Determination of surface chloride concentration accumulation of concrete in marine environment by machine learning

There are multiple aggressive agents like chloride ions with high concentrations in marine environment, posing a serious threat to the durability of concrete structures. The accumulation process of surface chloride concentration of concrete is one of the most critical factors in chloride penetration within concrete. A machine learning (ML) model was developed to predict C_s based on a chloride penetration database of both field exposure and laboratory test. In order to ensure the model’s generalization capability, the database covers C_s of concrete with different environmental parameters and exposure time. Four different machine learning algorithms including gaussian process regression (GPR), artificial neural networks (ANN), support vector machines (SVM), random forests (RF) were employed to train and validate with the dataset. Thereafter, the machine learning model combined with Monte Carlo simulation was used to predict the randomness of the surface chloride concentration of concrete.