A self-supervised learning framework integrating prior knowledge and simulation data for rolling bearing fault diagnosis with few-shot and imbalanced data

Abstract

Abstract The compound problem of few-shot and data imbalance remains a major obstacle in rolling bearing fault diagnosis. To address this issue, this paper proposes IMSSiT-SSL, a self-supervised learning framework that integrates prior knowledge with simulation data-driven approaches. Unlabeled simulation datasets are used for self-supervised pre-training through two physics-informed pretext tasks: a kurtosis-guided masked reconstruction task that selectively masks high-kurtosis segments to force the model to capture intrinsic fault features, and a characteristic indicator-based pseudo-label prediction task that explicitly embeds domain expert knowledge into the representation learning process. This dual-task pre-training strategy alleviates the few-shot challenge while directing the model’s attention toward fault-relevant impact segments, improving the physical interpretability of feature extraction. Subsequently, a small amount of labeled data is used for fine-tuning, where an adaptive boundary-regularized dual focal loss is introduced to encourage the model to focus on discriminating minority class samples, thus mitigating the negative effects of imbalanced data. Experimental results demonstrate that the proposed method achieves G -mean improvements of 3.07%–20.62% over competing methods across various imbalance ratios, and maintains a diagnostic accuracy of 98.78% under cross-speed few-shot conditions with only 30 labeled samples per class.