Backcalculation of Pavement Layer Thickness and Moduli by the Wavelet-Neuro Approach

Abstract

Backcalculating the pavement layer properties is a well-accepted procedure for the evaluation of the structural capacity of pavements. The ultimate aim of the backcalculation process from nondestructive testing (NDT) results is to estimate the in-situ pavement material properties. Using backcalculation procedure, flexible pavement layer thicknesses together with in-situ material properties can be estimated from the measured field data through appropriate analysis techniques. In this study, the wavelet-neuro (WN) models were developed for backcalculating the pavement layer thickness and elastic moduli from deflections measured on the surface of the flexible pavements. Experimental deflection data groups from NDT were used to show the capability of the WN approaches in backcalculating the pavement layer thickness and moduli and compared NN models. When the WN and NN models are examined, it has been shown that the WN model gave higher R2 values than the NN models.