Predicting the Compressive Strength of Concrete Using an RBF-ANN Model

In this study, a radial basis function (RBF) artificial neural network (ANN) model for predicting the 28-day compressive strength of concrete is established. The database used in study expansion by adding data from other works to one author’s previous work. stochastic gradient approach presented textbook employed determining centers RBFs and their shape parameters. With an extremely large number training iterations just few ANN, all RBF-ANNs have converged solutions global minimum error. So, only consideration whether ANN can work practical uses issue over-fitting. with three finally chosen. results verification imply that present RBF-ANN outperforms BP-ANN RBFs, parameters, weights, threshold are listed article. these numbers using formulae expressed article, anyone predict according mix proportioning on his/her own.