Integrating machine learning and Monte Carlo Simulation for probabilistic assessment of durability in RC structures affected by carbonation-induced corrosion

This study introduces an original approach that integrates a machine-learning algorithm and a Monte Carlo simulation technique to evaluate the durability of reinforced concrete (RC) structures subjected to carbonation-induced corrosion. The study commences by forecasting the carbonation depth of concrete samples subjected to natural conditions, employing Artificial Neural Networks (ANNs) with the backpropagation algorithm. A database was created by gathering information from 870 literature sources, and it was utilized to build 100 ANN models with different topologies. A rigorous evaluation was conducted to identify the most efficient ANN architecture. Subsequently, the approach was applied in a case study to evaluate the design life of structures in a real scenario, thereby demonstrating its tangible value in real-world applications. In addition, a parametric study was undertaken to examine the material’s compressive strength and the thickness of the concrete cover, which influences its durability. The design life was determined using the Monte Carlo Simulation technique coupled with the ANN model, in which the probability of depassivation due to carbonation was forecasted. Findings indicate that decreasing the concrete cover by 25% would lead to a 48% decrease in the structure’s design life, highlighting the influence of accurately determining and implementing the thickness of the concrete cover for RC structures. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.