Prediction of Indirect Tensile Strength of Intermediate Layer of Asphalt Pavements Using Artificial Neural Network Model

摘要

The repair method for pavements should be selected considering the structural capacity of sublayers, in addition to the conditionsobserved at the pavement surface, to reduce the recurrence of distress in the repaired area. However, it is practicallyimpossible to include the structural capacity of sublayers in the database of the pavement management system (PMS) becausethis would require additional tests in all expressway sections. Therefore, an artificial neural network model for predicting theindirect tensile strength (ITS) of the intermediate layer of all asphalt pavement sections in an expressway was developed inthis study, taking the international roughness index, rut depth, surface distress, and equivalent single axle load as independentvariables. The ITS of specimens cored from target sections was measured in the laboratory, and the PMS data for the targetsections were collected. The ITS was predicted by conducting a feedforward process prior to the training step. When theerror between the predicted and measured ITSs exceeded the allowable error, the model was repetitively trained using theresilient backpropagation method until the error fell within the acceptable boundary. The model was validated by analyzingthe correlations between the ITSs predicted from the data of the training and test sets. Finally, the model was complementedby the corresponding minimum and maximum values of the ITS measured at the target section.