A hybrid platform using finite element model and sensor data for bridge condition monitoring and performance assessment

Abstract

With the advancement of sensing technology, structural condition monitoring techniques based on sensor data have been actively studied for civil infrastructure. Although these techniques contributed to overcoming the limitations of structural visual inspection, there are still several difficulties resulting from using only sensor data. In this study, a hybrid platform is proposed for the structural condition monitoring of bridges. The proposed platform is designed to derive two types of models, and it requires three types of input, a finite element model, time-series sensor data, and reliability analysis software. A condition monitoring model is constructed using Gaussian process regression (GPR) which is a Bayesian inference method, and a reliability-based model is derived for bridge performance assessment by performing reliability analysis in conjunction with finite element analysis. The proposed hybrid platform is applied to an actual bridge in the Republic of Korea, and corresponding analysis results are addressed with the discussion on the applicability of the proposed platform.