Abstract

Concrete is the most widely used construction material throughout the world. Extensive experiments are conducted every year to study the physical, mechanical, and chemical properties of concrete involving a hefty amount of money and time. This work focuses on the utilization of Machine Learning (ML) algorithms to predict various concrete properties for avoiding unnecessary experimentation. In this work, six mechanical properties of concrete namely modulus of rupture, compressive strength, modulus of elasticity, Poisson’s ratio, splitting tensile strength, and coefficient of thermal expansion are estimated by applying five different ML algorithms viz. Linear Regression, Support Vector Machine, Decision Tree, Random Forest, and Gradient Boosting models on the Wisconsin concrete mixes database. Further, these ML models were evaluated to identify the most suitable model that can reliably predict the mechanical properties of concrete. The approach followed in this research was verified using the 10-fold Cross-Validation technique to eliminate training and testing split bias. The Grid Search Cross Validation method was used to find the best hyperparameters for each algorithm. Root mean squared error (RMSE) and coefficient of determination (R²) results showed that the Support Vector Machine outperformed the other models applied on the datasets. Support Vector Machine predicted the modulus of rupture of concrete after a curing time of 28 days with an R² score of 0.43, which is better than the R² scores of Random Forest and Gradient Boosting advanced algorithms by 34% and 26%, respectively.

摘要

混凝土是世界上使用最广泛的建筑材料。每年都会进行广泛的实验来研究混凝土的物理、机械和化学特性，这涉及大量的金钱和时间。这项工作的重点是利用机器学习 (ML) 算法来预测各种具体属性，以避免不必要的实验。在这项工作中，通过应用五种不同的机器学习算法，即估计混凝土的六种力学性能，即断裂模量、抗压强度、弹性模量、泊松比、劈裂抗拉强度和热膨胀系数。Wisconsin 混凝土混合数据库上的线性回归、支持向量机、决策树、随机森林和梯度提升模型。更远，对这些 ML 模型进行了评估，以确定能够可靠预测混凝土力学性能的最合适模型。本研究采用的方法已使用 10 倍交叉验证技术进行验证，以消除训练和测试分裂偏差。网格搜索交叉验证方法用于为每种算法找到最佳超参数。均方根误差 (RMSE) 和决定系数 (R ² ) 结果表明，支持向量机的性能优于应用于数据集的其他模型。支持向量机预测混凝土在养护 28 天后的断裂模量，R ²得分为 0.43，比随机森林和梯度提升高级算法的R ²得分分别好34% 和 26%。