Title

Backcalculation of Dynamic Modulus from Resilient Modulus of Asphalt Concrete with an Artificial Neural Network

Document Type

Journal Article

Publication Date

2008

Subject Area

ridership - elasticity, ridership - commuting

Keywords

Neural networks, Modulus of resilience, Hot mix paving mixtures, Hot mix asphalt mixtures, Dynamic modulus of elasticity, Dynamic modulus, Bituminous concrete, Backcalculation, Asphaltic concrete, Asphalt concrete, Artificial neural networks, ANNs (Artificial neural networks)

Abstract

The NCHRP Project 1-37A "Guide for Mechanistic–Empirical Design of New and Rehabilitated Pavement Structures" introduces the dynamic modulus (|E*|) as the material property for the characterization of hot-mix asphalt mixtures. This is a significant change from the resilient modulus used in the previous AASHTO "Guide for the Design of Pavement Structures." One of the challenges of changing the material characterization is that databases, such as the Long-Term Pavement Performance Materials Database, contain older material characterization information. Thus, such databases must convert their data to the currently accepted standard (i.e., |E*|). Other investigators have presented evidence that the resilient modulus can be predicted from the dynamic modulus by using the theory of viscoelasticity. By using their prediction method, this study proposes the population of a database of measured dynamic moduli with the corresponding predicted resilient moduli to train an artificial neural network (ANN). The ANN model was verified with four 12.5-mm surface course mixtures with different aggregate types and binder types and one 25.0-mm base mixture. The dynamic moduli predicted from the measured resilient moduli with the trained ANN were found to be reasonable compared with the measured dynamic moduli.