GSR-enhanced sparse feature learning for bearing fault diagnosis under data scarcity

Abstract

In bearing fault diagnosis, small-sample and class-imbalance issues are highly challenging, severely constraining the generalization capability of deep learning models in practical applications. Generalized stochastic resonance (GSR) has demonstrated significant potential in enhancing weak fault features, yet its effective integration with data-driven deep learning frameworks remains insufficiently explored. To address these challenges, this study proposes a GSR-enhanced robust sparse feature learning framework (RGSRNet). Specifically, the framework derives stability control conditions for the GSR system, integrates a lightweight dual-branch architecture to fuse global convolutional features and local sparse spectral peak features, and constructs a Wasserstein-regularized dual-loss function to optimize the feature space distribution. Experimental results confirm that RGSRNet consistently outperforms mainstream baseline methods under few-shot, class-imbalanced, noisy, and variable-speed conditions. In particular, RGSRNet achieves 99.92% accuracy with only 9 training samples per class and maintains a 99.89% F1-score under an extreme 1:10 class-imbalance scenario. It also achieves over 94% accuracy under strong noise interference and retains more than 91% accuracy under variable-speed conditions with only 3% training data. In addition, RGSRNet requires only 0.2423 M parameters and 9.0516 M FLOPs, indicating its potential for lightweight industrial deployment.