Neural networks based concrete airfield pavement layer moduli backcalculation

摘要

The Heavy Weight Deflectometer (HWD) is a Non-Destructive Test (NDT) equipment used to assess the structural condition of airfield pavement systems. This paper presents an Artificial Neural Networks (ANN) based approach for non-destructively estimating the stiffness properties of rigid airfield pavements subjected to full-scale dynamic traffic testing using simulated new generation aircraft gears. HWD tests were routinely conducted on three Portland Cement Concrete (PCC) test items at the Federal Aviation Administration's (FAA) National Airport Pavement Test Facility (NAPTF) to verify the uniformity of the test pavement structures and to measure pavement responses during full-scale traffic testing. Substantial corner cracking occurred in all three of the rigid pavement test items after 28 passes of traffic had been completed. Trafficking continued until the rigid items were deemed failed. The study findings illustrate the potential of ANN-based models for routine and real-time structural evaluation of rigid pavement NDT data.