Compressive strength prediction of concrete blended with carbon nanotubes using gene expression programming and random forest: hyper-tuning and optimization

Abstract

The strength of carbon nanotubes (CNTs) and cement composites is dependent on multiple variables. In addition, CNTs added to a cement-based matrix can boost its strength. However, the information related to CNTs characteristics is limited and scarce. Their incorporation may substantially enhance the mechanical and durability properties of cementitious mixtures. Despite challenges such as high cost and workability problems. Therefore, proper consumption of these materials must be used to attain desired qualities. The principal plan of this investigation is to create predictive framework by utilizing machine-learning algorithms. Gene expression programming (GEP), and the random forest algorithm (RFA) is employed to estimate the compressive strength of concrete mixed with CNTs. GEP is used as an individual approach, and RFA is used as an ensemble method to depict the most influential model. The outcomes of the two models are assessed by employing external K-fold cross-validation, and a comparison is done. A comprehensive database is established comprising 282 data points for the CS with blended CNTs. The model is then calibrated using six inputs, including curing time (CT), water-to-cement ratio (W/C), fine aggregate (FA), carbon nanotube content (CNTs), cement content (CC), and coarse aggregate (CA). In addition, the predicted results are validated using k-fold cross-validation, and performance metrics, such as mean absolute error (MAE), root squared error (RSE), correlation coefficient (R2), root mean square error (RMSE), and relative root mean square error (RRMSE). The result shows that RF regression with the nth estimator shows robust accuracy by showing minimal errors as analyzed to individual RF and GEP models. Likewise, the nth model depicts higher R2 = 0.96, and validation results demonstrate low errors. Moreover, the GEP model excels in terms of prediction through the empirical equation. In addition, Shapley analysis (SHAP) is performed to check the distribution of parameters to output. The result reveals that curing time, cement, and water to binder have substantial influence of CNT based concrete composite.

Keywords

• Carbon nanotubes
• Gene expression programming
• Random forest
• K-fold cross-validation
• Statistical measures