Rolling bearing fault diagnosis in electric motors based on IDIG-GAN under small sample condition

Abstract The bearing fault diagnosis based on deep learning algorithms requires a substantial amount of data. However, in practical industrial production, the diagnostic algorithms tend to work ineffectively due to the limitations of samples. Therefore, in this article, we propose an improved method of deep convolutional generative adversarial networks with discriminator gradient gap regularization (IDIG-GAN), which can effectively solve the problems of unstable training and poor training performance under a small sample dataset. Firstly, the self-attention mechanism is integrated into the DCGAN to capture global information to enhance the generalization capability of the network. Moreover, gradient normalization is applied to the discriminator to address the problem of vanishing gradients in the network. Furthermore, gradient gap regularization is incorporated into the loss function to narrow the gap between the discriminator gradient norms, thereby improving network stability when dealing with small fault datasets. Through training with the improved IDIG-GAN, then the generated samples are used to expand the dataset and construct a fault diagnosis model. By verifying under two bearing datasets, the results demonstrate that the proposed method can generate high-quality samples and effectively enhance the diagnostic capability of the network when working with small datasets.