Comparative analysis of different machine learning algorithms to predict mechanical properties of concrete
- 26 April 2021
- journal article
- research article
- Published by Taylor & Francis in Mechanics of Advanced Materials and Structures
- Vol. 29 (25) , 4032-4043
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.Keywords
This publication has 15 references indexed in Scilit:
- Machine learning in materials informatics: recent applications and prospectsnpj Computational Materials, 2017
- Reviewing the Novel Machine Learning Tools for Materials Design2017
- Methods to Avoid Over-Fitting and Under-Fitting in Supervised Machine Learning (Comparative Study)2014
- Soft computing techniques for compressive strength prediction of concrete cylinders strengthened by CFRP compositesScience and Engineering of Composite Materials, 2013
- Categorical Variables in Regression Analysis: A Comparison of Dummy and Effect CodingInternational Journal of Education, 2012
- Prediction of elastic modulus of normal and high strength concrete by support vector machineConstruction and Building Materials, 2010
- Knowledge discovery of concrete material using Genetic Operation TreesExpert Systems with Applications, 2009
- An empirical model for predicting the mechanical properties of FRP-confined concreteConstruction and Building Materials, 2008
- Ensemble Methods in Machine Learning2000
- The use of neural networks for the prediction of fatigue lives of composite materialsComposites Part A: Applied Science and Manufacturing, 1999