Evaluation of Different Conditions Affecting the Indirect Tensile Strength of Hydrated Lime Additive Bituminous Mixtures by Using Artificial Neural Networks Method


Dündar S., Yardım M. S. , Değer Şitilbay B.

ACE2018 - 13th International Congress On Advances In Civil Engineering, İzmir, Turkey, 12 - 14 September 2018

  • Publication Type: Conference Paper / Full Text
  • City: İzmir
  • Country: Turkey

Abstract

In this study, the effect of Hydrated Lime (HL), an additive to hot mix asphalt used in pavements, was experimentally investigated. The filler material was removed from the mixture and instead, HL was added to it with different ratios. The low temperature cracking resistance of the pavement was obtained at various temperatures. To this aim, asphalt briquettes, designed according to the Marshall method were produced with consideration of the optimum asphalt contents for samples with specified HL contents. In addition to the temperature effect, samples were produced in two different groups, namely conditioned and unconditioned in order to examine the effect of water. Indirect tensile strength test was applied on the produced samples. In this study Indirect Tensile Strength (ITS) was applied on samples with various HL and optimum asphalt contents. Then an Artificial Neural Network (ANN) model was developed using the ITS results. The experimental data was evaluated using the ANN in order to determine the optimum conditions in terms of ITS. It has been found that the HL has a significant contribution to the prevention of cracking in asphalt pavements formed due to long term exposure to cold weather conditions and high humidity. More specifically, it can also strengthen the material and increase resistance to cold and humidity. In addition to comparing the developed model and the experimental data, the results obtained provide significant contributions in evaluating the relationship between varying HL contents and the ITS values obtained by the specified conditioning and temperature changes.

Keywords: Hot mix asphalt, hydrated lime, indirect tensile strength, artificial neural networks