ABSTRACT
Prediction of pavement performance is a key process in the efficient management of pavement assets for a highway agency. There are a lot of tools that can be used to develop pavement performance prediction models, but the newest generation of tools belongs to the field of Artificial Intelligence. Flexible pavement rutting prediction models are developed using MLR and ANN techniques, using data from the Norwegian national road databank (NVDB) for the coastal roads of southern Norway. The intention is to use them for planning maintenance activities; as a part of a Pavement Management System (PMS). Comparative study of the results is also conducted. It was found that the prediction capabilities of the ANN and MLR models developed by this study are almost equal, explaining the variation in rut depth by about 90% accuracy.
