Providing Laboratory Rutting Models for Modified Asphalt Mixes with Different Waste Materials

Authors

  • Ali Reza Azarhoosh
    Affiliation

    Amirkabir University of Technology, Tehran, Iran.

  • Gholam Hossein Hamedi
    Affiliation

    University of Guilan, P.O.Box 3756, Rasht, Iran.

  • Hossein Fallahi Abandansari
https://doi.org/10.3311/PPci.10684

Abstract

Due to the complex behavior of asphalt pavement materials under various loading conditions, pavement structure, and environmental conditions, accurately predicting the permanent deformation of asphalt pavement is difficult. This study discusses the application of artificial neural network (ANN) and the multiple linear regression (MLR) in predicting permanent deformation of asphalt concrete mixtures modified by waste materials (waste plastic bottles and waste high-density polyethylene). The use of waste materials in the pavement industry can prevent the accumulation of waste material and environmental pollution and can reduce primary production costs. The results of a laboratory study evaluating the rutting properties of Hot-Mix Asphalt (HMA) mixtures using dynamic creep tests were investigated. The results indicate ANN techniques are more effective in predicting the rutting of the modified mixtures tested in this study than the traditional statistical-based prediction models. On the other hand, results show that an increase in percentage of waste materials is very effective in reducing the final strain of asphalt mixtures. However, an increase in percentage of additives over 7% does not help to reduce permanent deformation under dynamic loading in the asphalt mixtures.

Keywords:

Rutting, waste plastic bottles, waste high-density polyethylene, artificial neural networks, multiple linear regressions

Published Online

2017-10-17

How to Cite

Azarhoosh, A. R., Hamedi, G. H., Abandansari, H. F. “Providing Laboratory Rutting Models for Modified Asphalt Mixes with Different Waste Materials”, Periodica Polytechnica Civil Engineering, 62(2), pp. 308–317, 2018. https://doi.org/10.3311/PPci.10684

Issue

Section

Research Article