To deal with the difficulty in bearing remaining useful life prediction caused by the lack of history data, a data amplification method based on the generative adversarial network (GAN) is proposed in this paper, and the parameters of generator and discriminator in the GAN are determined by grid search algorithm. The proposed method is verified by the XJTU-SY bearing data sets from Xi’an Jiaotong University. First, 15 time-domain features related to the bearing life are extracted as the training data of the GAN to generate virtual data that can be used to build bearing life prediction models. Then, support vector regression and the radial basis function neural network are used to construct the bearing prognostic model based on real data, generated data, and mixed data. The results show that the proposed method can make up for the deficiency of data and improve the accuracy of bearing remaining useful life prediction.

Gear fault diagnosis has been a vital technology to enhance the reliability and reduce the maintenance cost of gear systems. Tooth spalling is one of the most destructive surface failure models of the gear faults. Revealing the dynamic characteristics of a gear system with spalling fault and extracting the fault feature are the premise and basis for effective fault diagnosis. Previous studies have mainly concentrated on the spalling damage on a single gear tooth, but the spalling distributed over double teeth which usually occurs in practical engineering problems is rarely reported. To remedy this deficiency, this paper constructs a new dynamical model of a gear system with double-teeth spalling fault and validates this model with various experimental tests. The dynamic characteristics of gear systems are obtained by considering the excitations induced by the number of spalling teeth, the relative position of two faulty teeth, and the rotational speed. The method based on the Variational Mode Decomposition (VMD) and the Fast Kurtogram (FK) is proposed to extract the features of the double-teeth spalling fault. First, the raw signal is decomposed into a set of Intrinsic Mode Functions (IMFs) by applying the VMD, and the IMFs with strong correlation are summed as a reconstructed signal. The reconstructed signal is then filtered by an optimal band-pass filter based on the FK. Combined with envelope spectrum analysis, the feature extraction ability of the proposed method is compared with that of the original FK method and the method based on the Empirical Mode Decomposition and the FK, respectively. The results indicate that the proposed dynamic model and fault feature extraction method can provide a theoretical basis for spalling defect diagnosis of gear systems.