The era of intensive construction of new roads is behind us, and now road agencies are focused on maintaining and preserving existing pavement surfaces. As they are faced with limited funds for maintenance, it is important to best utilize resources by selecting the best maintenance strategy. Selection of an appropriate maintenance strategy is a complex task which includes factors such as current condition of the pavement, road classification, traffic volume and type of pavement distress. These factors can be automated and implemented in pavement management systems to achieve a standardised approach to road pavement assessment and management. One of the key components of pavement management systems are pavement performance prediction models, which simulate the pavement deterioration process and forecast its condition over time. One such model is the artificial neural network. This paper analyzes the possibility of using artificial neural networks in pavement management systems to evaluate existing pavement condition, and its possible application for defining the maintenance strategy of state roads. A backpropagation algorithm was applied on 481.3 km of state roads in Osijek-Baranja County, which represents 7% of total length of the national road network in Croatia. The obtained results indicated that artificial neural networks can be used for optimization of maintenance or rehabilitation strategies, and for assessment
of pavement condition at the project and network level.

artificial neural network, pavement management system, backpropagation algorithm, pavement maintenance