Rolling bearing fault diagnosis method based on multi-sensor two-stage fusion
Cang Liu, Jinyu Tong, Jinde Zheng, Haiyang Pan, Jiahan Bao
Abstract
Abstract Despite the great achievements of deep learning methods based on a single sensor in fault diagnosis, learning useful information from multi-sensor data is still a challenge. In order to make full use of multi-sensor information and improve the performance of rolling bearing fault diagnosis, a novel multi-sensor information fusion framework is proposed in this paper. First, a multi-sensor-based multi-frequency information fusion method is proposed. The multi-frequency information of each sensor is segmented first to enhance the datasets, and then a weighted fusion rule based on fuzzy entropy is constructed to fuse the information of different frequency components for multi-sensors. Second, a multi-kernel attention convolutional neural network is designed to realize multi-frequency feature capture, fusion, and fault classification of multi-sensors. Finally, two different rolling bearing datasets are used to implement fault diagnosis experiments. Experimental results show that the proposed method outperforms the comparative methods in terms of diagnostic performance and robustness.