Shear Condition Classification of Cracked Reinforced Concrete Beams Using Machine Learning

Abstract

RC bridges represent about 40% of the US bridge inventory, with many of these bridges reaching or surpassing their design service life. As a result, there is a significant number of structures that require fast and accurate structural evaluation. Shear deficiencies can pose a higher safety risk than flexure deficiencies since shear failures are sudden. This study correlates shear crack width with shear condition and proposes a machine-learning framework to place RC beams into shear condition categories using quantitative estimates of shear, stiffness, and stirrup strain histories. The results of the proposed framework are compared with those from existing quantitative and qualitative assessment methodologies. The quantitative predictions of residual shear capacity and stiffness by the proposed framework are closer to experimental measurements than the ones by the existing methodologies. The qualitative condition classifications of the framework indicate less urgency for repair compared with the ones of the existing methodologies. The proposed framework enables the ranking of bridges within the same shear condition category due to its quantitative nature, and it has been implemented in a software application and can be used to set priorities for repair. Occasional overloading of bridges or older designs that are not compliant with modern design code requirements may lead to shear cracks in RC bridge elements. These cracks run diagonally and are typically found near the supports where shear is high. Bridge owners need tools to evaluate RC bridge elements with shear cracks to ensure that they have sufficient capacity. This study introduces a machine-learning-based software application that provides fast and accurate estimations of shear condition of RC beams using crack width, geometric properties, material properties, and reinforcement details as input. The output is shear, stirrup strain, stiffness corresponding to a crack width that can be measured on site, as well as clustering of bridges in an inventory based on this output. This application can be an alternative to ad-hoc evaluation methods, costly load testing, or time-consuming detailed finite-element analyses. It helps engineers, bridge owners, and asset managers make informed decisions regarding prioritization of maintenance actions by identifying bridges with the highest needs of repair.