Gholamali Shafabakhsh - Ph.D., Associate Professor, Faculty of Civil Engineering, Semnan University, Semnan, Iran
Amin Tanakizadeh - Ph.D. Student, Faculty of Civil Engineering, Semnan University, Semnan, Iran

One of the key parameters to design flexible pavements is the stiffness modulus of asphalt mixtures. This study aimed to develop models for prediction stiffness modulus of asphalt concrete using genetic programming. Due to the viscoelastic nature of asphalt mixes, the stiffness of these materials depends on temperature, loading time duration, rest period, and loading waveform. Therefore, in this paper, the authors use these parameters as independent variables to estimate stiffness of asphalt mixes under two loading waveforms (haversine and square). Stiffness modulus of asphalt mixture samples were determined using resilient modulus indirect tensile test (IDT) under haversine and square waveforms at different temperatures and loading conditions. First, two models were developed using genetic programming (GP) technique with MATLAB® genetic programming toolbox for two loading waveforms. Then, response surface models were developed using STATISTICA® software, and the developed models were evaluated. The predicted stiffness modulus was closely relevant to the measured one and prediction ability of the models was satisfactory that can be prevented from expensive and time-consuming laboratory tests

Asphalt concrete; Stiffness modulus; Genetic programming; Response surface model