The problem of imbalanced data amounts between the samples of healthy and faulty conditions degrades the performance of traditional intelligent diagnosis methods for rotating machinery. This paper explores a data generation approach to improve the diagnostic performance of key components in the rotating machinery. A new generative adversarial networks (GAN) model, called categorical feature GAN (CFGAN), is proposed to generate sufficient synthetic samples for the minority faulty conditions so as to rebalance the datasets. The main contribution is that the quality of the synthetic samples is ensured by considering both consistency and diversity with the real samples, which conduces to machinery fault diagnosis. Specifically, latent categorical features are firstly learned from the real fault samples via the proposed CFGAN, which is an integration model of autoencoder (AE) and auxiliary classifier GAN (ACGAN). Then, synthetic categorical features are produced by interpolation among the learned categorical features followed by slight noise addition. Finally, synthetic samples are generated using the synthetic categorical features through the generator of the CFGAN. In addition, Wasserstein distance (WD) is applied to the CFGAN to avoid mode collapse in training. Because categorical features rather than random noise are used to generate samples, and the interpolation is performed in the feature space instead of the noisy data space, the consistency of the synthetic samples is improved as compared to the traditional methods. The diversity is ensured by the use of diverse synthetic categorical features and the WD. Two machinery datasets under varying imbalance ratios confirmed that the proposed CFGAN model can synthesize high-quality samples and has better generalization capability over the existing data generation methods in machinery fault diagnosis.

Based on the ideas of the new information priority principle and the fractional-accumulation generating operator, in this paper we propose a novel weighted fractional GM(1,1) (WFGM(1,1)) prediction model. In the new model, the original sequence is first transformed by using the weighted fractional-accumulation generating operator, which involves two parameters. With special choices of these parameters, the proposed WFGM(1,1) model reduces to the classical GM(1,1) model and the fractional GM(1,1) (FGM(1,1)) model, as well as the new information priority GM(1,1) (NIPGM(1,1)) model studied recently. Stability property of the WFGM(1,1) model is studied in detail. In practice, the quantum particle swarm optimization algorithm is adopted to choose the quasi-optimal parameters for the new model so as to get the best fitting accuracy. Finally, four numerical examples from different practical applications are present. Numerical results show that the new proposed prediction model is very efficient and has both the best fitting accuracy and the best prediction accuracy compared with the GM(1,1) and the FGM(1,1) as well as the NIPGM(1,1) prediction models.