Zero-Shot Detection of Elastic Transient Morphology Across Physical Systems
This work addresses cross-domain anomaly detection for predictive maintenance, showing significant transferability but is incremental in applying learned representations to new sensor types.
The paper tackled the problem of detecting elastic transient anomalies across different physical systems without target-domain training, achieving strong zero-shot performance with AUC up to 0.99 on bearing fault datasets and demonstrating robustness in extreme-event scenarios.
We test whether a representation learned from interferometric strain transients in gravitational-wave observatories can act as a frozen morphology-sensitive operator for unseen sensors, provided the target signals preserve coherent elastic transient structure. Using a neural encoder trained exclusively on non-Gaussian instrumental glitches, we perform strict zero-shot anomaly analysis on rolling-element bearings without retraining, fine-tuning, or target-domain labels. On the IMS-NASA run-to-failure dataset, the operator yields a monotonic health index HI(t) = s0.99(t)/tau normalized to an early-life reference distribution, enabling fixed false-alarm monitoring at 1-q = 1e-3 with tau = Q0.999(P0). In discrete fault regimes (CWRU), it achieves strong window-level discrimination (AUC_win about 0.90) and file-level separability approaching unity (AUC_file about 0.99). Electrically dominated vibration signals (VSB) show weak, non-selective behavior, delineating a physical boundary for transfer. Under a matched IMS controlled-split protocol, a generic EfficientNet-B0 encoder pretrained on ImageNet collapses in the intermittent regime (Lambda_tail about 2), while the interferometric operator retains strong extreme-event selectivity (Lambda_tail about 860), indicating that the effect is not a generic property of CNN features. Controlled morphology-destruction transformations selectively degrade performance despite per-window normalization, consistent with sensitivity to coherent time-frequency organization rather than marginal amplitude statistics.