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

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