基于主成分-聚类法的高速公路沥青路面养护路段划分
|
摘要
为了合理划分高速公路沥青路面养护路段,改变以往由于养护路段划分不合理带来的养护资金不足、人工浪费的问题,采用主成分-聚类分析法对高速公路沥青路面养护路段进行了划分。以京藏高速公路甘肃白银段沥青路面使用性能指标检测数据为样本,首先运用主成分分析法对各个路面使用性能指标数据进行降维处理,根据主成分累计贡献率大小确定路况信息的主成分个数与主成分得分;再将得到的主成分得分作为聚类分析的变量,进行养护路段的分类与划分。结果表明:运用主成分-聚类分析法进行养护路段划分将路况特征一致的路段划分为一类,各指标间的相关性显著,根据主成分-聚类分析法的结果以及聚类后的路面使用性能的4个评价指标平均值大小,确定相应路段养护的优先次序,划分结果可用于科学的养护决策。
In this paper the principal component analysis and cluster analysis method are used to divide the maintenance sections of expressway asphalt pavement on the Baiyin Section of the Beijing-Tibet Highway in Gansu Province as a sample to change the previous shortage of funds and waste of labors for the unreasonable division of maintenance sections in past.The asphalt pavement sections data have been checked and verified.The principal component analysis and cluster analysis method are used to analyze the indexes of highway maintenance sections in Gansu Province.The variables are first dimension-reduced and the principal component scores that could basically provide all the information are determined according to the principal component contribution rate.Then the principal component scores are clustered by analyzing variables and classifying problems.Through analysis it is found that the use of principal component analysis and cluster analysis method for road segmentation,the correlation between the indicators is significant,and will not affect the road maintenance in the road segmentation and road surface rating,the redundancy of data can be minimized according to the divided types of road sections which are to be used for maintenance decision-making.The priority of the maintenance for the four types of road sections is determined by the average size of each indicator.
In this paper the principal component analysis and cluster analysis method are used to divide the maintenance sections of expressway asphalt pavement on the Baiyin Section of the Beijing-Tibet Highway in Gansu Province as a sample to change the previous shortage of funds and waste of labors for the unreasonable division of maintenance sections in past.The asphalt pavement sections data have been checked and verified.The principal component analysis and cluster analysis method are used to analyze the indexes of highway maintenance sections in Gansu Province.The variables are first dimension-reduced and the principal component scores that could basically provide all the information are determined according to the principal component contribution rate.Then the principal component scores are clustered by analyzing variables and classifying problems.Through analysis it is found that the use of principal component analysis and cluster analysis method for road segmentation,the correlation between the indicators is significant,and will not affect the road maintenance in the road segmentation and road surface rating,the redundancy of data can be minimized according to the divided types of road sections which are to be used for maintenance decision-making.The priority of the maintenance for the four types of road sections is determined by the average size of each indicator.
引文
[1]杜二鹏,马松林,景海民.基于灰色系统理论的沥青路面使用性能预测[J].同济大学学报:自然科学版,2010,38(8):1161-1164.
[2]古红兵,李金明,黄海明,周育名.沥青路面养护路段划分指标合理性研究[J].中外公路,2015,35(2):312-314.
[3]蒋红妍.高速公路路面养护管理系统研究[D].长安大学,2006.
[4]王佳,胡列格.养护路段的有序聚类划分[J].系统工程,2008,26(11):71-74.
[5]王佳.高速公路沥青路面使用性能评价与预测决策研究[D].长沙理工大学,2006.
[6]农家萍,张肖宁.模糊聚类分析在沥青路面养护路段划分中的应用[J].中外公路,2006,(3):119-122.
[7]马士宾,虞秋富,张静,袁文瑞.基于有序聚类法的大中修路段划分技术研究[J].河北工业大学学报,2014,43(5):106-109.
[8]Wang Wenjuan,Shaofan Wang,Danny Xiao,et al.An Unsupervised Cluster Method for Pavement Grouping Based on Multidimensional Performance Data[J].Journal of Transportation Engineering,Part B:Pavements,2018,144(2):04018005.
[9]Bianchini A.Pavement Maintenance Planning at the Network Level with Principal Component Analysis[J].Journal of Infrastructure Systems,2014,20(2):04013013-1-04013013-8.
[10]Li Bo,Ren Xiaoyu,LI Yanbo,MA Weizhong,LI Hanlian.Evaluation and Selection of Sealants and Fillers Using Principal Component Analysis for Cracks in Asphalt Concrete Pavements[J].Journal of Wuhan University of Technology(Materials Science),2017,32(2):408-412.
[11]殷晗宇.高速公路沥青路面使用性能评价与预测决策研究[D].长安大学,2016.
[12]李波,韩森,徐鸥明,滕旭秋.基于主成分分析法的沥青路面使用性能评价[J].长安大学学报:自然科学版,2009,29(3):15-18.
[13]杨彦海,董帅,侯博,张怀志.基于聚类分析法的沥青路面气候分区研究[J].重庆交通大学学报:自然科学版,2018,37(1):40-45+61.
[14]公丽艳,孟宪军,刘乃侨,毕金峰.基于主成分与聚类分析的苹果加工品质评价[J].农业工程学报,2014,30(13):276-285.
[15]Johnson R A,Wichern D W.Applied Multivariate Statistical Analysis,5/E[J].Technometrics,2005,47(4):517-517.
[16]王静,李波,马伟中,颜鲁春,李鹏.甘肃省河西走廊地区高速公路沥青路面养护对策[J].中外公路,2018,38(1):67-72.
[2]古红兵,李金明,黄海明,周育名.沥青路面养护路段划分指标合理性研究[J].中外公路,2015,35(2):312-314.
[3]蒋红妍.高速公路路面养护管理系统研究[D].长安大学,2006.
[4]王佳,胡列格.养护路段的有序聚类划分[J].系统工程,2008,26(11):71-74.
[5]王佳.高速公路沥青路面使用性能评价与预测决策研究[D].长沙理工大学,2006.
[6]农家萍,张肖宁.模糊聚类分析在沥青路面养护路段划分中的应用[J].中外公路,2006,(3):119-122.
[7]马士宾,虞秋富,张静,袁文瑞.基于有序聚类法的大中修路段划分技术研究[J].河北工业大学学报,2014,43(5):106-109.
[8]Wang Wenjuan,Shaofan Wang,Danny Xiao,et al.An Unsupervised Cluster Method for Pavement Grouping Based on Multidimensional Performance Data[J].Journal of Transportation Engineering,Part B:Pavements,2018,144(2):04018005.
[9]Bianchini A.Pavement Maintenance Planning at the Network Level with Principal Component Analysis[J].Journal of Infrastructure Systems,2014,20(2):04013013-1-04013013-8.
[10]Li Bo,Ren Xiaoyu,LI Yanbo,MA Weizhong,LI Hanlian.Evaluation and Selection of Sealants and Fillers Using Principal Component Analysis for Cracks in Asphalt Concrete Pavements[J].Journal of Wuhan University of Technology(Materials Science),2017,32(2):408-412.
[11]殷晗宇.高速公路沥青路面使用性能评价与预测决策研究[D].长安大学,2016.
[12]李波,韩森,徐鸥明,滕旭秋.基于主成分分析法的沥青路面使用性能评价[J].长安大学学报:自然科学版,2009,29(3):15-18.
[13]杨彦海,董帅,侯博,张怀志.基于聚类分析法的沥青路面气候分区研究[J].重庆交通大学学报:自然科学版,2018,37(1):40-45+61.
[14]公丽艳,孟宪军,刘乃侨,毕金峰.基于主成分与聚类分析的苹果加工品质评价[J].农业工程学报,2014,30(13):276-285.
[15]Johnson R A,Wichern D W.Applied Multivariate Statistical Analysis,5/E[J].Technometrics,2005,47(4):517-517.
[16]王静,李波,马伟中,颜鲁春,李鹏.甘肃省河西走廊地区高速公路沥青路面养护对策[J].中外公路,2018,38(1):67-72.