Utilizing Hybrid Machine Learning To Estimate The Compressive Strength Of High-Performance Concrete

This article examines the correlation between compressive strength (CS) and High-performance concrete (HPC) and its practical use in construction engineering. HPC is widely recognized for its remarkable attributes of strength and durability, which render it a high option for deployment in high -stress infrastructural systems like bridges and tunnels. The CS of concrete is a fundamental attribute critical in determining its capacity to maintain structural integrity and endurance over time. This paper investigates the efficacy of the Adaptive Neuro-Fuzzy Inference System (ANFIS) model in forecasting the CS of HPC. The presented model coupled with three meta -heuristic algorithms, namely Chef -based optimization algorithm (COA), Henry Gas Solubility Optimization (HSO), and Artificial Ecosystem -Based Optimization (AEO), to improve the performance and accuracy of ANFIS. In addition, the prediction was applied by 344 datasets from published papers in two phases containing training (70%) and testing (30%). As a result, ANEB (ANFIS coupled with AEO) obtained suitable results with high R2 and less RMSE value compared to other models. This precision in forecasting permits engineers to design concrete structures that are not only more efficient but also cost-effective. The integration of ANFIS in the prediction of the CS of HPC has the potential to facilitate the development of more resilient and durable infrastructures, consequently yielding consequential advantages for the construction sector.