Network Construction for Bearing Fault Diagnosis Based on Double Attention Mechanism

Abstract

Aiming at the difficulty of feature extraction in the case of multicomponent and strong noise in the traditional rolling bearing fault diagnosis method, this paper proposes a bearing fault diagnosis network with double attention mechanism. The original signal with noise is decomposed into a series of intrinsic mode functions (IMFs) by the Empirical Mode Decomposition method. The Pearson correlation coefficient is discussed to filter the IMFs components for signal reconstruction. The spatial features of the reconstructed signal are extracted by attention convolutional networks. Then, time series features are extracted based on the long short-term memory method. Furthermore, the importance of temporal features is measured through a temporal attention mechanism. The Softmax layer of the constructed network is used as the classifier for fault diagnosis. Comparing this method with the existing methods of experiments, the proposed method has not only better diagnosis accuracy but also stronger antiinterference ability and generalization ability, which can accurately diagnose and classify the bearing fault types. The fault diagnosis accuracy rate for each load is above 99%.