Bridges, Tunnels and other Transportation Structures
Full Session with Abstracts
Bridge health monitoring is an important component of infrastructure maintenance. Traditional bridge health monitoring techniques require sensors to be installed on bridges, which is costly and time consuming. In order to resolve this issue, new damage detection techniques by installing sensors on moving vehicles on bridges have gained rising attention from researchers in last decade. In this paper, a novel bridge damage detection technique focusing on monitoring population of bridges simultaneously utilizing crowdsourcing data collected from mobile phones on passing-by vehicles is developed. In this approach, Mel-frequency cepstral coefficients (MFCCs) is first extracted from the acceleration data collected from all the vehicles within a certain period. Principal component analysis (PCA) is to transform the features so that they are linearly uncorrelated. The damage can be identified by comparing the distributions of these transformed features. The results from the numerical analysis and laboratory experiments conducted using robot cars with smartphones show that the approach not only identifies the existence of the damage, but also provides useful information about severity. In addition to smartphones, the proposed framework can be extremely useful for SHM of population of bridges in smart cities using connected vehicle and other mobile technologies.