It is widely accepted that Structural Health Monitoring (SHM) is a critical component for creating sustainable Civil Infrastructure Systems (CIS). The effectiveness of the data analysis methods used in the SHM system is one of the key factors that determine the success rate of the implementations. Since various types of measurements, e.g. acceleration, strain and image, can be utilized in the SHM systems, different data analysis methods should be developed for extracting useful information from large amounts of data. In this paper, the authors provide a rather general discussion of the critical aspects of SHM in the context of condition assessment and damage detection. A time series analysis based method is investigated for structural damage detection. Moreover, a computer vision based technique is explored for anomaly (or novelty) detection. It is shown that certain algorithms using these approaches can be developed for rapid extraction of information about the changes in the behavior of the structure. Examples from laboratory and real life tests are presented for verification purposes and the performances of these methodologies are discussed in light of the experimental results. Finally, research needs to improve the accuracy and applicability of SHM systems for advancing the sustainable CIS are discussed.
展开▼
