Fault detection of a seven level modular multilevel inverter via voltage histogram and Neural Network

The multilevel inverters (MLIs) utilization has been increased in recent years due to their lots of advantages. The MLI has many switches that increase the probability of fault events. In this paper a fault diagnosis method for a cascade H-bridge 7-level inverter is proposed. The output phase voltage is used to detect fault type and their locations. The histogram analysis is used for feature extraction and these features have been used as input to the Neural Networks (NNs). The multilayer perceptron NNs have been used for fault diagnosis. Simulation results are given for a cascade 7-level inverter at different modulation indices and show that this method is accurate for detection of faults and their locations. This method works correctly under noisy condition and the classification performance for the noise with variance up to 1500 is 100%. The proposed method is faster and less complicated because of using histogram analysis instead of using sophisticated methods such as FFT or wavelet.