Intelligent fault diagnosis of rolling bearings based on MDF and Swin Transformer

A fault diagnosis model based on Motif Difference Field (MDF) and Swin Transformer is proposed to address the issue of scarce fault samples in actual working conditions, which leads to poor diagnostic and generalization capabilities of Deep Learning based fault diagnosis models. Using MDF instead of Gramian Angle Field (GAF), the one-dimensional signal is transformed into a two-dimensional image, retaining features while performing data augmentation; Using the Swin Transformer network model instead of the CNN network for bearing fault measurement. The results indicate that the model has higher accuracy and generalization compared to other deep learning methods.