Concrete aging factor prediction using machine learning

Abstract

Accurate prediction of concrete aging factor is pivotal for performance-based durability reinforced concrete design. This study introduces an innovative method leveraging machine learning techniques, employing seven algorithms: Bagging, Random Forest, AdaBoost, Gradient Boosting, XGBoost, CatBoost, and LightGBM. The dataset comprises 130 instances with seven input features describing cement type, cement content, pozzolan type, pozzolan content, w/b ratio, exposure condition, and age of concrete. Seventy models were trained across five scenarios, categorized into two groups: Group I using all features of the raw dataset, and Group II incorporating engineered features. Model performance, assessed by mean-absolute error (MAE), mean-square error (MSE), root-mean-square error (RMSE), and coefficient of determination (R²), reveals superior performance in Group II compared to Group I. Notably, the LightGBM algorithm in Scenario III outperforms all models with a remarkable MAE of 0.110, MSE of 0.018, RMSE of 0.133, and R² of 0.818. Subsequently, models from Scenarios V and IV exhibit strong performance. The implemented machine learning models demonstrate notable generalizability, effectively capturing feature interrelations without the need for resource-intensive experimental testing.