Machine Learning-Based Estimation of the Compressive Strength of Self-Compacting Concrete: A Multi-Dataset Study

Abstract

This paper aims at performing a comparative study to investigate the predictive capability of machine learning (ML) models used for estimating the compressive strength of self-compacting concrete (SCC). Seven prominent ML models, including deep neural network regression (DNNR), extreme gradient boosting machine (XGBoost), gradient boosting machine (GBM), adaptive boosting machine (AdaBoost), support vector regression (SVR), Levenberg–Marquardt artificial neural network (LM-ANN), and genetic programming (GP), are employed. Four experimental datasets, compiled in previous studies, are used to construct the ML-based methods. The models’ generalization capabilities are reliably evaluated by 20 independent runs. Experimental results point out the superiority of the DNNR, which has excelled other models in three out of four datasets. The XGBoost is the second-best model, which has gained the first rank in one dataset. The outcomes point out the great potential of the utilized ML approaches in modeling the compressive strength of SCC. In more details, the coefficient of determination (R2) surpasses 0.8 and the mean absolute percentage error (MAPE) is always below 15% for all datasets. The best results of R2 and MAPE are 0.93 and 7.2%, respectively.

Predicting Compressive Strength of High-Performance Concrete Using Hybridization of Nature-Inspired Metaheuristic and Gradient Boosting Machine

“…These indices were selected in this study because they are commonly used for performance measurement and comparison in previous works related to the compressive strength estimation of concrete mixes [24,26,30]. The metrics of RMSE, MAPE, and R 2 are given by:…”

“…Based on the review work [27] and recent papers [23,24,30,31], this study relies on the advanced approach of XGBoost to construct a data-driven model for estimating the CS of HPC. Considering the growing tendency to use metaheuristic algorithms for automating the model's construction process [24,[32][33][34][35], an integration of XGBoost [36] and Differential Flower Pollination (DFP) [37] is put forward.…”

Machine Learning-Based Prediction of the Compressive Strength of Brazilian Concretes: A Dual-Dataset Study

“…However, it is noted that this ratio is not the only relevant factor in compressive strength. Other elements, such as cement properties, aggregate particle size distribution, mixture proportions, chemical admixtures, and supplementary cementitious materials (such as fly ash and slag), may also influence this property [7].…”

Machine Learning Models for the Prediction of the Compressive Strength of Self-compacting Concrete

“…Similarly, Farooq et al (2021) [29] modeled the CS of SCC modi ed with y ash by implementing support vector machine (SVM), ANN and gene expression programming (GEP) programming. Based on experimental datasets gathered from prior studies, recent research by Hoang (2022) [30] employed Levenberg-Marquardt arti cial neural network (LM-ANN), genetic programming (GEP), deep neural network regression (DNNR), support vector regression (SVR), extreme gradient boosting machine (XGBoost), adaptive boosting machine (AdaBoost), gradient boosting machine (GBM) to predict the CS of SCC. The DNNR model outperformed the other models in his tests for predicting CS of SCC.…”