This study aimed to improve the accuracy of road pavement design by comparing and analyzing various statistical and machine-learning techniques for predicting asphalt layer thickness, focusing on regional roads in Pakistan. The explanatory variables selected for this study included the annual average daily traffic (AADT), subbase thickness, and subgrade California bearing ratio (CBR) values from six cities in Pakistan. The statistical prediction models used were multiple linear regression (MLR), support vector regression (SVR), random forest, and XGBoost. The performance of each model was evaluated using the mean absolute percentage error (MAPE) and root-mean-square error (RMSE). The analysis results indicated that the AADT was the most influential variable affecting the asphalt layer thickness. Among the models, the MLR demonstrated the best predictive performance. While XGBoost had a relatively strong performance among the machine-learning techniques, the traditional statistical model, MLR, still outperformed it in certain regions. This study emphasized the need for customized pavement designs that reflect the traffic and environmental conditions specific to regional roads in Pakistan. This finding suggests that future research should incorporate additional variables and data for a more in-depth analysis.

In Korea, concrete pavements were first applied to highways in 1981 and as a result of continued increase in length over the past years, 2,592 km of concrete pavement network is currently in service, of which 1,399 km(54%) of concrete pavements is 10 years or older, and 233km(9%) is 20 years or older. The length of concrete pavement sections nationwide has been steadily on the rise every year (EXTRI, 2017). Approximately 54% of current concrete pavement highway network will reach the service life limit in 2025 which means around 660 billion won is needed for future pavement repair project (EXTRI, 2017). Given that concrete pavements beyond design life still have a remaining service life, it is economically advantageous to repair them before reconstruction. Asphalt overlays are a major repair method for older concrete pavements. Depending on the concrete pavement condition, thickness and mixture of asphalt overlays are determined. Service life of asphalt overlays varies by the presence, time and size of cracks in existing concrete pavements and reflecting crack at joints. Temperature change of concrete pavement is among the major reaction parameters of reflecting crack. Reflecting crack develops when asphalt bottom-up cracking by longitudinal shrinkage and expansion due to temperature change of the concrete base layer, top-down cracking by temperature difference between top and bottom of concrete, and shear stress by traffic loading are combined (Baek, 2010). Crack and joint behaviors of concrete pavement vary between the base layer and the concrete surface of composite pavement system, and different conductivity by mixture and thickness of asphalt overlay leads to temperature change of concrete base course. This study measured temperatures of each layer of diverse composite pavements in place on site and analyzed differences in temperature change of concrete base layer depending on mixture and thickness of asphalt overlays. Overlay thickness parameters were 5cm and 10cm, two values most widely used, while mixture parameters were SMA and porous asphalt. Based on temperature change of concrete surface, this study also evaluated the difference of temperature change in concrete base layer with an asphalt overlay on top. Findings from this study are expected to be utilized for studies on mechanism and modeling of reflecting crack in old concrete pavements with asphalt overlays.

본 연구는 장수명 아스팔트 포장 공법개발 연구의 일환으로 포장수명을 40년이상 지속시킬 수 있는 단면설계를 수행하였다. 본 연구의 목적은 포장체의 장수명화를 위하여 효과적이고 간편하게 포장체의 각층 단면두께 및 탄성계수를 결정하는 절차를 제시함에 있다. 포장체의 유한요소 해석을 통하여 장수명 아스팔트포장의 가상데이터베이스를 구축하였다. 이 가상데이터베이스는 포장체 각 층의 두께, 탄성계수 및 포장체 내의 처짐, 응력 및 변형률을 포함하고있다. 구축된 데이터베이스를 이용하여 포장의 장수명에 필요한 한계변형률을 만족하는 포장의 단면을 제시하였다. 연구결과, 총 아스팔트층의 두께가 410mm보다 큰 경우에는 포장층의 각층의 두께나 재료의 특성과 관계없이 항상 장수명 아스팔트 포장으로 간주할 수 있으나, 250mm보다 작을 경우에는 장수명 아스팔트 포장에서 제외되었다. 총 아스팔트층의 두께가 250mm보다 크고 410mm보다 작은 경우에는 장수명 아스팔트 포장 조건에 만족하기 위한 포장층 두께와 탄성계수값을 결정할 수 있는 절차를 제시하였다.