The pavement management system (PMS) consists of several components including data collection, analysis, and reporting procedures. This system helps make decisions about the prioritization of road sections and selecting optimal maintenance strategy for the related road pavement networks. Considering the deteriorating rate of pavement sections and the limited budget and resources, it is important to find the most optimal maintenance and rehabilitation (M&R) scenarios for each pavement section. This study presents a model based on the cloud decision tree (CDT) theory for selecting the most optimal M&R strategies. A CDT system is presented for Iran’s national road network. The system includes a general decision-making model and various decision trees for every province of the country. Exclusive decision-making models were presented for freeways, highways, and main roads. Furthermore, different decision tree models are presented based on roads Annual Average Daily Traffic (AADT). Using the presented theory resulted in a general model with an accuracy of 80%. Evaluation of acquired decision trees showed that fatigue cracking and International Roughness Index (IRI) are the mo st important parameters to determine the appropriate M&R scenarios. Using these parameters provided results close to the re suits of experts’ surveys under real conditions, regardless of rank and traffic volume of the road sections.
Read full abstract