Artificial neural network approach for overlay design of flexible pavements

Pavements are constructed to deteriorate because of many factors such as traffic loading, material related factors, climate, and other environmental factors. In order to preserve these investments, a maintenance program should be carried out at right time and right places. One of the most important maintenance activities is asphalt overlays. Designing an overlay is more challenging since it restricts the pavement design engineer to a vast number of boundary conditions that must be observed and designed for. The most important factor in this process is the assessment of the existing pavement structural capacity, and relating it to the new overlay. The process becomes more complicated when considering environmental changes of the pavement materials. Such process should be implemented using a computer model to overcome complexity procedures, repeated tasks and time consuming. An artificial neural network approach can be used for the elimination of this drawback. This study presents an attempt to apply artificial neural network to recommend pavement overlay thickness based on learning from Mechanistic-Empirical overlay design cases. Results of this study reveal that artificial neural network is appropriate for implementation in calculating flexible overlay thickness based on mechanistic-based design procedure.