Compressive Strength Prediction of Self-Compacting Concrete-A Bat Optimization Algorithm Based ANNs

Abstract

This article examines the feasibility of using bat-trained artificial neural networks (ANNs) to predict the compressive strength of self-compacting concrete (SCC). The nonlinear behavior of SCC challenges traditional modeling techniques. Therefore, this work takes advantage of the superior predictive performance of ANNs coupled with the bat algorithm. A database of 205 SCC samples collected from the literature is used to develop the ANN model. The correctness of the bat-based neural network model is then substantiated by contrasting its performance with that of the particle swarm optimization and teaching-learning-based optimization algorithms employed to train a neural network model. The statistical indices indicate the superior performance of the bat-based ANN model. In addition, a sensitivity analysis was carried out to determine the effects of various input parameters on the compressive strength of SCC.