Forecasting deterioration of bridge components from visual inspection data

In order to extract the optimal output in the form of good management decisions with least resources, a bridge management system or BMS in short, is an essential part for every road transport authority. In a BMS, decisions regarding frequency of maintenance, conducting repairs and rehabilitation are based on inspection data collected for the bridges by trained inspectors following a condition rating method developed by the authority. The road authorities are constantly trying to convert these condition monitoring data to a meaningful practical decision supporting tool. To address this need, a study has been conducted to forecast deterioration of reinforced concrete bridge elements using Markov process. The aim of the research work is to identify the future maintenance needs utilizing the visual inspection data. Visual inspection data has been sourced from Victoria, Australia and transition matrices have been derived using Bayesian optimisation techniques of Markov chain model to predict the future condition of bridge components. Clustering of data with respect to input parameters such as era of construction, exposure conditions, annual average daily traffic and percentage of heavy vehicles can provide an improved deterioration model for bridge Engineers. Deterioration trends for three major structural components are presented in this paper.