BAT Algorithm-Based ANN to Predict the Compressive Strength of Concrete—A Comparative Study

The number of effective factors and their nonlinear behaviour—mainly the effect on concrete properties—has led researchers to employ complex models such as artificial neural networks (ANNs). compressive strength is certainly a prominent characteristic for design analysis structures. In this paper, 1030 samples from literature are considered model accurately efficiently strength. To aim, Feed-Forward (FF) network employed based eight different factors. More in detail, parameters ANN learned using bat algorithm (BAT). resulting optimized thus validated by comparative analyses towards ANNs with genetic (GA) Teaching-Learning-Based-Optimization (TLBO), well multi-linear regression model, four proposed literature. results indicate that BAT-optimized more accurate estimating concrete.