Towards Real-time Structural Evaluation of In-Service Airfield Pavement Systems Using Neural Networks Approach
The primary objective of this study was to assess the pavement structural deterioration based on Non-Destructive Test (NDT) data using an Artificial Neural Networks (ANN) based approach. ANN-based prediction models were developed for rapid determination of flexible airfield pavement layer stiffnesses from actual NDT deflection data collected in the field in real time. For training the ANN models, ILLI-PAVE, an advanced finite-element pavement structural model which can account for non-linearity in the unbound pavement granular layers and subgrade layers, was employed. Using the ANN-predicted moduli based on the NDT test results, the relative severity effects of simulated Boeing 777 (B777) and Boeing 747 (B747) aircraft gear trafficking on the structural deterioration of National Airport Pavement Test Facility (NAPTF) flexible pavement test sections were characterized.
This is a manuscript of an article from ANNIE 2006, ANN in Engineering Conference, St. Louis, Missouri, November 5-8, 2006