Estimating the compressive strength of GGBFS-based concrete employing optimized regression analysis

Carbon dioxide is produced during the manufacture of normal Portland cement; however, this gas may be minimized by utilizing ground granulated blast furnace slag (GGBFS). When planning and constructing concrete buildings, compressive strength (fc), a crucial component of concrete mixtures, is a need. It is essential to assess this GGBFS-blended concrete property precisely and consistently. The major objective of this research is to provide a practical approach for a comprehensive evaluation of machine learning algorithms in predicting the fc of concrete containing GGBFS. The research used the Equilibrium optimizer (EO) to enhance and accelerate the performance of the radial basis function (RBF) network (REO) and support vector regression (SVR) (SEO) analytical methodologies. The novelty of this work is particularly attributed to the application of the EO, the assessment of fc including GGBFS, the comparison with other studies, and the use of a huge dataset with several input components. The combined SEO and REO systems demonstrated proficient estimation abilities, as evidenced by coefficient of determination (R2) values of 0.9946 and 0.9952 for the SEO’s training and testing components and 0.9857 and 0.9914 for the REO, respectively. The research identifies the SVR optimized with the EO algorithm as the most successful system for predicting the fc of GGBFS concrete. This finding has practical implications for the construction industry, as it offers a reliable method for estimating concrete properties and optimizing concrete mixtures.