In industrial scenarios, accumulated sensor data collected from the working processes of rotating machinery are usually imbalanced, and there is scope for improving the diagnostic performance of existing fault diagnosis methods. To solve this problem, a novel method named the upgraded generative adversarial network (UGAN) is presented in this paper. In our method, energy-based generative adversarial networks (EBGANs) and auxiliary classifier generative adversarial networks (AC-GANs) are first combined as the main architecture due to their good sample generation and classification performance. Then, conditional variational autoencoders (CVAEs) are utilized as the generator to generate high-quality samples for orientation. Furthermore, self-normalizing convolutional autoencoders (SCAEs) are introduced into the discriminator to maintain the stability of the network and increase the capability of the network to discriminate fault samples. The experimental results on two benchmark datasets show that the proposed method possesses excellent fault diagnosis capabilities under imbalanced data conditions.
Aiming at the fault diagnosis issue of rotating machinery, a novel method based on the deep learning theory is presented in this paper. By combining one-dimensional convolutional neural networks (1D-CNN) with self-normalizing neural networks (SNN), the proposed method can achieve high fault identification accuracy in a simple and compact architecture configuration. By taking advantage of the self-normalizing properties of the activation function SeLU, the stability and convergence of the fault diagnosis model are maintained. By introducing α -dropout mechanism twice to regularize the training process, the overfitting problem is resolved and the generalization capability of the model is further improved. The experimental results on the benchmark dataset show that the proposed method possesses high fault identification accuracy and excellent cross-load fault diagnosis capability.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.