IRMSwin-T: A lightweight shifted windows transformer based on inverted residual structure and residual multi-layer perceptron for rolling bearing fault diagnosis

Shanshan Ding; Renwen Chen; Hao Liu; Fei Liu; Junyi Zhang

doi:10.1063/5.0171091

IRMSwin-T: A lightweight shifted windows transformer based on inverted residual structure and residual multi-layer perceptron for rolling bearing fault diagnosis

Rev Sci Instrum. 2023 Sep 1;94(9):095116. doi: 10.1063/5.0171091.

Authors

Shanshan Ding¹, Renwen Chen¹, Hao Liu¹, Fei Liu¹, Junyi Zhang¹

Affiliation

¹ College of Aerospace Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, People's Republic of China.

PMID: 37737703
DOI: 10.1063/5.0171091

Abstract

The data-driven fault diagnosis method has achieved many good results. However, classical convolutional and recurrent neural networks have problems with large parameters and poor anti-noise performance. To solve these problems, we propose a lightweight shifted windows transformer based on inverted residual structure and residual multi-layer perceptron (IRMSwin-T) for fault diagnosis of rolling bearings. First, the original data are expanded by using overlapping sampling technology. Then, the collected one-dimensional vibration signals are vector serialized by using the patch embedding strategy. Finally, the IRMSwin-T network is developed to extract features of vector sequences and classify faults. The experimental results showed that compared with mainstream lightweight models, the IRMSwin-T model in this paper has fewer parameters and higher diagnostic accuracy.