This study aims to investigate the effect of warm mix asphalt (WMA) additives on fatigue life of unmodified and SBS- modified asphalt mixes. Two different WMA additives, including Aspha-min and Sasobit were used to fabricate WMA specimens. Fatigue test was performed on warm polymer modified asphalt (PMA) by indirect tensile test on two stress levels (300,450kPa) at 20°C and fatigue life was compared with PMA mixture. Also, indirect tensile strength (ITS) test was performed to determine the moisture susceptibility of warm PMA. In order to evaluate the fatigue performance of warm mix asphalt (WMA) mixtures in comparison with hot mixture asphalt (HMA), four-point flexural beam test was employed. Four- point flexural beam test was conducted at four strain levels (650, 800, 1000 and 1200μɛ) and frequency of 7.5Hz at 20°C. According to the test results, it was shown that warm PMA mixtures prepared by Aspha-min and Sasobit, have less fatigue resistance in comparison with PMA mixture. Also the fatigue resistance of warm PMA mixture made by Sasobit is greater than fatigue resistance of warm PMA mixture made by Aspha-min. Based on the ITS test results, warm PMA with Sasobit additive and PMA achieved the desirable tensile strength ratio (TSR) criterion (80%) but warm PMA Aspha-min had TSR lower than 80%. Also fatigue life determination based on 50% reduction in initial stiffness showed that the fatigue life of HMA mixture is less than WMA mixtures at lower strain levels whereas it was comparable with warm mix asphalt at higher strain levels

The collapse settlement of granular soil, which brings about considerable deformations, is an important issue in geotechnical engineering. Several factors are involved in this phenomenon, which makes it difficult to predict. The present study aimed to develop a model to predict the collapse settlement and coefficient of stress release of sandy gravel soil through evolutionary polynomial regression (EPR). To achieve this, a dataset containing 180 records obtained from a large-scale direct shear test was used. In this study, five models were developed with the secant hyperbolic, tangent hyperbolic, natural logarithm, exponential, and sinusoidal inner functions. Using sand content (SC), normal stress (${\sigma }_n$), shear stress level (SL), and relative density (Dr) values, the models can predict the collapse settlement (∆H) and coefficient of stress release (CSR). The results indicated that the models developed with the exponential functions were the best models. With these models, the values of $R^2$ for training, testing, and all data in the prediction of collapse settlement were 0.9759, 0.9759, and 0.9757, respectively, and the values of $R^2$ in predicting the coefficient of stress release were 0.9833, 0.9820, and 0.9833, respectively. The sensitivity analysis also revealed that the sand content (SC) and relative density (Dr) parameters had the highest and lowest degrees of importance in predicting collapse settlement. In contrast, the Dr and SC parameters showed the highest and lowest degrees of importance in predicting the coefficient of stress release. Finally, the conducted parametric study showed that the developed models were in line with the results of previous studies.