EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Zero-Shot Bridge Health Monitoring Using Cepstral Features and Streaming LSTM Networks

Azin Mehrjoo, Kyle L. Hom, Homayoon Beigi, Raimondo Betti

Infrastructures · 03.11.2025 · 10 (11) · 292

DOI: 10.3390/infrastructures10110292 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Infrastructures, online erschienen am 03.11.2025. Verfasst von Azin Mehrjoo und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a real-time, output-only structural health monitoring framework that integrates damage-sensitive cepstral features with a streaming Long Short-Term Memory (LSTM) network for automated damage detection. Acceleration time histories are segmented into overlapping windows, converted into cepstral coefficients, and processed sequentially by a stacked LSTM architecture with state carry-over. This design preserves temporal dependencies while enabling low-latency inference suitable for continuous monitoring. The framework was evaluated under a strict zero-shot setting on the full-scale Z24 Bridge benchmark, in which no training or calibration data from the bridge were used. Our results show that the proposed approach can reliably discriminate staged damage states and track their progression using only vibration measurements. By combining a well-established spectral feature representation with a streaming sequence model, the study demonstrates a practical pathway toward deployable, data-driven monitoring systems capable of operating without retraining on each individual asset.

Zitieren

APA

Mehrjoo, A., Hom, K. L., Beigi, H., & Betti, R. (2025). Zero-Shot Bridge Health Monitoring Using Cepstral Features and Streaming LSTM Networks. Infrastructures, 10(11), 292. https://doi.org/10.3390/infrastructures10110292

Vancouver

Mehrjoo A, Hom KL, Beigi H, Betti R. Zero-Shot Bridge Health Monitoring Using Cepstral Features and Streaming LSTM Networks. Infrastructures. 2025;10(11):292. doi:10.3390/infrastructures10110292

BibTeX
@article{Mehrjoo2025,
  author = {Mehrjoo, Azin and Hom, Kyle L. and Beigi, Homayoon and Betti, Raimondo},
  title = {Zero-Shot Bridge Health Monitoring Using Cepstral Features and Streaming LSTM Networks},
  journal = {Infrastructures},
  year = {2025},
  volume = {10},
  number = {11},
  pages = {292},
  doi = {10.3390/infrastructures10110292}
}
Kostenlos starten →