Prediction of Pervious Concrete Permeability and Compressive Strength Using Artificial Neural Networks

Pervious concrete is a concrete mixture prepared from cement, aggregates, water, little or no fines, and in some cases admixtures. The hydrological property of pervious concrete is the primary reason for its reappearance in construction. Much research has been conducted on plain concrete, but little attention has been paid to porous concrete, particularly to the analytical prediction modeling of its permeability. In this paper, two important aspects of pervious concrete due to permeability and compressive strength are investigated using artificial neural networks (ANN) based on laboratory data. The proposed network is intended to represent a reliable functional relationship between the input independent variables accounting for the variability of permeability and compressive strength of a porous concrete. Results of the Back Propagation model indicate that the general fit and replication of the data regarding the data points are quite fine. The R-square goodness of fit of predicted versus observed values range between 0.879 and 0.918 for the final model; higher values were observed for the permeability as compared with compressive strength and for the train data set rather than the test data set. The findings can be employed to predict these two important characteristics of pervious concrete when there are no laboratorial data available.