吉林大学学报(工学版) ›› 2021, Vol. 51 ›› Issue (6): 2031-2039.doi: 10.13229/j.cnki.jdxbgxb20200676

• 交通运输工程·土木工程 • 上一篇    

城市公交车辆驻站时间特征分析及预测

杨世军(),裴玉龙(),潘恒彦,程国柱,张文会   

  1. 东北林业大学 交通学院,哈尔滨 150040
  • 收稿日期:2020-09-03 出版日期:2021-11-01 发布日期:2021-11-15
  • 通讯作者: 裴玉龙 E-mail:ysj0826@nefu.edu.cn;peiyulong@nefu.edu.cn
  • 作者简介:杨世军(1981-),男,讲师,博士研究生. 研究方向:交通规划,交通运输管理. E-mail:ysj0826@nefu.edu.cn
  • 基金资助:
    国家重点研发计划项目(2018YFB1600900);国家自然科学基金重点项目(51638004)

Characteristics analysising and prediction of dwelling time of urban bus

Shi-jun YANG(),Yu-long PEI(),Heng-yan PAN,Guo-zhu CHENG,Wen-hui ZHANG   

  1. School of Traffic and Transportation,Northeast Forestry University,Harbin 150040,China
  • Received:2020-09-03 Online:2021-11-01 Published:2021-11-15
  • Contact: Yu-long PEI E-mail:ysj0826@nefu.edu.cn;peiyulong@nefu.edu.cn

摘要:

为准确分析公交车辆的驻站时间特征,并对其进行预测,本文对公交车辆驻站过程中的时间构成进行分析,引入了驻站服务时间的概念,用于量化车辆驻站过程中乘客上、下车的时长。根据人工调查数据分析,得出上车时间与下车时间是驻站服务时间与驻站时间的影响因素;与下车时间相比,上车时间与驻站服务时间、驻站时间的相关性更强,且两者的最大值与驻站服务时间、驻站时间的相关性最强。分析了车内拥挤状态对乘客上车时间、下车时间的影响,同时分析了乘客的付费方式、年龄、负重情况对上车时间的影响。引入车辆停靠偏离距离的概念,分析了驻站过程中车辆停靠偏离程度、上车人数对上车延误损失时间的影响,以及车辆待启时长对出站启步延误损失时间的影响。基于上述分析结果,构建了具有8个输入层的BP神经网络的驻站时间预测模型,模型的训练结果和预测结果的拟合优度分别为0.915和0.955,具有良好的预测作用。

关键词: 城市交通, 公交车辆, 驻站时间, 延误损失时间, 驻站服务时间, BP神经网络, 驻站时间预测

Abstract:

In order to accurately analyze the characteristics of bus dwelling time and forecast the dwelling time, this paper analyzes the time structure of bus dwelling process. The concept of station service time is introduced to quantify the length of time that a vehicle is used for passengers to get on and off the train in the process of station service. According to the analysis of manual survey data, it is concluded that the boarding time and alighting time are the influencing factors of the station service time and dwelling time. Compared with the alighting time, the correlations between boarding time and station service time, and between boarding time and dwelling time are stronger, and the maximum value of both has the strongest correlation with the station service time and dwelling time. This paper analyzes the impact of congestion situation inside the bus on the boarding time and alighting time of passengers, as well as the influence of the payment method, age and load of passengers on the boarding time. This paper introduces the concept of vehicle stop deviation distance, and analyzes the influence of the degree of vehicle stop deviation and the number of passengers on the boarding delay loss time, and the influence of vehicle waiting time on the departure delay loss time. Based on the above analysis results, a BP neural network model with eight input layers is constructed. The goodness of fit between the training results and the prediction results is 0.915 and 0.955 respectively, which has a good forecasting effect.

Key words: urban traffic, bus, dwelling time, time lost due to delay, station time, BP neural network, prediction of the dwelling time

中图分类号: 

  • U491.1

图1

车辆驻站时间构成"

表1

各时刻参数及其含义"

参数含义参数含义
t1车辆进站停车t5

乘客停止下车,

车辆后门关闭

t2

车辆后门开启,

乘客开始下车

t6

乘客上车结束,

车辆前门关闭

t3车辆前门开启t7前车起步出发
t4乘客开始上车t8车辆起步出站

图2

上、下车时间与上、下车人数的关系"

图3

驻站服务时间分析"

图4

驻站时间分析"

图5

车内拥挤程度对上、下车时间的影响"

图6

支付方式对上车时间的影响"

图7

年龄构成对上车时间的影响"

图8

行李负重对上车时间的影响"

图9

损失延误时间示意"

表2

参数及其含义"

参数含义参数含义
Ci公交车辆编号xqd车辆停靠位置
Li后车与前车的实际距离xzs站台起点位置
Ls后车与前车的安全距离xze站台终点位置

图10

上车延误损失时间分析"

图11

车辆启步延误损失时间分析"

表3

输入层指标"

编号符号指标释义
1NP停靠站停车位数量
2NL停靠站线路数量
3Nup站点上车人数
4Ndown站点下车人数
5AG站台乘客平均年龄
6LO站台乘客行李负重系数
7FE上车乘客中手机扫码支付的比例
8Bcro车内拥挤状态

图12

驻站时间的BP神经网络模型结构"

图13

BP神经网络训练与预测结果拟合"

1 Estrada M, Trapote C, Roca M, et al. Improving bus travel times with passive traffic signal coordination[J]. Transportation Research Record, 2009, 2111(1): 68-75.
2 Fan W D, Machemehl R B. Do transit users just wait for buses or wait with strategies some numerical results that transit planners should see[J]. Transportation Research Record, 2009, 2111(1): 169-176.
3 Peng Zhong-ren, Lyndem E, Chen Wei-ya. Understanding transit service gaps[C]∥The 89th Transportation Research Board Annual Meeting, Washington DC, 2009: 1-18.
4 Khoo H L. Statistical modeling of bus dwell time at stops[J]. Journal of the Eastern Asia Society for Transportation Studies, 2013, 10: 1489-1500.
5 Chen Shao-kuan, Zhou Rui, Zhou Yang-fan, et al. Computation on bus delay at stops in Beijing through statistical analysis[J]. Mathematical Problems in Engineering, 2013, 2013(1971): No.745370.
6 Tirachini A. Bus dwell time: the effect of different fare collection systems,bus floor level and age of passengers[J]. Transportmetrica A: Transport Science, 2013, 9(1):28-49.
7 Arhin S A, Noel E C. Predicting dwell time by bus stop type and time of the day[J]. Journal of Civil & Environmental Engineering, 2015, 5(5): No.1000189.
8 梁士栋,赵淑芝,马明辉,等. 路段直线式公交站点对公交车延误的影响[J]. 吉林大学学报:工学版,2016,46(6):1807-1817.
Liang Shi-dong, Zhao Shu-zhi, Ma Ming-hui, et al. Impacts of linear bus stop on bus delays[J]. Journal of Jilin University(Engineering and Technology Edition), 2016, 46(6): 1807-1817.
9 王旭,陈旭梅,寇伟彬,等. 公交站点停靠时间预测模型研究[J]. 交通信息与安全,2016,34(2):55-61.
Wang Xu, Chen Xu-mei, Kou Wei-bin, et al. A prediction model of bus dwelling time at the stops[J]. Journal of Transport Information and Safety, 2016, 34(2): 55-61.
10 吕伟,李志红,赵彩虹,等. 城市公交车停靠时间特征的观测试验与实证研究[J]. 公路交通科技,2019,36(11):90-96.
Lü Wei, Li Zhi-hong, Zhao Cai-hong, et al. Observation experiment and empirical study on parking time characteristics of city buses[J]. Journal of Highway and Transportation Research and Development, 2019, 36(11): 90-96.
11 邓媚,李春达. 不同站台环境下公交车停靠时间的动态预测模型[J]. 重庆交通大学学报:自然科学版,2019,38(12):105-109.
Deng Mei, Li Chun-da. Dynamic prediction model of bus dwell time under different station conditions[J]. Journal of Chongqing Jiaotong University(Natural Science), 2019, 38(12): 105-109.
12 朱文韬,钱国敏,马东方,等. 考虑路口上游停靠站影响的公交延误模型[J]. 浙江大学学报: 工学版,2020,54(4):796-803, 815.
Zhu Wen-tao, Qian Guo-min, Ma Dong-fang, et al. Bus delay model considering influence of stop at upstream of intersection[J]. Journal of Zhejiang University(Engineering Science), 2020, 54(4): 796-803, 815.
13 马尚萱. 常规公交站点停靠时间分析与预测方法[D]. 南京:东南大学交通学院,2016.
Ma Shang-xuan. Bus dwell time analysis and prediction methods[D]. Nanjing: School of Transportation, Southeast University, 2016.
14 陈亮,冯柳,李巧茹. 考虑在车感知价值的公交发车间隔计算模型[J]. 哈尔滨工业大学学报,2018,50(3):150-155.
Chen Liang, Feng Liu, Li Qiao-ru. Bus departure interval model considering on-bus perceived value[J]. Journal of Harbin Institute of Technology, 2018, 50(3): 150-155.
15 Group KFH. Transit Capacity and Quality of Service Manual[M]. 3th ed. Washington DC: TRB, 2013.
16 姜桂艳,刘彬,隋晓艳. 基于IC卡收费系统的公交客流信息实时采集方法[J]. 吉林大学学报:工学版,2016,46(4):1076-1082.
Jiang Gui-yan, Liu Bin, Sui Xiao-yan. Real time information collection of passenger flow in public transportation based on bus IC card charging system[J]. Journal of Jilin University(Engineering and Technology Edition), 2016, 46(4): 1076-1082.
17 刘莹,于淼,刘阳. 基于乘客感知的公交车线路服务质量评价模型[J]. 东北大学学报:自然科学版,2019,40(5):750-755.
Liu Ying, Yu Miao, Liu Yang. Evaluation model of bus Route service quality based on passengers perceptions[J]. Journal of Northeastern University(Natural Science), 2019, 40(5): 750-755.
18 Liu Y. An improved AHP and BP neural network method for service quality evaluation of city bus[J]. International Journal of Computer Applications in Technology, 2018, 58(1): 37-44.
19 罗菊,方照东,袁泉.基于集成神经网络的信道估计方法研究[J].重庆邮电大学学报:自然科学版,2020, 32(6): 969-975.
Luo Ju, Fang Zhao-dong, Yuan Quan. Research on channel estimation method based on integrated neural network[J]. Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition), 2020, 32(6): 969-975.
20 李娜娜, 胡坚剑, 顾军华, 等. 深度置信网络优化模型在人才评价中的应用[J]. 计算机工程, 2020, 46(2): 80-87, 102.
Li Na-na, Hu Jianjian, Gu Jun-hua, et al. Application of optimized deep belief network model in talent evaluation[J]. Computer Engineering, 2020, 46(2): 80-87, 102.
21 张飞,雒江涛,何宸,等. NDN中基于神经网络的兴趣洪泛攻击综合防御方案[J].重庆邮电大学学报:自然科学版, 2020, 32(2): 177-184.
Zhang Fei, Luo Jiang-tao, He Chen,et al. Evaluation model of bus Route service quality based on passengers perceptions[J]. Journal of Northeastern University(Natural Science), 2020, 32(2): 177-184.
[1] 孙宝凤,姜源,郑黎黎,崔万坤,任欣欣. 变覆盖半径下城市轨道交通维护保障网络设计模型[J]. 吉林大学学报(工学版), 2020, 50(2): 526-534.
[2] 陈磊,王江锋,谷远利,闫学东. 基于思维进化优化的多源交通数据融合算法[J]. 吉林大学学报(工学版), 2019, 49(3): 705-713.
[3] 刘东亮, 王秋爽. 基于NGSIM数据的车辆瞬时速度获取方法[J]. 吉林大学学报(工学版), 2018, 48(1): 330-335.
[4] 王德军, 吕志超, 王启明, 张贤达, 王子健. 基于汽缸压力辨识的发动机失火故障诊断[J]. 吉林大学学报(工学版), 2017, 47(3): 917-923.
[5] 黄璇, 郭立红, 李姜, 于洋. 改进粒子群优化BP神经网络的目标威胁估计[J]. 吉林大学学报(工学版), 2017, 47(3): 996-1002.
[6] 郭应时, 付锐, 赵凯, 马勇, 袁伟. 驾驶人换道意图实时识别模型评价及测试[J]. 吉林大学学报(工学版), 2016, 46(6): 1836-1844.
[7] 高明亮, 于生宝, 郑建波, 徐畅, 张堃, 栾卉. PSBP在高密度电阻率法二维反演中的应用[J]. 吉林大学学报(工学版), 2015, 45(6): 2026-2033.
[8] 李寿涛, 田微, 郭鹏程, 马用学, 张浩, 王楠. 基于模糊自适应的BP神经网络动态行驶车辆车长测算[J]. 吉林大学学报(工学版), 2015, 45(6): 1881-1886.
[9] 闫楚良, 郝云霄, 刘克格. 基于遗传算法优化的BP神经网络的材料疲劳寿命预测[J]. 吉林大学学报(工学版), 2014, 44(6): 1710-1715.
[10] 陈莉, 孙永海, 付天宇, 丁健峰. 羊肚菌胞外多糖快速估测方法[J]. 吉林大学学报(工学版), 2014, 44(2): 567-572.
[11] 侯阿临, 廖庆, 靳志娟, 陈娟, 耿莹. 计算全息图的人工神经网络压缩算法[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 21-24.
[12] 司建波, 杨芳, 郭蔚莹, 姚燕. 基于BP神经网络的两阶段疾病预测模型[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 481-484.
[13] 王改革, 郭立红, 段红, 刘逻, 王鹤淇. 基于萤火虫算法优化BP神经网络的目标威胁估计[J]. 吉林大学学报(工学版), 2013, 43(04): 1064-1069.
[14] 王国磊, 陈恳, 陈雁, 朱丽, 王力强, 颜华. 变参数下的空气喷枪涂层厚度分布建模[J]. 吉林大学学报(工学版), 2012, 42(01): 188-192.
[15] 张祥合, 王丹, 任露泉, 赵宏伟. 基于多维空间仿生信息学的目标识别新算法[J]. 吉林大学学报(工学版), 2011, 41(增刊2): 269-274.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!