An efficient method for imbalanced fault diagnosis of rotating machinery

Abstract

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.

Synthesizing Rolling Bearing Fault Samples in New Conditions: A Framework Based on a Modified CGAN

“…Wang et al [ 31 ] combined GAN and the conditional variational autoencoder to enhance the quality of generated samples for fault pattern recognition in planetary gearboxes. Reference [ 43 ] proposed an improved fault diagnosis approach to learn the deep features of the data by combining an encoder with GANs, integrating the discriminator with the deep regret analysis method to avoid the mode collapse by imposing the gradient penalty on it. Reference [ 43 ] also proposed a novel method called upgraded GAN, which is a combination of energy-based GANs, auxiliary-classifier, and conditional variational autoencoders.…”

“…Reference [ 43 ] proposed an improved fault diagnosis approach to learn the deep features of the data by combining an encoder with GANs, integrating the discriminator with the deep regret analysis method to avoid the mode collapse by imposing the gradient penalty on it. Reference [ 43 ] also proposed a novel method called upgraded GAN, which is a combination of energy-based GANs, auxiliary-classifier, and conditional variational autoencoders. Some other applications of GANs for data argumentation in the literature for fault diagnoses were demonstrated by Liu et al [ 44 ], who proposed a data synthesis approach using deep feature-enhanced GANs for roller bearing fault diagnoses; [ 45 ] used wavelength transform to extract image features from time-domain signals with GANs to generate more training samples and CNN for fault detection.…”

Synthesizing Rolling Bearing Fault Samples in New Conditions: A framework based on a modified CGAN

“…Wang et al [31] combined GAN and conditional variational auto-encoder (CVAE-GAN) to enhance the quality of generated samples for fault pattern recognition in planetary gearboxes. [43] proposed an improved fault diagnosis approach to learn the deep features of the data by combining an encoder with GANs and integrating the discriminator with the deep regret analysis method to avoid mode collapse by imposing the gradient penalty on it. [43] also proposed a novel method called (upgraded GAN) UGAN, which is a combination of Energy-based GANs (EBGAN), Auxiliary-classifier (ACGAN), and conditional variational autoencoders (CVAEs).…”

“…[43] proposed an improved fault diagnosis approach to learn the deep features of the data by combining an encoder with GANs and integrating the discriminator with the deep regret analysis method to avoid mode collapse by imposing the gradient penalty on it. [43] also proposed a novel method called (upgraded GAN) UGAN, which is a combination of Energy-based GANs (EBGAN), Auxiliary-classifier (ACGAN), and conditional variational autoencoders (CVAEs). Some other applications of GANs for data argumentation in literature for fault diagnosis are demonstrated by Liu et al [44], who proposed a data synthesis approach using deep feature enhanced GANs for roller bearing fault diagnosis, and [45] which used wavelength transform to extract image features from time-domain signals with GANs for generating more training samples and CNN for fault detection.…”

Imbalanced fault identification via embedding-augmented Gaussian prototype network with meta-learning perspective

“…However, deep learning models have the ability to be used in more complex situations, which are difficult for the traditional methods [12][13][14]. Therefore, more and more researchers are focusing on the imbalance problems using deep learning methods [15][16][17]. The typical methods for solving imbalance problems can be roughly divided into sampling-based, data augmentation-based, weighting-based and anomaly detectionbased methods [13].…”