Trunk highway passenger flow forecasting method based on comprehensive transportation network
-
摘要: 提出了一种融合多种运输方式的干线公路客流预测方法；通过引入基于“人次”的标准客运单元和“点-线”的枢纽节点转化方法，将公路、铁路、航空以及水运等不同运输方式子网络进行融合，构建了可体现不同运输方式之间换乘关系的综合交通网络模型；考虑出行经济费用、出行时间、最大出行恢复时间、舒适度等因素，构建了综合交通网络下不同运输方式的阻抗模型；利用额定载客数和单位时间发车次数等参数，实现了综合交通网络下不同运输方式路段最大容量的标定；基于标准客运单元和综合交通网络模型提出了考虑综合交通阻抗的客流分布预测模型，实现了考虑其他运输方式影响的干线公路客流预测，并以黑龙江省哈大绥齐地区为例进行方法验证。研究结果表明：与2019年的实际观测值相比，在无伴行线路时基于综合交通网络的干线公路客流预测方法预测结果平均误差为5.47%，略低于传统四阶段法的6.14%，但在有伴行线路时该方法平均误差为4.58%，远小于传统四阶段法的11.89%；相比传统四阶段法，该方法能够更好地反映综合交通网络结构变化后转移客流对干线公路客流量的影响；相比新增水运线路，新增高速铁路或普通铁路伴行线路对干线公路客流影响更大，更能促使公路客流向铁路进行转移。Abstract: A trunk highway passenger flow forecasting method integrating multiple transport modes was proposed. By introducing the standard passenger transport unit based on the man-time and the hub nodes conversion method from point to line, the sub-networks of different transport modes, such as highways, railways, airlines and waterways, were integrated, and the comprehensive transportation network model which can reflect the transfer relationship among different transport modes was built. By considering the travel economic cost, travel time, maximum travel recovery time, comfort level and other factors, the impedance functions of different transport modes in the comprehensive transportation network were constructed. The maximum capacities of different transport modes in the comprehensive transportation network were calibrated by using the rated passenger number and the number of departures per unit time. Based on the standard passenger transport unit and comprehensive transportation network model, the passenger flow distribution forecasting model considering the impedance of comprehensive transportation was proposed. On this basis, the passenger flow forecasting model considering the influence of different transport modes was realized. Taking Harbin, Daqing, Suihua and Qiqihar area in Heilongjiang Province as an example, the method was verified. Analysis results show that compared with the actual observation value in 2019, the average error of forecasting results of the passenger flow forecasting method based on the comprehensive transportation network is 5.47%, slightly lower than the 6.14% of the traditional four-stage method when there are no accompanying lines around the characteristic roads. However, the average error of forecasting results of the proposed method is 4.58% when the accompanying lines are around the characteristic roads, far less than the error value 11.89% of the traditional four-stage method. Compared with the traditional four-stage method, the proposed method can better reflect the influence of the transfer passenger on the traffic volume of the trunk highway after the structural change of comprehensive transportation network. Compared with adding waterways, adding high-speed or conventional railways accompanying lines have more obvious impact on the passenger flow of trunk highways, and can promote the transfer of passenger flow from highways to railways. 4 tabs, 12 figs, 32 refs.
-
图 9 基于综合交通网络的干线公路客流预测结果
Figure 9. Forecast result of trunk highway passenger flow based on comprehensive transportation network
图 12 新增伴行线路后干线公路特征路段客流增长率
Figure 12. Growth rates of passenger flow at characteristic sections of trunk highways after adding new accompanying lines
表 1 综合交通网络组成要素
Table 1. Elements of comprehensive transportation network
要素 要素组成 点 交叉节点 公路交叉口、航道交叉口、铁路交叉点等 换乘节点 火车站、公路客运站、飞机场等交通枢纽 边 公路路线、铁路路线、水运航道、飞机航线、表示综合交通枢纽换乘关系的虚拟线段等 
下载: 导出CSV
表 2 客运出行基础费用验证
Table 2. Verification of passenger travel basic costs
运输方式 起讫点 里程/km 实际费用/元 计算费用/元 费用误差/% 公路 哈尔滨—齐齐哈尔 329 80.50 82.25 2.13 哈尔滨-绥化 458 112.00 114.50 2.18 哈尔滨—大庆 173 43.50 43.25 0.58 普通铁路 哈尔滨—绥化 135 19.50 19.78 1.44 绥化—齐齐哈尔 430 62.50 59.58 4.67 哈尔滨—齐齐哈尔 292 43.50 41.38 4.87 高速铁路 哈尔滨—齐齐哈尔 325 98.00 100.75 2.81 哈尔滨—北京 1 231 550.50 543.61 1.25 哈尔滨—郑州 1 843 799.00 813.87 1.86
下载: 导出CSV
表 3 干线公路特征路段客流预测结果
Table 3. Forecast results of passenger flow at characteristic sections of trunk highway
路段名称 公路等级 其他运输方式伴行情况 2017年客流量/(人次·d-1) 2019年客流量/(人次·d-1) 预测结果 本文方法预测客流量/(人次·d-1) 预测误差/% 传统四阶段法预测客流量/(人次·d-1) 预测误差/% 国道黑大公路(G202)哈尔滨至兰西段 一级公路 现存铁路伴行线 20 661 21 203 21 873 3.16 23 519 10.92 绥满高速(G10)哈尔滨段至肇东段 高速公路 现存铁路伴行线 28 322 36 398 33 806 -7.12 33 898 -6.87 鹤哈高速(G1111)哈尔滨至绥化段 高速公路 现存铁路伴行线 24 657 25 517 26 413 3.51 28 649 12.27 双嫩高速(G4512)齐齐哈尔段 高速公路 现存铁路伴行线 13 817 13 406 14 108 5.24 15 816 17.98 绥满高速(G10)阿城至尚志段 高速公路 现存铁路伴行线 14 786 15 378 15 976 3.89 17 130 11.39 国道绥满公路(G301)肇东至向阳段 一级公路 无其他运输方式伴行 22 361 23 821 25 112 5.42 24 836 4.26 国道三莫公路(G333)依安界至讷河段 二级公路 无其他运输方式伴行 9 118 9 671 10 285 6.35 10 303 6.54 哈尔滨绕城高速(G1001)朝阳互通—瓦盆窑互通 高速公路 无其他运输方式伴行 26 793 30 033 28 937 -3.65 28 176 -6.18 京哈高速(G1)省界至双城段 高速公路 无其他运输方式伴行 23 679 24 247 25 809 6.44 26 083 7.57
下载: 导出CSV
表 4 新增伴行线路后干线公路特征路段客流预测结果
Table 4. Forecast results of passenger flow in characteristic sections of trunk highway after adding new accompanying lines
路段名称 等级 其他运输方式伴行情况 2017年客流量/(人次·d-1) 预测结果 本文方法未来年客流量/(人次·d-1) 增长率/% 传统四阶段法未来年客流量/(人次·d-1) 增长率/% 机场路(S102) 一级公路 无其他运输方式伴行 18 926 22 179 17.19 21 693 14.62 国道绥满公路(G301)肇东至向阳段 一级公路 无其他运输方式伴行 22 361 26 174 17.05 25 696 14.91 国道黑大公路(G202)哈尔滨至兰西段 一级公路 现状存在铁路伴行线 20 661 22 968 11.17 24 165 16.96 绥满高速(G10)哈尔滨段至肇东段 高速公路 现状存在铁路伴行线 28 322 34 977 23.50 35 496 25.33 鹤哈高速(G1111)哈尔滨至绥化段 高速公路 现状存在铁路伴行线 24 657 28 117 14.03 30 210 22.52 国道黑大公路(G202)明水至拜泉段 一级公路 新增普通铁路伴行线 15 723 14 973 -4.77 18 291 16.33 绥满高速(G10)林甸至齐齐哈尔段 高速公路 新增高速铁路伴行线 18 122 15 962 -11.92 21 429 18.25 哈肇公路(G102)木兰至通河段 二级公路 新增水运伴行线 8 049 8 798 9.31 9 582 19.05 哈同高速(G1011)方正段 高速公路 新增水运伴行线 22 571 24 556 8.79 25 757 14.12 国道明沈公路(G203)望奎至绥望界 二级公路 新增普通铁路伴行线 9 518 9 893 3.94 11295 18.67
下载: 导出CSV
-
[1] 张宗博, 谢君平, 马金麟. 江苏省徐州市域公路交通发展现状及其需求预测[J]. 江苏师范大学学报(自然科学版), 2016, 34(4): 51-54. https://www.cnki.com.cn/Article/CJFDTOTAL-XZSX201604011.htmZHANG Zong-bo, XIE Jun-ping, MA Jin-lin. Development status and demand forecast of highway traffic in Xuzhou, Jiangsu Province[J]. Journal of Jiangsu Normal University (Natural Science Edition), 2016, 34(4): 51-54. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-XZSX201604011.htm [2] ZHONG M, HANSON B L. GIS-based travel demand modeling for estimating traffic on low-class roads[J]. Transportation Planning and Technology, 2009, 32(5): 423-439. doi: 10.1080/03081060903257053 [3] KRYLATOV A Y, ZAKHAROV V V, MALYGIN I G. Competitive traffic assignment in road networks[J]. Transport and Telecommunication Journal, 2016, 17(3): 212-221. doi: 10.1515/ttj-2016-0019 [4] ALVES M A C, CORDEIRO R L F. Effective and unburdensome forecast of highway traffic flow with adaptive computing[J]. Knowledge-Based Systems, 2021, 212: 106603. doi: 10.1016/j.knosys.2020.106603 [5] KOLIDAKIS S, BOTZORIS G, PROFILLIDIS V, et al. Road traffic forecasting—a hybrid approach combining artificial neural network with singular spectrum analysis[J]. Economic Analysis and Policy, 2019, 64: 159-171. doi: 10.1016/j.eap.2019.08.002 [6] LI Run-mei, HUANG Yin-feng, WANG Jian. Long-term traffic volume prediction based on k-means Gaussian interval type-2 fuzzy sets[J]. IEEE/CAA Journal of Automatica Sinica, 2019, 6(6): 1344-1351. [7] LYU Y S, DUAN Y J, KANG W W, et al. Traffic flow prediction with big data: a deep learning approach[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(2): 865-873. [8] LIU Can-qi, HU Dong. A forecasting method of trip generation based on land classification combined with OD matrix estimation[C]//IET. 7th Advanced Forum on Transportation of China: London: IET, 2011: 1-4. [9] WU Y K, TAN H C, QIN L Q, et al. A hybrid deep learning based traffic flow prediction method and its under standing[J]. Transportation Research Part C: Emerging Technologies, 2018, 90: 166-180. doi: 10.1016/j.trc.2018.03.001 [10] 聂佩林, 龚峻峰. 一种路网交通流参数的融合预测方法[J]. 交通运输系统工程与信息, 2015, 15(6): 39-45. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201506007.htmNIE Pei-lin, GONG Jun-feng. A combined traffic network flow prediction method[J]. Journal of Transportation Systems Engineering and Information Technology, 2015, 15(6): 39-45. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201506007.htm [11] 葛梦雪, 宋国华, 王芃森, 等. 基于手机应用软件测算OD数据的区域交通需求预测[J]. 公路交通科技, 2019, 36(5): 152-158. https://www.cnki.com.cn/Article/CJFDTOTAL-GLJK201905021.htmGE Meng-xue, SONG Guo-hua, WANG Peng-sen, et al. Regional traffic demand forecasting based on OD data calculated by mobile phone application software[J]. Journal of Highway and Transportation Research and Development, 2019, 36(5): 152-158. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GLJK201905021.htm [12] 李双宝, 邱万军. 公路沿线机场集疏交通量预测方法研究[J]. 公路, 2020, 65(2): 177-182. https://www.cnki.com.cn/Article/CJFDTOTAL-GLGL202002038.htmLI Shuang-bao, QIU Wan-jun. Research on the prediction method of airport traffic volume along highway[J]. Highway, 2020, 65(2): 177-182. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GLGL202002038.htm [13] 裴玉龙, 徐慧智. 基于城市区位势能的路网密度规划方法[J]. 中国公路学报, 2007, 20(3): 81-85. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL200703014.htmPEI Yu-long, XU Hui-zhi. Planning method of road network density based on urban area position potential energy[J]. China Journal of Highway and Transport, 2007, 20(3): 81-85. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL200703014.htm [14] 傅成红, 张阳. 基于参数优化的SVR城市群交通需求预测方法[J]. 系统工程, 2016, 34(2): 114-120. https://www.cnki.com.cn/Article/CJFDTOTAL-GCXT201602018.htmFU Cheng-hong, ZHANG Yang. An improved SVR algorithm based on the nuclear parameter optimization for traffic demand forecasting of urban agglomeration[J]. Systems Engineering, 2016, 34(2): 114-120. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GCXT201602018.htm [15] 袁华, 陈泽濠. 基于时间卷积神经网络的短时交通流预测算法[J]. 华南理工大学学报(自然科学版), 2020, 48(11): 107-113, 122. https://www.cnki.com.cn/Article/CJFDTOTAL-HNLG202011013.htmYUAN Hua, CHEN Ze-hao. Short-term traffic flow prediction based on temporal convolutional networks[J]. Journal of South China University of Technology (Natural Science Edition), 2020, 48(11): 107-113, 122. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-HNLG202011013.htm [16] 高华睿, 郝龙, 王明明, 等. 基于Att-Bi-LSTM的高速公路短时交通流预测研究[J]. 武汉理工大学学报, 2020, 42(9): 59-64. https://www.cnki.com.cn/Article/CJFDTOTAL-WHGY202009008.htmGAO Hua-rui, HAO Long, WANG Ming-ming, et al. Research on short-term traffic flow forecast of expressway based on Att-Bi-LSTM[J]. Journal of Wuhan University of Technology, 2020, 42(9): 59-64. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-WHGY202009008.htm [17] 温惠英, 张东冉, 陆思园. GA-LSTM模型在高速公路交通流预测中的应用[J]. 哈尔滨工业大学学报, 2019, 51(9): 81-87, 95. https://www.cnki.com.cn/Article/CJFDTOTAL-HEBX201909012.htmWEN Hui-ying, ZHANG Dong-ran, LU Si-yuan. Application of GA-LSTM model in highway traffic flow prediction[J]. Journal of Harbin Institute of Technology, 2019, 51(9): 81-87, 95. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-HEBX201909012.htm [18] 李桃迎, 王婷, 张羽琪. 考虑多特征的高速公路交通流预测模型[J]. 交通运输系统工程与信息, 2021, 21(3): 101-111. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202103013.htmLI Tao-ying, WANG Ting, ZHANG Yu-qi. Highway traffic flow prediction model with multi-features[J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(3): 101-111. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202103013.htm [19] 徐凤, 朱金福, 杨文东. 复杂网络在交通运输网络中的应用研究综述[J]. 复杂系统与复杂性科学, 2013, 10(1): 18-25. https://www.cnki.com.cn/Article/CJFDTOTAL-FZXT201301002.htmXU Feng, ZHU Jin-fu, YANG Wen-dong. The complex networks' applications in transportation networks: a survey[J]. Complex Systems and Complexity Science, 2013, 10(1): 18-25. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-FZXT201301002.htm [20] 李成兵. 城市群交通运输系统供需非均衡模型研究[J]. 交通运输系统工程与信息, 2017, 17(1): 47-53. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201701009.htmLI Cheng-bing. Supply and demand non-equilibrium model of city agglomeration transportation system[J]. Journal of Transportation Systems Engineering and Information Technology, 2017, 17(1): 47-53. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201701009.htm [21] 陈晓明, 李引珍, 沈强, 等. 基于双层复杂网络的城市交通网络协同优化方法[J]. 计算机应用, 2019, 39(10): 3079-3087. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJY201910047.htmCHEN Xiao-ming, LI Yin-zhen, SHEN Qiang, et al. Urban traffic networks collaborative optimization method based on two-layered complex networks[J]. Journal of Computer Applications, 2019, 39(10): 3079-3087. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JSJY201910047.htm [22] 陈峰林. 多模式客运交通综合阻抗模型研究[J]. 江苏科技信息, 2017, 4(13): 34-35. https://www.cnki.com.cn/Article/CJFDTOTAL-KJXY201713014.htmCHEN Feng-lin. Study on integrated impedance model of multi-mode passenger traffic[J]. Jiangsu Science and Technology Information, 2017, 4(13): 34-35. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-KJXY201713014.htm [23] 王秋平, 王思颖, 任歆雨, 等. 基于城市交通网络的历史街区单向交通组织优化[J]. 西安建筑科技大学学报(自然科学版), 2014, 46(3): 342-347. https://www.cnki.com.cn/Article/CJFDTOTAL-XAJZ201403007.htmWANG Qiu-ping, WANG Si-ying, REN Xin-yu, et al. One-way traffic organization optimization of the historic district based on urban traffic network[J]. Journal of Xi'an University of Architecture and Technology (Natural Science Edition), 2014, 46(3): 342-347. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-XAJZ201403007.htm [24] 刘攀, 刘志远, 田琼, 等. 城市多模式交通供需平衡机理与仿真系统研究[J]. 中国基础科学, 2021, 23(1): 57-66. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGJB202101008.htmLIU Pan, LIU Zhi-yuan, TIAN Qiong, et al. Study on supply-demand balance mechanism and simulation system of urban multi-modal transportation[J]. China Basic Science, 2021, 23(1): 57-66. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZGJB202101008.htm [25] 公维勇, 高建杰, 焦海贤. 城市交通空间需求与交通网络双均衡研究[J]. 重庆交通大学学报(自然科学版), 2011, 30(3): 429-431, 444. https://www.cnki.com.cn/Article/CJFDTOTAL-CQJT201103018.htmGONG Wei-yong, GAO Jian-jie, JIAO Hai-xian. Study on the Bi-directional equalization between urban traffic spatial demands and networks[J]. Journal of Chongqing Jiaotong University (Natural Science Edition), 2011, 30(3): 429-431, 444. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-CQJT201103018.htm [26] 王炜, 华雪东, 郑永涛. 综合交通系统"多网合一"交通分析模型与算法[J]. 交通运输工程学报, 2021, 21(2): 159-172. https://www.cnki.com.cn/Article/CJFDTOTAL-JYGC202102017.htmWANG Wei, HUA Xue-dong, ZHENG Yong-tao. Multi-network integrated traffic analysis model and algorithm of comprehensive transportation system[J]. Journal of Traffic and Transportation Engineering, 2021, 21(2): 159-172. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JYGC202102017.htm [27] 张锐, 姚恩建, 杨扬. 多方式条件下城市交通分配研究[J]. 交通运输系统工程与信息, 2014, 14(6): 107-112, 170. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201406017.htmZHANG Rui, YAO En-jian, YANG Yang. Multimodal urban traffic assignment analysis[J]. Journal of Transportation Systems Engineering and Information Technology, 2014, 14(6): 107-112, 170. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201406017.htm [28] 徐君翔, 郭静妮, 张锦. 区域多枢纽单分配混合轴辐式综合交通网络优化及实证[J]. 中国管理科学, 2019, DOI: 10.16381/j.cnki.issn1003-207x.2019.1911.XU Jun-xiang, GUO Jing-ni, ZHANG Jin. Optimization and demonstration of regional mixed hub and spoke comprehensive transportation network[J]. Chinese Journal of Management Science, 2019, DOI: 10.16381/j.cnki.issn1003-207x.2019.1911.(inChinese) [29] 王世广, 于德新, 王树兴, 等. 基于改进度的城市路网元素连接特性[J]. 交通运输工程学报, 2018, 18(2): 101-110. https://www.cnki.com.cn/Article/CJFDTOTAL-JYGC201802014.htmWANG Shi-guang, YU De-xin, WANG Shu-xing, et al. Connectivity characteristics of urban road network elements based on improved degree[J]. Journal of Traffic and Transportation Engineering, 2018, 18(2): 101-110. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JYGC201802014.htm [30] 何南, 李季涛. 考虑运输方式间影响关系的公路客运交通需求预测[J]. 公路交通科技, 2017, 34(7): 153-158. https://www.cnki.com.cn/Article/CJFDTOTAL-GLJK201707021.htmHE Nan, LI Ji-tao. Highway passenger transport demand forecasting considering relationship among transport modes[J]. Journal of Highway and Transportation Research and Development, 2017, 34(7): 153-158. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GLJK201707021.htm [31] 张翔. 基于SUE客流分配的城市轨道交通可达性研究[D]. 成都: 西南交通大学, 2019.ZHANG Xiang. Research on accessibility of urban rail transit based on SUE passenger flow assignment[D]. Chengdu: Southwest Jiaotong University, 2019. (in Chinese) [32] 何宇强, 毛保华, 陈团生, 等. 高速客运专线客流分担率模型及其应用研究[J]. 铁道学报, 2006, 28(3): 18-21. https://www.cnki.com.cn/Article/CJFDTOTAL-TDXB200603003.htmHE Yu-qiang, MAO Bao-hua, CHEN Tuan-sheng, et al. The mode share model of the high-speed passenger railway line and its application[J]. Journal of The China Railway Society, 2006, 28(3): 18-21. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-TDXB200603003.htm -
点击查看大图
图(12) / 表(4)
计量
- 文章访问数: 621
- HTML全文浏览量: 148
- PDF下载量: 208
- 被引次数: 0
