Prediction of compressive strength of self-compacting concrete using four machine learning technics

Abstract

In self-compacting concrete (SCC), admixtures and other modifiers are commonly used to decrease bleeding and segregation. Higher air content may be necessary to improve the mixture's ability to withstand freezing and thawing. Based on the suggestions of the AFGC and EFNARC, several SCC mixes were created in this study. There was an air-entrainment admixture (AEA) applied in various percentages.Experimental studies have been performed to examine the mechanical characteristics of SCC's, such as sonic velocity (at 1 and 7 days) and compressive strength (at 1, 7, and 28 days) using different air content. This mechanical characterization is used taking into account void ratio and water absorption.In this sense, the objective of this work is to predict the compressive strength at 28 days from the intrinsic parameters such as void ratio, water absorption, and the mechanical responses, at a young age, such as sonic velocity and compressive strength (at 1 and 7 days).To do this, we used the most famous machine learning algorithms to know: Multiple Linear Regression (MLR), Random Forest Regression (RFR), Decision Tree Regression (DTR) and Support Vector Regression (SVR). Finally, the best-proposed model is given on the basis of statistical comparison between the different used algorithms.