Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
The State Representation Methodology (SRM) combined with the Frequency Slice Wavelet Transform (FSWT), which is a new time-frequency analysis tool, is proposed for assessing the condition of bridges on the basis of bridge monitoring data. First, this paper presents an overall description of the SRM method via FSWT analysis. It then shows, through numerical simulations, some novel characteristics and advantages of FSWT analysis in contrast to the conventional wavelet approach and the feature extraction accuracy of SRM analysis for the detection of bridge damage on the basis of monitoring data. The principal results obtained through this study can be summarized as follows: (1) details of a newly proposed SRM and its application to bridge condition assessment based on bridge monitoring data are introduced. The proposed SRM combined with the FSWT is validated as a novel time-frequency analysis tool for assessing bridge condition on the basis of bridge monitoring data. (2) New properties of FSWT analysis are demonstrated, and advantages in contrast to the traditional wavelet method are highlighted. Feature extraction in SRM analysis is precise for damage detection in a bridge system on the basis of monitoring data and using numerical simulations.
Volkan Cevher, Mikhail Kapralov, Jonathan Mark Scarlett, Amir Zandieh
,
Nikola Besic, Urs Martin Germann, Daniele Nerini