A deep learning and softmax regression fault diagnosis method for multi-level converter

With the single-tube and double-tube fault of seven-level converter, this paper presents a new way to learn the faults feature based on the deep neural network of sparse autoencoder. Sparse autoencoder is an unsupervised learning method, it can learn the feature information of the fault data according to training. The feature information is used to train the softmax classifier by softmax regression to realize the aim of classification. Comparing with the traditional neural network of BP neural network, the experimental results show that the method to classify the fault of seven level converter based on deep neural network of sparse autoencoder can achieve higher accuracy.