01024478

Component

Recent research studies have successfully demonstrated the use of Artificial Neural Network (ANN) models for predicting critical structural responses and layer moduli of pavement geomaterials for highway flexible pavements. The primary objective of this paper was to develop an effective tool for real-time backcalculation of pavement layer non-linear moduli based on Heavy Weight Deflectometer (HWD) test data especially in the analysis of airport flexible pavements subjected to New Generation Aircraft (NGA). Four flexible test sections at the National Airport Pavement Test Facility (NAPTF) were modeled using the ILLI-PAVE finite element program which can take into the account the non-linearity of pavement geomaterials. A multi-layer, feed-forward network which uses an error-backpropagation algorithm was trained to approximate the HWD backcalculation function using the ILLI-PAVE generated synthetic database. At the NAPTF, test sections were simultaneously subjected to Boeing 777 trafficking in one lane and Boeing 747 trafficking on the other lane using a test machine. To monitor the effect of time and traffic on pavement structural responses, HWD tests were conducted on the trafficked lanes and on the untrafficked centerline of test sections as trafficking progressed. The trained ANN models were successfully used to predict the asphalt concrete moduli and non-linear subgrade moduli using the HWD test data. The results were used to compare the relative effect of B777 and B747 trafficking on the elastic moduli and characterize the seasonal variation in moduli values. Further research is required to develop robust ANN models for predicting the unbound granular layer moduli.

01020180

06-2705

English

17p

2006

Transportation Research Board 85th Annual Meeting

CD-ROM

Figures; References; Tables

Airport runways; Asphalt concrete pavements; Backcalculation; Flexible pavements; Neural networks; Research projects

Boeing 747 aircraft; Boeing 777 aircraft; National Airport Pavement Test Facility

Geomaterials; Layer moduli; Multilayer feed-forward neural networks

Aviation; Data and Information Technology; Pavements; Research; Terminals and Facilities

Transportation Research Board Annual Meeting 2006 Paper #06-2705

TRIS, TRB

Mar 3 2006 11:06AM