Deep branch attention network and extreme multi-scale entropy based single vibration signal-driven variable speed fault diagnosis scheme for rolling bearing

Abstract

In view of the difficulty in measuring the speed signal and integrating the vibration and speed information flexibly in actual variable speed bearing fault diagnosis, a single vibration signal-driven variable speed intelligent fault diagnosis scheme for rolling bearings is developed to guarantee the reliability and safety of the equipment in this paper. In the proposed fault diagnosis scheme, the extreme multi-scale entropy (EMSEn) of the raw vibration signal is employed as the alternative characterization parameter of the speed information, and an intelligent diagnosis model named deep branch attention network (DBANet) is developed to integrate the vibration and speed information more flexibly. The developed DBANet contains 2 parallel and relatively independent forward propagation channels, and the attention mechanism is introduced into the deep architecture at branch level to adjust the importance of different branches, which endow the model with the ability of fusing the vibration and speed information autonomously. The effectiveness of the proposed method is verified by experiments, and the experimental results show that, compared with the methods relying on external information fusion, the suggested DBANet can integrate the vibration and speed information more flexibly. Besides, in the case of no speed signal, the proposed diagnosis scheme can achieve more outstanding results compared with the methods of using other multi-scale entropy features as the alternative characterization parameter of the speed information.