Pavement deterioration models are crucial components of a Pavement Management System (PMS). As a matter of fact most empirical deterioration progression models developed to date have had limited success, especially outside the location they were developed.
This paper deals with the development of flexible pavement roughness progression models, expressed in terms of International Roughness Index, from PMS data of the Ethiopian road network, using Multi-Linear Regression (MLR) and Artificial Neural Network (ANN) techniques.
The possible use of Light Weight Deflectometer surface deflection modulus variable in the models instead of the uncertain pavement base course thickness is investigated and verified.
A comparative study was also made between the MLR and ANN models, and the results from this research effort demonstrated that the ANN models outperform the MLR models.
© 2001-2024 Fundación Dialnet · Todos los derechos reservados