Poster 18-04

Derivation of Truck Traffic Classification Groups from Cluster Analysis of Weigh-in-Motion Data

PI: S. Sonny Kim

Co-PI(s): Stephan A. Durham, Ph.D., P.E., F.ASCE Jidong Yang, Ph.D., P.E.

Institution(s): The University of Georgia

Abstract

The Mechanistic-Empirical (ME) pavement design requires high-dimensional traffic feature inputs, including Vehicle Class Distributions (VCD), Monthly Distribution Factors (MDF), Hourly Distribution Factors (HDF), and Normalized Axles Load Spectra (NALS). In simplifying the pavement ME design practice, Truck Traffic Classification (TTC) groups are commonly used for characterized traffic inputs. Thus, properly defining TTC groups is critical for state-specific pavement ME design practice. In this study, the truck traffic data from the existing Weight-in-Motion (WIM) stations were utilized to develop specific TTC groups for efficient pavement ME design practice in Georgia. A data analytics procedure was developed by leveraging Machine Learning (ML) techniques to first reduce the high-dimensional traffic features by Principal Component Analysis (PCA), followed by K-means clustering method to identify appropriate TTC groups. The effectiveness of the derived TTC groups was verified by application of pavement ME design software with characterized traffic inputs.

Please comment below with any statements or questions you may have. Also let GTI if you would be interested webinars or presentations on similar topics.