Abstract Truck weight data is needed for a wide range of applications including but not limited to pavement design, weight enforcement, traffic monitoring, and freight transportation planning. Unfortunately, the low spatial resolution of weight sensors along the transportation network can limit these and other potential applications. The main contribution of this paper is a methodology to estimate gross vehicle weight (GVW) distributions at traffic count sites, which collect traffic volumes but currently do not have the ability to directly measure vehicle weight. This paper presents a method for estimating GVW distributions of five-axle tractor-trailers (“3-S2”) at traffic count sites by fuzing weight data from weigh-in-motion (WIM) sites with position data from global positioning system (GPS) equipped trucks. Truck travel patterns derived from a truck GPS database were used to determine the degree to which a WIM and traffic count site are spatially related. A GVW distribution was then estimated by combining Gaussian mixture models (GMM) estimated at WIM sites defined to be spatially related to the traffic count site. A leave-one-out cross validation framework allowed for comparisons of estimated and measured GVW distributions at each WIM site. Coincidence ratios and two-sample Kolmogorov-Smirnov (KS) tests were used as comparison metrics for a case study of 112 WIM sites in California. The proposed methodology provided better goodness-of-fit between observed and estimated GVW distributions compared to a baseline approach which defined the spatial relation between sites using great circle distances (GCD).

中文翻译：

---

动态称重和全球定位系统数据的融合，以估计交通计数站点的卡车重量分布

摘要 卡车重量数据需要广泛的应用，包括但不限于路面设计、重量执行、交通监控和货运规划。不幸的是，沿交通网络的重量传感器的低空间分辨率会限制这些和其他潜在的应用。本文的主要贡献是一种在交通计数站点估计车辆总重 (GVW) 分布的方法，该站点收集交通量，但目前无法直接测量车辆重量。本文提出了一种通过将动态称重 (WIM) 站点的重量数据与全球定位系统 (GPS) 的位置数据进行融合来估计交通计数站点的五轴牵引拖车 (“3-S2”) 的 GVW 分布的方法。 ) 配备的卡车。来自卡车 GPS 数据库的卡车行驶模式用于确定 WIM 和交通计数站点在空间上的相关程度。然后通过组合在定义为与交通计数站点空间相关的 WIM 站点估计的高斯混合模型 (GMM) 来估计 GVW 分布。留一法交叉验证框架允许比较每个 WIM 站点的估计和测量 GVW 分布。重合比和两个样本 Kolmogorov-Smirnov (KS) 测试被用作加利福尼亚州 112 个 WIM 站点案例研究的比较指标。与使用大圆距离 (GCD) 定义站点之间空间关系的基线方法相比，所提出的方法在观察到的和估计的 GVW 分布之间提供了更好的拟合优度。