Author(s)

Muhammad Sufian, Xin Wang, Mohamed F.M Fahmy, Zhishen Wu, Muhammad Rahman, Amr M.A Moussa

Corresponding Author

Muhammad Sufian

Abstract

This study investigates the influence of coarse aggregate (CA) type and shape on the compressive strength of concrete. Two types of coarse aggregates were used, i.e., basalt crushed and naturally rounded of 15 mm size. Eight concrete mixtures were designed according to four distinct concrete mix design (CMD) codes. A total of 64 concrete samples were prepared and tested under compression. The results show that concrete made with basalt CA achieved significantly higher CS (by 7% to 39%) compared to concrete made with natural CA, across different CMD codes. The incorporation of basalt CA enhanced the toughness and ductility of concrete, making it a better option for normal and medium-strength concrete structures. In addition to the experimental program, two ensembled machine learning (ML) models, i.e., extreme gradient boosting (XGB), and random forest (RF) were employed to forecast the CS of concrete. RF and XGB showed remarkable accuracy as evident by R2= 0.93 and R2= 0.92, respectively, and low error matrices. Moreover, the feature importance analysis identified cement content and CA type as the primary determinants of strength, while the water-cement ratio served as a crucial regulator.

Keywords

Coarse Aggregate, Basalt, Mix Design Code, Compressive Strength, Machine Learning