ABSTRACT
Structural health monitoring has been increasingly used due to the advances in sensing technology and data analysis, facilitating the shift from time-based to condition-based maintenance. This work is part of the efforts which have applied structural health monitoring to the Sydney Harbour Bridge – one of Australia’s iconic structures. It combines data fusion and feature extraction, dimensionality reduction and pattern recognition techniques to accurately distinguish faulty components from well-functioning ones using ambient vibration testing. Specifically, frequency domain decomposition is used to aggregate data from multiple sensors and random projection is used for dimensionality reduction on the feature data. Then, healthy and damaged patterns of bridge components are learned in the lower dimensional projected space using one-class support vector machine. The experimental results showed high feasibility of the proposed method in damage detection and assessment in structural health monitoring.
