Database and optimized machine learning prediction of the deteriorated response of corroded reinforced concrete beams

Abstract

This research introduces an extensive database aggregating 54 experimental programs with 804 test specimens and 45 input parameters, investigating the implications of chloride-induced corrosion on the deteriorated mechanical response of corroded reinforced concrete beams. Several machine learning models are explored to determine the highest performing predictor for five key response variables – the residual ultimate moment capacity, residual capacity factor, yield load, yield displacement, and the ultimate displacement. Three existing analytical approaches are included for comparison to verify the efficacy of the trained statistical models. The optimized machine learning models significantly outperformed conventional analytical methods and achieved high levels of predictive accuracy. Ensemble tree-based learning algorithms, namely gradient-boosting regression trees and random forests, consistently produced the best predictions. Finally, the top-performing models are aggregated into a Python-based application that allows users to input new data and predict the mechanical response of a corroded beam failing in bending.