Abstract
ABSTRACT China’s highway network, with over 90% asphalt pavements, demands region-specific management strategies due to varying environmental and traffic conditions across the country and the susceptibility of asphalt to these factors. This study introduces a K-means++ clustering method for regionalising China’s highway asphalt pavements, focusing on the complex interaction between climate and traffic. The research integrates key indicators to delineate distinct climate, traffic, and climate-traffic zones, enhancing understanding of pavement performance and maintenance requirements. Employing an extensive dataset that includes temperature, precipitation, traffic volume, vehicle travel distance and congestion levels, the study applies the Elbow method to identify the optimal number of clusters, ensuring compactness and clear separation within the data. The results reveal clear zones, each with unique attributes essential for informed pavement design and maintenance. Advanced clustering techniques offer insights into the relationships between regional factors, supporting data-driven management decisions. The comprehensive framework presented integrates environmental and traffic factors into an accurate regionalisation model, pivotal for strategic planning and maintenance of China’s highway infrastructure. It addresses the combined impacts of climate and traffic on pavement performance, providing a scientific basis for pavement management strategies.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call