Backcalculation of flexible pavement moduli using artificial neural networks
Abstract
Artificial neural networks provide a fundamentally new approach to backcalculation of pavement layer moduli from falling-weight deflectometer deflection basins. In the context of backcalculation, a neural can be trained to approximate the inverse function by repeatedly showing it forward solutions. The single most important advantage of using neural networks for backcalculation is speed. Two backpropagation neural network were trained to backcalculate pavement moduli for three-layer flexible pavement profiles. One network was trained using ideal deflection basins. Subsequent testing showed that the network could backcalculate pavement layer moduli accurately. A second network was trained using basin, with random noise added to simulate measurement errors. When tested using similarly noisy deflection basin, that network did a reasonably good job of predicting moduli. That same network performed very well on experimental data from two pavement test sections of Strategic Highway Research Program.
Publication Title
Transportation Research Record
Recommended Citation
Meier, R., & Rix, G. (1994). Backcalculation of flexible pavement moduli using artificial neural networks. Transportation Research Record (1448), 75-82. Retrieved from https://digitalcommons.memphis.edu/facpubs/13016