Fault Diagnosis in Rolling Bearings Using Multi-Gaussian Attention and Covariance Loss for Single Domain Generalization

This article introduces a new method for fault diagnosis in rolling bearings, addressing performance drops caused by domain shifts under changing operational conditions. Unlike domain generalization (DG), which relies on multiple source domains, this method focuses on single DG to learn robust features from a single domain and generalize to new conditions. The proposed method, called multi-Gaussian attention-based single DG (MGA-SDG), aims to enhance model generalization to unseen target domains. Multi-Gaussian attention (MGA) projects multiscale fault features into Gaussian feature spaces using both single modal and bimodal Gaussian functions, assigning attention weights based on feature alignment with these functions. This process ensures consistent and robust feature representations across domains. Furthermore, a covariance loss is employed to maintain distinct distributions for the weighted features, enhancing feature diversity. Experimental results on both public and proprietary rolling bearing datasets show that MGA-SDG achieves over 95.81% accuracy. This performance exceeds that of state-of-the-art methods, highlighting its potential for real-world industrial applications.