A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Clustering Methods for Truck Traffic Characterization in Pavement ME Design
Axle loading spectrum inputs obtained from existing weigh-in-motion (WIM) stations are one of the key data elements required in the pavement mechanistic-empirical (ME) design. Because of limited number of WIM stations within a state agency, it is critical to implement clustering approaches to identifying similar traffic patterns and developing cluster average Level 2 inputs for a particular pavement design. Even though several states have applied clustering methods for this purpose, they rely solely on hierarchical-based method. Many other types of clustering techniques based on different induction principles are available but have not been tested. In this paper, four types of clustering methods, including agglomerative hierarchical, partitional K-means, model-based, and fuzzy c-means algorithms, are implemented to cluster traffic attributes for pavement ME design using data sets from 39 WIM sites in Michigan. Two case studies, one flexible pavement and one rigid pavement, are conducted. The impacts of using various clustering methods for preparation of Level 2 traffic inputs on pavement performance are examined. Cosine similarity analyses reveal that the four clustering methodologies generate highly comparable traffic inputs and predicted pavement performance as compared to the Level 1 results. However, the equivalent single axle loads (ESALs) from the four clustering methods can result in 12.7 mm (0.5 in.) of difference of designed surface layer thickness. The hierarchical method consistently has the lowest cosine similarity values, the fuzzy-based method has the highest similarity, while the other two clustering methods generally outperform the hierarchical method if Level 1 site-specific results are set as the benchmark. This study raises the awareness that more research is desired to select the most appropriate clustering approach for the development of Level 2 traffic inputs based on existing WIM data sets for pavement ME design.
Clustering Methods for Truck Traffic Characterization in Pavement ME Design
Axle loading spectrum inputs obtained from existing weigh-in-motion (WIM) stations are one of the key data elements required in the pavement mechanistic-empirical (ME) design. Because of limited number of WIM stations within a state agency, it is critical to implement clustering approaches to identifying similar traffic patterns and developing cluster average Level 2 inputs for a particular pavement design. Even though several states have applied clustering methods for this purpose, they rely solely on hierarchical-based method. Many other types of clustering techniques based on different induction principles are available but have not been tested. In this paper, four types of clustering methods, including agglomerative hierarchical, partitional K-means, model-based, and fuzzy c-means algorithms, are implemented to cluster traffic attributes for pavement ME design using data sets from 39 WIM sites in Michigan. Two case studies, one flexible pavement and one rigid pavement, are conducted. The impacts of using various clustering methods for preparation of Level 2 traffic inputs on pavement performance are examined. Cosine similarity analyses reveal that the four clustering methodologies generate highly comparable traffic inputs and predicted pavement performance as compared to the Level 1 results. However, the equivalent single axle loads (ESALs) from the four clustering methods can result in 12.7 mm (0.5 in.) of difference of designed surface layer thickness. The hierarchical method consistently has the lowest cosine similarity values, the fuzzy-based method has the highest similarity, while the other two clustering methods generally outperform the hierarchical method if Level 1 site-specific results are set as the benchmark. This study raises the awareness that more research is desired to select the most appropriate clustering approach for the development of Level 2 traffic inputs based on existing WIM data sets for pavement ME design.
Clustering Methods for Truck Traffic Characterization in Pavement ME Design
Li, Qiang (author) / Wang, K. P. (author) / Eacker, Mike (author) / Zhang, Zhongjie (author)
2016-06-09
Article (Journal)
Electronic Resource
Unknown
Growth of truck traffic volume for mechanistic-empirical pavement design
| Online Contents | 2009
Estimation of Lane Distribution of Truck Traffic for Pavement Design
| Online Contents | 1995