Use of regression trees to predict overweight trucks from historical weigh-in-motion data

作     者：Mariana Bosso Kamilla L.Vasconcelos Linda Lee Ho Liedi L.B.Bernucci Mariana Bosso;Kamilla L. Vasconcelos;Linda Lee Ho;Liedi L.B. Bernucci

作者机构：Department of Transportation EngineeringUniversity of Sao Paulo(USP)Sao PauloBrazil Department of Production EngineeringUniversity of Sao Paulo(USP)Sao PauloBrazil 

出 版 物：《Journal of Traffic and Transportation Engineering(English Edition)》 (交通运输工程学报（英文版）)

年 卷 期：2020年第7卷第6期

页      面：843-859页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 0813[工学-建筑学] 0814[工学-土木工程] 0823[工学-交通运输工程] 

基　　金：The authors thank the Arteris S.A.(Autopista Fernao Dias and Centro de Desenvolvimento Tecnologico) ANTT(Agencia Nacional de Transportes Terrestres) and CNPq(Conselho Nacional de Desenvolvimento Cientifico e Tecnologico)for supporting this research 

主　　题：Regression piecewise Overloaded trucks Travel patterns Axle loading RPART package Enforcement activities 

摘      要：The traffic of overloaded trucks is a critical problem in *** affects pavement performance life,reduces the service life of bridges,and has a negative impact on road safety,average speed and level of *** are several practices to prevent the truck overloading issue,i.e.,enforcement activities to verify the truck’s compliance with the legal weight *** paper investigates the development of a method that uses available weigh-in-motion(WIM)data to identify overloaded truck weight and travel *** proposed approach is based on regression trees method,a simple and easily understandable analytic tool used to build prediction models from a large set of *** overall analysis of the overloaded truck regression tree model shows that the most important variable to classify and predict overloading is the truck *** the axle overloading,the most significant variable is the time of the day(most of the overloaded trucks travel at late night or early morning).The regression tree results can be used to optimize the efficiency of administration activities by planning truck enforcement operations based on the more critical ***,the results improve the knowledge about the load characteristics of trucks,which can lead to more effective pavement management systems and more assertive pavement structure designs.