Bayesian Model Updating of a Simply-Supported Truss Bridge Based on Dynamic Responses

Abstract

AbstractThis study intends to investigate the application of model updating based on forced vibration data to a simply-supported truss bridge. A fast Bayesian FFT method was used to perform the modal identification obtained from field tests, and the Transitional Markov Chain Monte Carlo (TMCMC) algorithm is employed to generate samples. Although updating as many parameters as possible is the ideal model update process, it is not practical to identify all the parameters because of limitation of the experimental data. The bridge was thus divided into several clusters, and the values of the updated parameters of the members in the same cluster are assumed to be equal. Two model updating schemes were discussed as an example to investigate the effect of parameter selection, such as how to model the spring at each support, in model updating process. It was observed that although models with more parameters tend to fit better, the updated result often showed a different trend from the engineering prediction.KeywordsBayesian model updatingTransitional Markov Chain Monte CarloField vibration testDamage detectionSimply-supported truss bridge