Fault diagnosis in multi-level inverter system using adaptive back propagation neural network

In this paper, a fault diagnostic system in a multilevel- inverter using a adaptive back-propagation neural network is developed. An adaptive back propagation neural network classification is applied to the fault diagnosis of a MLI system to avoid the difficulties in using mathematical models. A multilayer perceptron (MLP) network with 40 - 12 - 8 architecture is used to identify the type and location of occurring faults from inverter output voltage measurement. The neural network design process is clearly described. The classification performance of the proposed network between normal and abnormal condition and that among fault features is obtained. Thus, by utilizing the proposed neural network fault diagnostic system, a better understanding about fault behaviors, diagnostics, and detections of a multilevel inverter system can be accomplished.