Predicting the Compressive Strength of Fly Ash Composite Foam Concrete Using Artificial Neural Networks and Soft Computing Techniques

This study develops soft-computing models to predict the compressive strength of Fly Ash Composite Foam Concrete (FFC), a lightweight, sustainable cementitious material. A database of 302 experimental records was compiled from previous studies, including wet density, cement content, fly ash content, sand content, water–binder ratio, foam content, and curing age. Five predictive models were evaluated, with the Artificial Neural Network (ANN) achieving the best performance, yielding an accuracy of 98% and the lowest prediction error. Sensitivity analysis identified wet density, cement content, and foam content as the most influential variables. The results demonstrate that soft computing approaches can significantly reduce experimental effort, lower costs, and support the sustainable design of FFC mix ratios for diverse applications.