A spectral-based clustering for structural health monitoring of the Sydney Harbour Bridge
详细信息 查看全文
- 作者：Mehrisadat Makki Alamdari ; MehrisadatMakki.Alamdari@data61.csiro.au" class="auth_mail" title="E-mail the corresponding author ; Thierry Rakotoarivelo Thierry.Rakotoarivelo@data61.csiro.au" class="auth_mail" title="E-mail the corresponding author ; Nguyen Lu Dang Khoa NguyenLuDang.Khoa@data61.csiro.au" class="auth_mail" title="E-mail the corresponding author
- 关键词：Structural Health Monitoring ; Power Spectral Density ; Spectral Moment ; Clustering ; Anomaly Detection ; k-means&minus ; &minus
- 刊名：Mechanical Systems and Signal Processing
- 出版年：2017
- 出版时间：15 March 2017
- 年：2017
- 卷：87
- 期：part_PA
- 页码：384-400
- 全文大小：1746 K
文摘
- •
A method to detect structural and system anomalies on infrastructures is proposed.
- •
The method is based on the clustering of the spectral moments of accelerations.
- •
The method was evaluated on large data from the Sydney Harbour Bridge, Australia.
- •
Known structural and instrumentation anomalies were correctly detected.
- •
Previously unknown anomalies were detected and confirmed with more investigations.