Prediction of compressive strength of ultra-high performance concrete (UHPC) containing supplementary cementitious materials

To evaluate the possibility of predicting the compressive strength of UHPC incorporating supplementary cementitious materials, such as fly ash and silica fume, an artificial neural networks (ANN) was constructed using 78 groups of experimental details from 11 published researcher's work. The model that composed of an input level, one output level, and a hidden level was developed through the MATLAB platform. The input level applied 11 input variables which contain: the mass of sand, cement, water, coarse aggregate, fly ash, silica fume, superplasticizer, water to cement-equivalent ratio, aggregate to cement-equivalent ratio, fine aggregate ratio, the difference between the minimum and maximum value of aggregate. The results indicate that the developed ANN model has a high accuracy for the prediction of the compressive strength of UHPC containing binary supplementary materials. The comparison between the predicted results and experimental data is given by evaluating the root mean square error (RMSE), mean absolute percentage error (MAPE) and absolute fraction of variance (R-2).