Fault diagnosis method for rolling bearing based on attention mechanism and BiTCN model

Fault diagnosis of rolling bearings typically requires the extraction of a large number of features. However, due to the inherent limitations of unidirectional feature extraction, it is challenging to capture temporal dependencies in both directions for non-stationary signals, resulting in low fault recognition accuracy and poor model adaptability to diverse datasets. To address this issue, we propose a fault diagnosis model based on attention mechanisms and a bidirectional temporal convolutional network (BiTCN). Firstly, the vibration signal is preprocessed. Then, the processed signal is fed into Squeeze-and-Excitation Networks (SENet) to select diagnostically relevant features, reducing computational load. Next, the BiTCN processes the selected features to extract bidirectional temporal dependencies from vibration signals, which unlike unidirectional TCN models. The multi-head attention mechanism (MA) dynamically reallocates weights to these features, which are then classified by a fully connected layer for fault diagnosis. The bearing fault datasets from Jiangnan University and Case Western Reserve University validate the fault diagnosis performance of our method. Experimental results show that the accuracy of the proposed model on the bearing fault dataset from Jiangnan University is 99.49%, and the accuracy of the model on the Case Western Reserve University dataset can reach 99%. These results demonstrate that the proposed model exhibits excellent bearing fault diagnosis performance, meets the requirements for fault diagnosis, and provides a novel approach for bearing fault diagnosis.