Zero-Shot Detection of Elastic Transient Morphology Across Physical Systems

TL;DR

This paper demonstrates that a neural representation learned from gravitational-wave interferometric data can be effectively transferred as a zero-shot operator for anomaly detection in different physical systems, such as bearings, without retraining.

Contribution

It introduces a morphology-sensitive operator trained on gravitational-wave data that generalizes to unseen sensors and systems, enabling zero-shot anomaly detection and health monitoring.

Findings

Operator achieves high AUC in fault detection (0.90 window-level, 0.99 file-level).

Transferability is limited by physical signal characteristics, not CNN features.

Morphology-preserving transformations degrade performance, indicating sensitivity to time-frequency structure.

Abstract

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.