Using Radial Basis Function Artificial Neural Network for Predicting Asphalt Content of Asphalt Paving Mixture

Abstract

The determination of the asphalt content of asphalt paving mixtures is afundamentally important test for many authorities and researchers inhighways field . This study seek to examined the application and use ofradial basis function artificial neural network with Gaussian activationfunction by MATLAB software for predicting the asphalt content of thehot mix asphalt paving mixtures using their properties of Marshall test.The architecture of the study developed network consist of five inputnodes representing five properties of Marshall test, with six hidden nods,while the output consist of one output node representing the asphaltcontent percent.The study results have show that the radial basis function network canbe applied as a recommended and appropriate computational tool toaccurately and quickly determine the asphalt content of asphalt mixturesas alternative to using traditional techniques.