基于GPS数据的危险品运输车辆行程链聚类研究

doi:10.16265/j.cnki.issn1003-3033.2023.09.1676

摘要/Abstract

摘要：

为帮助政府相关部门精细化监管危险化学品运输,提出一种基于全球定位系统(GPS)数据的危险品运输车辆行程链聚类分析框架。设置时空阈值,从GPS数据中提取车辆基站和中途有效停车点,生成危险品运输车辆行程链;在计算行程链数、平均停车点数、平均行程链停车时长和平均行程链距离等已有指标的基础上,使用平均行程风险和平均停车点风险衡量危险品运输车辆行程风险;以行程链特征为聚类指标,轮廓系数与误差平方和为评估指标,比选K-Means、K-Means++、PAM、FCM这4种算法的行程链聚类效果;通过实际案例分析验证框架的可行性。结果表明:K-Means++ 算法效果最佳,危险品运输车辆被分为化工园区接驳(44.19%)、城际运输(31.42%)、城市配送(13.23%)、场站接驳(9.76%)和非工作状态(1.40%)5类。

关键词: 全球定位系统(GPS)数据, 危险品运输车辆, 行程链, 聚类, 运输风险

Abstract:

In order to assist the government in regulating the transportation of hazardous materials, a cluster analysis framework based on GPS data was proposed. We set the spatiotemporal threshold, extracted the vehicle base station and halfway effective stop point from the GPS data, and generated trip chains of the hazardous material vehicle. Based on calculating the number of trip chains, the average number of stop points, the average stop time of trip chains and the average distance of trip chains, the average risk of trip and trip point were proposed to measure the risk of hazardous materials transportation vehicles. The characteristics of vehicle trip chain were taken as clustering indicators, silhouette coefficient and the sum of squares due to error were taken as evaluation indicators, and by comparing the results of K-Means, K-Means++, PAM and FCM algorithms, the trip chains of hazardous materials transportation vehicles were clustered. The feasibility of the framework was verified by case analysis. The results show that the K-Means++ algorithm has the best effect, and the hazardous material transportation vehicles are divided into 5 categories: chemical park connection (44.19%), intercity transportation (31.42%), city distribution (13.23%), freight terminal connection (9.76%) and non-working state (1.40%).

Key words: global positioning system (GPS) data, hazardous materials transportation vehicle, trip chain, cluster, transportation risk

陈冉冉, 徐佳力, 李健. 基于GPS数据的危险品运输车辆行程链聚类研究[J]. 中国安全科学学报, 2023, 33(9): 157-163.

CHEN Ranran, XU Jiali, LI Jian. Study on trip chain clustering of hazardous materials transportation vehicle based on GPS data[J]. China Safety Science Journal, 2023, 33(9): 157-163.

图/表 7

图1

表1

图2

图3

表2

表3

图4

参考文献 21

[1]	杨婷, 帅斌, 黄文成. 基于N-K模型的道路危险品运输系统耦合风险分析[J]. 中国安全科学学报, 2019, 29(9):132-137. doi: 10.16265/j.cnki.issn1003-3033.2019.09.021
	YANG Ting, SHUAI Bin, HUANG Wencheng. Coupling risk analysis of road dangerous goods transportation system based on N-K model[J]. China Safety Science Journal, 2019, 29(9):132-137. doi: 10.16265/j.cnki.issn1003-3033.2019.09.021
[2]	王海星, 王翔宇, 王招贤, 等. 基于数据挖掘的危险货物运输风险驾驶行为聚类分析[J]. 交通运输系统工程与信息, 2020, 20(1):183-189.
	WANG Haixing, WANG Xiangyu, WANG Zhaoxian, et al. Dangerous driving behavior clustering analysis for hazardous materials transportation based on data mining[J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(1):183-189.
[3]	黄合来, 罗启章, 彭韵颖, 等. 山区高速公路隧道群路段危化品运输风险评价体系研究[J]. 中南大学学报:自然科学版, 2018, 49(8):2107-2114.
	HUANG Helai, LUO Qizhang, PENG Yunying, et al. Risk evaluation for hazardous chemicals transportation at mountainous freeway with tunnels groups[J]. Journal of Central South University:Science and Technology, 2018, 49(8):2107-2114.
[4]	柴获, 何瑞春, 代存杰, 等. 考虑时空相异的危险品运输车辆安全调度[J]. 交通运输工程学报, 2019, 19(3):145-156.
	CHAI Huo, HE Ruichun, DAI Cunjie, et al. Safety scheduling of hazardous materials transportation vehicle considering spatio-temporal dissimilarity[J]. Journal of Traffic and Transportation Engineering, 2019, 19(3):145-156.
[5]	辛春林, 孟佳, 张建文, 等. 危险品运输路径优化问题研究综述[J]. 中国安全科学学报, 2018, 28(3):102-107. doi: 10.16265/j.cnki.issn1003-3033.2018.03.018
	XIN Chunlin, MENG Jia, ZHANG Jianwen, et al. A review of researches on optimization of hazardous materials transportation route[J]. China Safety Science Journal, 2018, 28(3):102-107. doi: 10.16265/j.cnki.issn1003-3033.2018.03.018
[6]	张玥, 帅斌, 黄文成, 等. 基于FRAM的铁路危险品运输事故演化机制研究[J]. 中国安全科学学报, 2020, 30(2):171-176. doi: 10.16265/j.cnki.issn1003-3033.2020.02.027
	ZHANG Yue, SHUAI Bin, HUANG Wencheng, et al. Accident evolution mechanism of railway dangerous goods transportation based on FRAM[J]. China Safety Science Journal, 2020, 30(2):171-176. doi: 10.16265/j.cnki.issn1003-3033.2020.02.027
[7]	吕伟, 蒋翠玲, 姜雅娟, 等. 考虑多因素影响的毒气扩散风险潜势图构建[J]. 中国安全科学学报, 2020, 30(11):175-181. doi: 10.16265/j.cnki.issn 1003-3033.2020.11.026
	LYU Wei, JIANG Cuiling, JIANG Yajuan, et al. Construction of risk potential map of toxic gas diffusion considering influence of multiple factors[J]. China Safety Science Journal, 2020, 30(11):175-181. doi: 10.16265/j.cnki.issn 1003-3033.2020.11.026
[8]	赵慧英, 钱大琳, 张博, 等. 危险货物道路运输车辆出行链活动类型识别[J]. 哈尔滨工业大学学报, 2019, 51(9):193-200.
	ZHAO Huiying, QIAN Dalin, ZHANG Bo, et al. Activity type recognition of trip chain for hazmat road transportation vehicle[J]. Journal of Harbin Institute of Technology, 2019, 51(9):193-200.
[9]	HOLGUÍN-VERAS J, PATIL G. Observed trip chain behavior of commercial vehicles[J]. Transportation Research Record: Journal of the Transportation Research Board, 2005, 1906:74-80. doi: 10.1177/0361198105190600109
[10]	JOUBERT J W, MEINTJES S. Freight activity chain generation using complex networks of connectivity[J]. Transportation Research Procedia, 2016, 12:425-435. doi: 10.1016/j.trpro.2016.02.078
[11]	SIRIPIROTE T, SUMALEE A, HO H W. Statistical estimation of freight activity analytics from global positioning system data of trucks[J]. Transportation Research Part E: Logistics and Transportation Review, 2020, 140: DOI: 10.1016/j.tre.2020.101986.
[12]	RUAN Minyan, LIN Jie, KAWAMURA K. Modeling urban commercial vehicle daily tour chaining[J]. Transportation Research Part E: Logistics and Transportation Review, 2012, 48(6):1169-1184. doi: 10.1016/j.tre.2012.06.003
[13]	MA Xiaolei, WANG Yong, MCCORMACK E D, et al. Understanding freight trip-chaining behavior using a spatial data-mining approach with GPS data[J]. Transportation Research Record: Journal of the Transportation Research Board, 2016, 2596:44-54. doi: 10.3141/2596-06
[14]	DUAN Mengyuan, QI Geqi, GUAN Wei, et al. Comprehending and analyzing multiday trip-chaining patterns of freight vehicles using a multiscale method with prolonged trajectory data[J]. Journal of Transportation Engineering Part A: Systems, 2020, 146:DOI: 10.1061/JTEPBS.0000392.
[15]	LARANJEIRO P F, MERCHAN D, GODOY L A, et al. Using GPS data to explore speed patterns and temporal fluctuations in urban logistics: the case of So Paulo, Brazil[J]. Journal of Transport Geography, 2019, 76:114-129. doi: 10.1016/j.jtrangeo.2019.03.003
[16]	ALHO A R, SAKA T, CHUA M H, et al. Exploring algorithms for revealing freight vehicle tours, tour-types, and tour-chain-types from GPS vehicle traces and stop activity data[J]. Journal of Big Data Analytics in Transportation, 2019, 1:175-190. doi: 10.1007/s42421-019-00011-x
[17]	SHARMAN B W, ROORDA M J. Multilevel modelling of commercial vehicle inter-arrival duration using GPS data[J]. Transportation Research Part E: Logistics and Transportation Review, 2013, 56:94-107. doi: 10.1016/j.tre.2013.06.002
[18]	KIM Sijin, PARK D, KIM Seheon, et al. Modeling courier vehicles' travel behavior: case of Seoul, South Korea[J]. Transportation Research Record: Journal of the Transportation Research Board, 2014, 2410(1):67-75. doi: 10.3141/2410-08
[19]	KHAN M, MACHEMEHL R. Analyzing tour chaining patterns of urban commercial vehicles[J]. Transportation Research Part A: Policy and Practice, 2017, 102:84-97. doi: 10.1016/j.tra.2016.08.014
[20]	YOU S I, RITCHIE S G. A GPS data processing framework for analysis of drayage truck tours[J]. KSCE Journal of Civil Engineering, 2018, 22(4):1454-1465. doi: 10.1007/s12205-017-0160-6
[21]	DAISY N S, MILLWARD H, LIU L. Trip chaining and tour mode choice of non-workers grouped by daily activity patterns[J]. Journal of Transport Geography, 2018, 69:150-162. doi: 10.1016/j.jtrangeo.2018.04.016

行程链数/条	危险品运输车辆数/辆	行程链平均停车点数/(个·条^-1)	占比/%
0	107	—	7.65
[1,3]	377	5.27	26.95
[4,6]	611	5.18	43.67
[7,9]	180	4.43	12.87
≥10	124	3.77	8.86

聚类结果	K-Means	K-Means++	PAM	FCM
簇数	5	5	4	5
SC	0.28	0.30	0.23	0.26
SSE	2 723.97	2 719.16	3 637.98	3 379.80

簇	N₁/条	N₂/(个·条^-1)	N₃/(h·条^-1)	N₄/(km·条^-1)	N₅/(人·km^-2)	N₆/(人·km^-2)	车辆占比/%
1	4.49	5.03	2.11	56.46	2 136.1	2 534.31	44.19
2	3.41	7.20	6.66	155.09	4 398.73	4 903.43	31.42
3	5.01	4.98	2.37	32.10	10 728.12	8 623.16	13.23
4	12.26	3.86	1.58	42.07	3 654.72	3 148.55	9.76
5	2.43	4.27	26.64	314.47	3 798.69	3 862.90	1.40