A Probabilistic Method for Estimating Pavement Performance Using Falling Weight Deflectometer Data

Most mechanistic-empirical methods for determining the integrity of an existing pavement rely on the use of deflection-based nondestructive evaluation devices and a number of models to estimate the remaining life associated with a flexible pavement. We have developed a software tool that integrates artificial neural network (ANN) technology, the functional condition of pavement, uncertainty analysis and traffic information to predict a probabilistic pavement performance curve. The ANN models predict the critical strains at the layer interfaces, using readily available data such as the best estimates of each layer thickness and surface deflections from a Falling Weight Deflectometer test. As such, the backcalculation process is eliminated. Based on the validation results from an accelerated pavement testing facility and a test track, the system seems to be robust and appears to provide reasonable results. For the covering abstract see ITRD E118503.