A probabilistic approach for modelling deterioration of asphalt surfaces

This paper details findings from the New Zealand Transport Agency's research project by Henning and Roux (2008). It forms part of the overall New Zealand Long-term Pavement Performance (LTPP) programme. The paper documents the development of prediction models for dense-graded asphalt (AC) surfaces and open-graded porous asphalt (OGPA) surfaces. Two models were developed including crack initiation on AC surfaces and ravelling initiation on OGPA surfaces. Continuous probabilistic models were utilised for both crack and ravelling initiation in order to predict the probability of the defect occurring. Models developed during this research use data which is readily available on network level databases, and can therefore be applied to asset management applications such as the New Zealand (NZ) dTIMS system (NZ's nationally adopted pavement management system (PMS)). Although a crack initiation model was also developed, it was not as robust as the ravelling model. Further work required includes refining of the models based on the LTPP data which includes bitumen property data. Although the developments are solely based on NZ data, there are a number of aspects applicable to the South African context. Firstly it presents a novel way of modelling the performance of asphaltic surfaces. Secondly it demonstrates some practical implications of maintenance practices that are sometimes considered for South African conditions.