Transformer-Embedded Task-Adaptive-Regularized Prototypical Network for Few-Shot Fault Diagnosis

Few-shot fault diagnosis (FSFD) seeks to build accurate models from scarce labeled data, a frequent challenge in industrial settings with noisy measurements and varying operating conditions. Conventional metric-based meta-learning (MBML) often assumes task-invariant, class-separable feature spaces, which rarely hold in heterogeneous environments. To address this, we propose a Transformer-embedded Task-Adaptive-Regularized Prototypical Network (TETARPN). A tailored Transformer-based Temporal Encoder Module is integrated into MBML to capture long-range dependencies and global temporal correlations in industrial time series. In parallel, a task-adaptive prototype regularization dynamically adjusts constraints according to task difficulty, enhancing intra-class compactness and inter-class separability. This combination improves both adaptability and robustness in FSFD. Experiments on bearing benchmark datasets show that TETARPN consistently outperforms state-of-the-art methods under diverse fault types and operating conditions, demonstrating its effectiveness and potential for real-world deployment.