A neural network constructed by deep learning technique and its application to intelligent fault diagnosis of machines

In traditional intelligent fault diagnosis methods of machines, plenty of actual effort is taken for the manual design of fault features, which makes these methods less automatic. Among deep learning techniques, autoencoders may be a potential tool for automatic feature extraction of mechanical signals. However, traditional autoencoders have two following shortcomings. (1) They may learn similar features in mechanical feature extraction. (2) The learned features have shift variant properties, which leads to the misclassification of mechanical health conditions. To overcome the aforementioned shortcomings, a local connection network (LCN) constructed by normalized sparse autoencoder (NSAE), namely NSAE-LCN, is proposed for intelligent fault diagnosis. We construct LCN by input layer, local layer, feature layer and output layer. When raw vibration signals are fed to the input layer, LCN first uses NSAE to locally learn various meaningful features from input signals in the local layer, then obtains shift-invariant features in the feature layer and finally recognizes mechanical health conditions in the output layer. Thus, NSAE-LCN incorporates feature extraction and fault recognition into a general-purpose learning procedure. A gearbox dataset and a bearing dataset are used to validate the performance of the proposed NSAE-LCN. The results indicate that the learned features of NSAE are meaningful and dissimilar, and LCN helps to produce shift-invariant features and recognizes mechanical health conditions effectively. Through comparing with commonly used diagnosis methods, the superiority of the proposed NSAE-LCN is verified. (C) 2017 Elsevier B.V. All rights reserved.