A multi-channel fault information bearing fault diagnosis method based on improved vision transformer

Bearings are crucial components of modern mechanical equipment and their failure can lead to equipment downtime, economic losses, and potential threats personal safety. Therefore, it is essential to carry out fault diagnosis of bearings. In this paper, Multichannel Signal Transformer (MST) model is employed for diagnosing bearing faults. Initially, a single vibration signal and two motor current signals are collected and combined into a multichannel signal. This multichannel signal is then used to train and test the MST model. The performance of the MST model is subsequently compared with that of an established one-dimensional CNN. The feasibility of the method is verified by comparing the accuracy and loss function values of the two models in fault diagnosis. Finally, the confusion matrix of the MST model for fault classification is analyzed, and the t-SNE visualization is performed on the features of the fully-connected layer. The results demonstrate that the MST model has a higher accuracy in fault diagnosis.