Bearing Fault Diagnosis Under Multisensor Fusion Based on Modal Analysis and Graph Attention Network

In existing research on rotating machinery diagnosis using graph neural networks (GNNs), most methods are based on vibration analysis under contact sensor monitoring. However, the gathered vibration signal is sensitive to the increased mass of the sensor, and after prolonged close contact, the vibration sensor may cause structural damage to the object. A multisensor fusion based on modal analysis and graph attention network (MFMAGAT) for bearing fault diagnosis is suggested as a solution to these issues. First, we proposed a phase-based full-field noncontact measurement method based on direction-controlled pyramids to extract phase information at different scales and directions and use the phase information to characterize the vibration of the structure. Then, based on the vibration and acoustic signals of the characterized structure, we constructed a kernel function that can fuse the heterogeneous information, and its singular value decomposition can jointly characterize the response of the structure at the same frequency bands from the video data and the acoustic data. Finally, considering that the decomposed features are independent and orthogonal to each other, the GAT is introduced at this time to find the weights among the components to jointly characterize the structural damage and improve the damage recognition accuracy. Comparison results show that the proposed method is effective and performs better than other conventional GNN diagnosis methods.