Prediction of Concrete Compressive Strength Using Machine Learning Techniques

Authors

  • غصون اندراوس قسم الهندسة الإنشائية- كلية الهندسة المدنية- جامعة اللاذقية- اللاذقية – سورية

Keywords:

Compressive strength, Machine learning, Prediction, Regression models, Random Forest, XGBoost.

Abstract

This study aims to develop a predictive model for estimating the compressive strength of concrete using machine learning techniques, based on a large experimental dataset of standard concrete mixtures obtained from the UCI Machine Learning Repository database. The dataset contains all the necessary information for model development, including the quantity of the main concrete components: cement, blast furnace slag, fly ash, water, superplasticizer, coarse aggregate, fine aggregate, in addition to the experimentally measured compressive strength of cylindrical concrete samples at different ages ranging from 3 to 365 days.

The dataset was divided into a training set (70%) and a testing set (30%). Subsequently, four machine learning models were developed using the Python programming language, namely: Linear Regression, Random Forest, Gradient Boosting, and Extreme Gradient Boosting (XGBoost). The performance of these models was evaluated using several statistical metrics, including the coefficient of determination (R²), mean squared error (MSE), and root mean squared error (RMSE), in order to identify the most accurate predictive model.

The results demonstrated the superiority of the XGBoost model in terms of prediction accuracy and its ability to effectively capture the nonlinear relationship between the concrete mixture components and compressive strength. These findings confirm the effectiveness of machine learning techniques—particularly gradient boosting-based algorithms such as XGBoost―in improving the accuracy of compressive strength prediction, reducing the time and cost associated with conventional laboratory testing, and providing a reliable approach for predictive modeling in modern engineering applications.

Downloads

Published

2026-10-29