of cell fault by using the sliding-mode hybrid observer for the generation of the residue. The development of an observer-based MLP artificial neural network controller is discussed in the third part to diagnose faults in the converter. The effectiveness of the proposed method is illustrated using experimentally obtained control signals on converter parameters, and the results have shown good accuracy in detecting and locating faults.