Decision Tree Analysis for Developing Weigh-in-Motion Spectra in the Californian Pavement Management System (PaveM)

Weigh-in-motion (WIM) devices record vehicle axle loads on highways. WIM data include loads, inter-axle spacings, classification, gross weights, length, and travel speed. Pavement design, management, performance studies all require data, directly as a spectrum or indirectly standard axles. In 2016, 132 were operating California’s highway network, one of the densest best-maintained clusters in United States. The University California Research Center (UCPRC) has been working with these since 2002, it completed analysis collected from 1998 to 2003 2008. This research investigated similarities load distributions at sites grouped them generate traffic inputs for pavement design. paper is an extension that work, including processing 2004–2015 80 sites, identifying distribution each site, updating original groupings, developing new procedure assign spectra other locations. For past 11 years, weight showed similar patterns, but average truck speeds decreased by 11%. A combination clustering cut-tree was used create decision tree classify stations’ into five spectra. methodology compute entire network Caltrans management system, PaveM. An application tool also developed generating input files CalME PavementME design tools.