Optimization of resilient modulus prediction from FWD results using artificial neural network

Abstract

One of the most important steps in the design of new pavements and overlays is the selection of an accurate input value for the subgrade resilient modulus (M_r). This paper evaluates the use of regression analysis and artificial neural networks (ANN) to develop models that can be used to accurately predict the subgrade M_r design input value using Falling Weight Deflectometer (FWD) test results. The results of the regression analyses conducted in this paper indicated that the use of linear elastic analysis for backcalculation of the FWD modulus yielded better prediction of laboratory measured resilient modulus compared to using the AASHTO or Florida Equations. In addition, the accuracy of M_r prediction was significantly enhanced when ANN based models were used. For models that were based on FWD modulus backcalculated using different Softwares, the ANN improvement was only noticed when the model included soil physical properties. Finally, the results of this paper indicated that when using the FWD modulus backcalculated using the AASHTO or Florida equation to predict M_r design input value, it’s recommended to use the ANN model with variables selected using stepwise selection analysis.