Assessment of remaining service life of deteriorated concrete bridges under imprecise probabilistic information

Abstract

This paper proposes a framework for the reliability-based remaining service life prediction of existing deteriorated structures considering both aleatory and epistemic uncertainties separately. A Bayesian probability box (p-box) is developed for modelling the epistemic uncertainty by considering the bounds of the distribution parameter, whereas the aleatory uncertainty is modelled as a precise distribution function. The framework allows to automatically update results and the bounds of estimation of remaining service life (RSL) by deploying data from regular and recurrent inspections of bridges, which are typically available in practice. The framework is applied to a real reinforced concrete bridge that has deteriorated due to corrosion of steel reinforcements to assess the capabilities of the proposed method. Results show a notable dispersion of the prediction of the RSL considering the imprecision of data which strongly highlights that the epistemic uncertainty should be considered when making decisions related to existing bridges. In fact, for the example presented, considering the epistemic uncertainty on corrosion of reinforcements could impact the probability of failure by a factor of nearly two. In addition, the updated Bayesian p-box can efficiently quantify significant reductions of epistemic uncertainty if additional information becomes available.