MACHINE LEARNING APPLICATIONS FOR PREDICTING MECHANICAL AND DURABILITY PROPERTIES OF STEEL FIBER REINFORCED CONCRETE: A COMPREHENSIVE REVIEW

Abstract

Estimating concrete properties using soft computing techniques has been shown to be a time and cost-efficient method in the construction industry. Multilayer perceptron neural network (MLPNN) and ensembled machine learning models known as MLPNN-adaptive boosting and MLPNN-bagging are used for predicting steel fiber-reinforced concrete (SFRC) strength under compressive and flexural loads, with MLPNN-AdaBoost demonstrating higher R² values of 0.94 and 0.95 for flexural and compressive strength, respectively, and lower error values resulting in more precision than other methods (Al-Hashem et al., 2022). Three ensembled models including Gradient Boosting (GB), Random Forest (RF), and Extreme Gradient Boosting (XGB) are considered to predict the 28-day flexural strength of steel fiber-reinforced concrete, with Gradient Boosting showing the highest precision with an R² of 0.96, compared to Random Forest (RF) and Extreme Gradient Boosting (XGB), which had R² values of 0.94 and 0.86, respectively (Zheng et al., 2022).