Comparative analysis of different machine learning algorithms to predict mechanical properties of concrete
Bhanu P. Koya, Sakshi Aneja, Rishi Gupta, Caterina Valeo
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.