Prediction of properties of self-compacting concrete containing fly ash using artificial neural network

This paper investigates the feasibility of using artificial neural networks (ANNs) modeling to predict the properties of self-compacting concrete (SCC) containing fly ash as cement replacement. For the purpose of constructing this model, a database of experimental data was gathered from the literature and used for training and testing the model. The data used in the artificial neural network model are arranged in a format of six input parameters that cover the total binder content, fly ash replacement percentage, water–binder ratio, fine aggregates, coarse aggregates and superplasticizer. Four outputs parameters are predicted based on the ANN technique as the slump flow, the L-box ratio, the V-funnel time and the compressive strength at 28 days of SCC. To demonstrate the utility of the proposed model and improve its performance, a comparison of the ANN-based prediction model with other researcher’s experimental results was carried out, and a good agreement was found. A sensitivity analysis was also conducted using the trained and tested ANN model to investigate the effect of fly ash on SCC properties. This study shows that artificial neural network has strong potential as a feasible tool for predicting accurately the properties of SCC containing fly ash.