Application of Artificial Neural Network to Predict the Properties of Permeable Concrete

The structure of permeable concrete has been the primary reason for its use in construction. Permeable is composed water, cement, aggregate, and little- to no-fines resulting presence a significant number voids. This makes an ideal solution water accumulation issues as it acts drainage system. study employs feedforward backpropagation artificial neural network model that combines experimental laboratory data from previous studies with appropriate architectures training techniques. purpose analysis develop reliable functional relationship, based on water-cement ratio, aggregate-cement density parameters, which estimate compressive strength, porosity, permeability concrete. Multiple linear regression correlations are also established predict correlate these inputs outputs. two derived methods then compared discussed. results reveal ANN better anticipate properties than analysis.