Department Details
Branch: Engineerings
Department: Civil Engineering Department
Location: Adminstrative Building

Publication Details
Staff Member Name1- Prof. dr. Ahmed Mahmoud Azmy
Publication Name Application of Neural Networks in the Prediction of Compressive Strength of High Strength Concrete
Publication DescriptionIn the present study, the artificial neural networks (ANNs) were used for predicting the compressive strength of High Strength Concrete (HSC) mixtures. Experimental testing was carried out at the laboratories of the Department of Civil Engineering of Higher Technological Institute, 10th of Ramadan City where the compressive strength of 108 mix design was obtained. Among the two ANN models (a feed-forward back propagation (BP) and a radial basis function (RBF)) employed for this investigation, the BP neural network was found to be superior to RBF network for prediction of the compressive strength of HSC mixtures. A BPNN model having a structure 5-7-3-1 (five neurons in input and seven neurons in first hidden layer, three neurons in second hidden layer and one neuron in output layer) produced better prediction with an accuracy of 95.156%. The BPNN (5-7-3-1) model was fairly close to the corresponding actual values of compressive strength with the maximum error of 4.421%, a minimum error of 0.092% and the average error of 1.96% were obtained. The results indicate that the developed model is an efficient tool for prediction of the compressive strength of HSC from both economic and time-saving points of view.