Sensors | |
Time-Frequency Methods for Structural Health Monitoring |
|
Alexander L. Pyayt1  Alexey P. Kozionov1  Ilya I. Mokhov1  Bernhard Lang2  Robert J. Meijer3  Valeria V. Krzhizhanovskaya3  | |
[1] Siemens LLC, Corporate Technology, Volynskiy lane 3A, St. Petersburg, 191186, Russia; E-Mails:;Siemens AG, Corporate Technology, Muenchen, 80200, Germany; E-Mail:;University of Amsterdam, Science Park 904, 1098 XH, Amsterdam, The Netherlands; E-Mails: | |
关键词: anomaly detection; structural health monitoring; time-frequency analysis; sensors; flood protection systems; levee monitoring; one-side classification; leakage detection; | |
DOI : 10.3390/s140305147 | |
来源: mdpi | |
【 摘 要 】
Detection of early warning signals for the imminent failure of large and complex engineered structures is a daunting challenge with many open research questions. In this paper we report on novel ways to perform Structural Health Monitoring (SHM) of flood protection systems (levees, earthen dikes and concrete dams) using sensor data. We present a robust data-driven anomaly detection method that combines time-frequency feature extraction, using wavelet analysis and phase shift, with one-sided classification techniques to identify the onset of failure anomalies in real-time sensor measurements. The methodology has been successfully tested at three operational levees. We detected a dam leakage in the retaining dam (Germany) and “strange” behaviour of sensors installed in a Boston levee (UK) and a Rhine levee (Germany).
【 授权许可】
CC BY
© 2014 by the authors; licensee MDPI, Basel, Switzerland.
【 预 览 】
Files | Size | Format | View |
---|---|---|---|
RO202003190028017ZK.pdf | 1975KB | download |