A bearing fault diagnosis method for high-noise and unbalanced dataset

Abstract

Purpose The purpose is using generative adversarial network (GAN) to solve the problem of sample augmentation in the case of imbalanced bearing fault data sets and improving residual network is used to improve the diagnostic accuracy of the bearing fault intelligent diagnosis model in the environment of high signal noise. Design/methodology/approach A bearing vibration data generation model based on conditional GAN (CGAN) framework is proposed. The method generates data based on the adversarial mechanism of GANs and uses a small number of real samples to generate data, thereby effectively expanding imbalanced data sets. Combined with the data augmentation method based on CGAN, a fault diagnosis model of rolling bearing under the condition of data imbalance based on CGAN and improved residual network with attention mechanism is proposed. Findings The method proposed in this paper is verified by the western reserve data set and the truck bearing test bench data set, proving that the CGAN-based data generation method can form a high-quality augmented data set, while the CGAN-based and improved residual with attention mechanism. The diagnostic model of the network has better diagnostic accuracy under low signal-to-noise ratio samples. Originality/value A bearing vibration data generation model based on CGAN framework is proposed. The method generates data based on the adversarial mechanism of GAN and uses a small number of real samples to generate data, thereby effectively expanding imbalanced data sets. Combined with the data augmentation method based on CGAN, a fault diagnosis model of rolling bearing under the condition of data imbalance based on CGAN and improved residual network with attention mechanism is proposed.

Fault Diagnosis for Reducers Based on a Digital Twin

“…Many scholars have made outstanding contributions in the field of image generation [ 52 ]. Therefore, to further illustrate the efficiency of the proposed method in the domain of virtual signal generation, the obtained results were compared with those of CACGAN [ 10 ], ML1D-GAN [ 13 ], ACGAN [ 53 ], and CycleGAN [ 54 ].…”

Application of Life Cycle of Aeroengine Mainshaft Bearing Based on Digital Twin

“…On the other hand, different artificial neural network methods have been established based on convolutional neural networks (CNN) to identify bearing faults and improve the accuracy of fault diagnosis, such as MACCNN [53], ADCNN [54], MT-1DCNN [55], 1-D CNN [56], CNN-GRU [57], etc., or an intelligent fault diagnosis model (GL-mRMR-SVM) based on support vector machine (SVM) and feature fusion and feature selection [58], a support tensor machine (STM) [59], etc., to establish a new fault identification method to improve the accuracy of mainshaft bearing fault diagnosis. Wang Rui [60] proposed a deep convolutional neural network that combines residual blocks and channel attention mechanisms for bearing fault diagnosis. The channel attention mechanism was used to improve the recognition ability of the model, and the residual blocks improved the characteristics of deep convolutional neural networks and the extraction ability, and ultimately improved the accuracy of fault diagnosis.…”