Network-scale deterioration modelling of bridges based on visual inspections and structural attributes

Abstract

Managing and maintaining bridges on a network-scale is directly associated with the capacity to monitor and forecast the deterioration state of these bridges. Data-driven models such as state-space models (SSM) has been effectively utilized for modelling the deterioration behaviour based on visual inspections of bridge network. However, such a model relies only on the inspection data and does not take into account the structural attributes of each bridge. In addition, the capacity for estimating the deterioration speed is limited, especially in cases with limited number of inspections. In this study, we combine the SSM deterioration model with a kernel regression (KR) method. The SSM-KR framework improves the estimates of the deterioration speed and reduces the overall bias in forecasting the deterioration. The role of KR is to model patterns between the deterioration speed and the structural attributes. Verification and validation of the SSM-KR model are done using synthetic data and real data respectively, whereby the real data is taken from a Canadian bridge network. In addition, the performance of SSM-KR is benchmarked against the existing SSM model using an independent test set of real inspections.