An Improved MSCNN and GRU Model for Rolling Bearing Fault Diagnosis

Abstract

In this paper, a novel fault diagnosis method based on the fusion of squeeze and excitation-multiscale convolutional neural networks (SENet-MSCNN) and gate recurrent unit (GRU) is proposed to address the problem of low diagnosis rate caused by the fact that normal samples are much larger than fault samples in the vibration big data. The method takes the time-domain vibration signal as input and fuses the spatial features extracted by SENet-MSCNN. The temporal features extracted by GRU in order to bring them into the fully connected layer for identification so as to realize the intelligent diagnosis of rolling bearing adaptive feature extraction. Finally, the method is applied to the simulated signal and experimental data for testing and analysis. The results reveal that the model can reach 98.98 % and 76.44 % migration diagnostic accuracy in bearing and gearbox datasets. At the same time, it has strong noise immunity, adaptivity, and robustness, providing an effective way for intelligent diagnosis of rolling bearing vibration big data.