Artificial rabbit optimization‐based ANFIS model development for predicting the compressive strength of GGBFS‐based concrete.

The carbon dioxide emissions associated with the production of conventional Portland cement may be mitigated through the utilization of ground granulated blast furnace slag (GGBFS). The consideration of compressive strength (fc) is essential in the design and construction of concrete structures, as it is an essential demand in concrete mixtures. The primary objective of this study is to establish an effective approach for conducting a comprehensive evaluation of machine learning algorithms in predicting the fc of concrete that incorporates GGBFS. The work focuses on using the adaptive neuro‐fuzzy inference system (ANFIS) to create predictive models for fc. The fc of the collected datasets ranged from 6.3 to 101.3 MPa. The study included the artificial rabbit optimization (ARO) and Bald Eagle search algorithm (BES) to improve the effectiveness of the ANFIS approaches. The novelty of this study is attributed to several factors, including the utilization of the ARO and BES methodologies, the incorporation of GGBFS in the evaluation of fc, the comparison with previous research findings, and the utilization of a substantial dataset encompassing multiple input variables. These factors offer a novel method for improving the effectiveness of prediction models and advance our understanding of forecasting the mechanical characteristics of concrete. The integrated ANF‐AR and ANF‐BA systems showed good estimating skills, according to the findings, which showed R2 values of 0.9961 and 0.9967 for the ANF‐AR's training and testing components and 0.9916 and 0.9946 for the ANF‐BA, respectively. Overall, the ANFIS optimized with ARO model is recognized as the outperformed system for prediction purposes. [ABSTRACT FROM AUTHOR]