Machinery fault diagnosis is pretty vital in modern manufacturing industry since an early detection can avoid some dangerous situations. Among various diagnosis methods, data-driven approaches are gaining popularity with the widespread development of data analysis techniques. In this research, an effective deep learning method known as stacked autoencoders (SAEs) is proposed to solve gearbox fault diagnosis. The proposed method can directly extract salient features from frequency-domain signals and eliminate the exhausted use of handcrafted features. Furthermore, to reduce the overfitting problem in training process and improve the performance for small training set, dropout technique and ReLU activation function are introduced into SAEs. Two gearbox datasets are employed to conform the effectiveness of the proposed method; the result indicates that the proposed method can not only achieve significant improvement but also is superior to the raw SAEs and some other traditional methods.

Mechanical fault datasets are always highly imbalanced with abundant common mechanical fault samples but a paucity of samples from rare fault conditions. To overcome this weakness, the simulation of rare fault signals is proposed in this paper. Specifically, frequency spectra are employed as model signals, then Wasserstein generative adversarial network (WGAN) is implemented to generate simulated signals based on a labeled dataset. Finally, the real and artificial signals are combined to train stacked autoencoders (SAE) to detect mechanical health conditions. To validate the effectiveness of the proposed WGAN-SAE method, two specially designed experiments are carried out and some traditional methods are adopted for comparison. The diagnosis results show that the proposed method can deal with imbalanced fault classification problem much more effectively. The improved performance is mainly due to the artificial fault signals generated from the WGAN to balance the dataset, where the signals that are lacking in training dataset are effectively augmented. Furthermore, the learned features in each layer of the generator network are also analyzed via visualization, which may help us understand the working process of the WGAN.

Among various fault diagnosis methods, deep learning has shown state-of-the-art performance in processing mechanical big data. This paper investigates a reliable deep learning method known as autoencoder, which is most suitable for automatic feature extraction of fault signals. However, traditional autoencoders have two deficiencies: (1) the multi-layer structure of autoencoder has an internal covariate shift problem, which will cause great difficulty for the network training. (2) The application of autoencoder in the case of rotating speed fluctuation is not mature. To overcome the aforementioned deficiencies, batch normalization strategy is employed in every layer of the autoencoder network to obtain a steady distribution of activation values during training. It can regularize the network without parameter adjustment, and deal with the speed fluctuation problem perfectly. So, a new network named batch-normalized autoencoder is first proposed for intelligent fault diagnosis. The raw vibration signals are directly fed into the network and the extracted features are employed to train a softmax classifier for health state identification. A bearing and a gearbox data set are finally used to confirm the effectiveness of the proposed method. The results manifest that the proposed method can extract salient features from the raw signals and handle the fault diagnosis problem under the speed fluctuation problem.

No abstract

No abstract