Bayesian approach for characterizing wind-induced displacement responses of bridge using structural health monitoring data

This paper presents an approach for quantifying the uncertainty in assessing wind-induced displacement responses of bridge with the data acquired from a Structural Health Monitoring (SHM) system. Both the wind speed and wind direction are served as quantitative explanatory variables in the Bayesian regression model to account for the wind-induced displacement responses. The parameters of the model as well as the uncertainties of the parameters and the model are identified by using the Markov Chain Monte Carlo (MCMC) method. To validate the performance of the formulated regression model, a new set of data is fed into the model for testing. The proposed approach is illustrated by applying it to the monitoring data acquired from a long-span suspension bridge − the Tsing Ma Bridge. Through comparing the Root Mean Square Errors (RMSE) in training and testing phases, it is demonstrated that the Bayesian model performs comparably well in the case of unseen data.