Artificial neural network based modelling of the Marshall Stability of asphalt concrete

  • Authors:
  • Ercan Ozgan

  • Affiliations:
  • Duzce University, Technical Education Faculty, Structural Department, Konuralp Yerleskesi, Duzce, Turkey

  • Venue:
  • Expert Systems with Applications: An International Journal
  • Year:
  • 2011

Quantified Score

Hi-index 12.05

Visualization

Abstract

In this study, the Marshall Stability (MS) of asphalt concrete under varying temperature and exposure times was modeled by using artificial neural network. In order to investigate the MS based on physical properties, exposure time and environment temperature, exposure times of 1.5, 3, 4.5 and 6h and temperatures of 30^oC, 40^oC and 50^oC were selected. The results showed that at the environment temperature of 17^oC the stability of the asphalt core samples decreased by 40.16% at 30^oC after 1.5h and 62.39% after 6h. At 40^oC, the decrease was 74.31% after 1.5 and 78.10% after 6h. At 50^oC the stability of the asphalt decreased by 83.22% after 1.5h, and 88.66% after 6h. Experiment results and ANN model exhibited good correlation for this reason the ANN method could be used to model the MS.