Estimation of the improved high-performance concrete’s mechanical characteristics using unique regression methods

Abstract

A unique approach for assessing the compressive strength (CS) of high-performance concrete (HPC) incorporating blast furnace slag (BFS) and fly ash (FA) has been created using support vector regression (SVR) analytics. In order to identify crucial SVR methodology variables that could be adjusted for improved performance, the Henry gas solubility optimization (HGSO) and Cuckoo search optimization (CSO) algorithms were both employed in this study. The recommended methods were developed utilizing 1030 experiments and eight inputs, including the CS as the forecasting objective, admixtures, aggregates, and curing age as the main mix design component. The results were then contrasted with those from related literature. The estimate results suggest that combined HGSO-SVR and CSO-SVR analysis might perform extraordinarily well in estimating. The Root mean square error value for the HGSO - SVR decreased remarkably when compared to the CSO - SVR. As can be seen from the comparisons, the HGSO - SVR that was built beats anything previously published. In conclusion, the suggested HGSO - SVR analysis might be determined as the proposed system for forecasting the CS of HPC improved with FA and BFS.