Neural Network Model for Asphalt Concrete Permeability

In this study, a four-layer feed-forward neural network is constructed and applied to determine a mapping associating mix design and testing factors of asphalt concrete samples with their performance in conductance to flow or permeability. To generate data for the neural network model, a total of 100 field cores from 50 different mixes (two replicate cores per mix) are tested in the laboratory for permeability and mix volumetric properties. The significant factors that affect asphalt permeability are identified using simple and multiple regression analysis. The analyses results show that permeability of an asphalt concrete is affected mainly by five factors: (1) air void $\left(V_a\right)$ ; (2) the grain size through which 10% materials pass $\left(d_{10}\right)$ ; (3) the grain size through which 30% materials pass $\left(d_{30}\right)$ ; (4) saturation, or the CoreLok Infiltration Coefficient (CIC); and (5) effective asphalt to dust ratio $(P_{be}∕P_{0.075})$ . The significant factors are then used to define the domain of a neural network. Regardless of the significant factors included in defining the domain of such a mapping, a principle component analysis is performed to ascertain the most significant of these factors. The network is trained using the Levenberg-Marquardt algorithm. Using randomly generated synaptic weights to initialize the training algorithm, histograms are compiled and outputs are estimated. Excellent agreement is observed between simulation and laboratory data. It is believed that the developed NN model will be a useful tool in the study of asphalt pavement construction and maintenance.