Fault detection and classification by unsupervised feature extraction and dimensionality reduction

Abstract

A unique technique is proposed based on sparse-autoencoders for automated fault detection and classification using the acoustic signal generated from internal combustion (IC) engines. This technique does not require any hand-engineered feature extraction and feature selection from acoustic data for fault detection and classification, as usually done. The proposed technique uses sparse-autoencoder for unsupervised features extraction from the training data. The training and testing data sets are then transformed by these extracted features, before being used by the softmax regression for classification of unknown engines into healthy and faulty class. The use of sparse-autoencoder to learn fault features improves the classification performance significantly with a small number of training data. This technique is tested on industrial IC engine data set, with overall classification performance of 183 correct classifications out of 186 test cases for four different fault classes.