Traffic volume estimation in a cable-stayed bridge using dynamic responses acquired in the structural health monitoring

Abstract

This paper presents the traffic volume estimation by constructing a statistical model using dynamic response data acquired by a structural health monitoring system installed on an in-service cable-stayed bridge. The structural health monitoring system consists of various sensors, including accelerometers, tilt sensors, temperature sensors, and the vehicle counting system. In this paper, the correlations between the response features from dynamic data, peak frequencies and amplitudes of responses, and the temperature and the traffic volume were firstly investigated. The results revealed that the traffic volume was a dominant factor that influenced on variances of the extracted features, while the temperature showed low effects on them in the target bridge. Some of the response features that showed high correlations were then selected for constructing a linear regression model to estimate the total traffic volume per 5 min. The constructed model then showed the accurate fitting performance to the data, and it was also capable of predicting the traffic volume on the bridge. Copyright © 2016 John Wiley & Sons, Ltd.