Effective prediction of rutting diseases in seasonal frozen area is helpful for comprehensive evaluation of asphalt pavement performance. In this paper, based on the Mechanical-Experienced Pavement Design Guide (MEPDG) theory, the rutting prediction model of asphalt pavement in the seasonal frozen area is established by using the measured rutting data of 9 typical highways in the seasonal frozen area of China. The research results show that the traffic volume, climate, and asphalt layer thickness of the pavement structure are directly proportional to the change in rutting. The proposed correction coefficients for the prediction model of asphalt pavement rutting in the seasonal frozen area are β1r = 2, β2r = 1.03 and β3r = 0.93. The normal distribution map and P-P map of the rutting prediction model conform to the normal distribution. The fit between the predicted data of the prediction model and the measured data is high. The fitting value between the predicted data and the measured data before correction is R2 = 0.9357. The fitting value between the revised predicted data and the measured data is R2 = 0.9925. The research results are of great significance for the prediction of rutting and maintenance of asphalt pavement in the seasonal frozen area.

Effective prediction of rutting diseases in seasonal frozen area is helpful for comprehensive evaluation of asphalt pavement performance. In this paper, based on the Mechanical-Experienced Pavement Design Guide (MEPDG) theory, the rutting prediction model of asphalt pavement in the seasonal frozen area is established by using the measured rutting data of 9 typical highways in the seasonal frozen area of China. The research results show that the traffic volume, climate, and asphalt layer thickness of the pavement structure are directly proportional to the change in rutting. The proposed correction coefficients for the prediction model of asphalt pavement rutting in the seasonal frozen area are β1r = 2, β2r = 1.03 and β3r = 0.93. The normal distribution map and P-P map of the rutting prediction model conform to the normal distribution. The fit between the predicted data of the prediction model and the measured data is high. The fitting value between the predicted data and the measured data before correction is R2 = 0.9357. The fitting value between the revised predicted data and the measured data is R2 = 0.9925. The research results are of great significance for the prediction of rutting and maintenance of asphalt pavement in the seasonal frozen area.