A novel motor bearing fault diagnosis method based on a deep sparse binary autoencoder and principal component analysis

Due to the complex and variable operating conditions of motor bearings, it is difficult for a deep autoencoder (DAE) to effectively extract valuable fault features from the raw vibration signal, which makes it difficult to identify faults. To enhance the extraction ability of the deep features of a network model and improve the accuracy of fault identification, this paper proposes a fault diagnosis method for motor bearings based on a deep sparse binary autoencoder and principal component analysis (PCA). Firstly, a deep sparse binary autoencoder is constructed by combining an autoencoder with a binary processor to improve the ability to extract deep features. Secondly, principal component analysis is used to fuse high-dimensional features to reduce dimensionality and eliminate redundant information existing in the deep features. Finally, fused deep features are input into a Softmax classifier to train the intelligent fault diagnosis model. The proposed method is validated on a rolling bearing dataset. Compared with existing methods, the experimental results show that this method can effectively extract robust features from the original vibration signals and improve the fault diagnosis results.