基于公路通行数据的节假日山地景区运力适配方法

doi:10.13229/j.cnki.jdxbgxb.20240692

吉林大学学报(工学版) ›› 2025, Vol. 55 ›› Issue (5): 1576-1587.doi: 10.13229/j.cnki.jdxbgxb.20240692

• 交通运输工程·土木工程 • 上一篇下一篇

基于公路通行数据的节假日山地景区运力适配方法

闫晟煜¹(),温福华¹,武瑾¹,郑毅²(),郝时杰¹,尤文博¹

^1.长安大学汽车学院，西安 710018
^2.云南省交通投资建设集团有限公司大数据资源开发中心，昆明 650032

收稿日期:2024-06-21 出版日期:2025-05-01 发布日期:2025-07-18
通讯作者: 郑毅 E-mail:Leo9574@163.com;11403297@qq.com
作者简介:闫晟煜（1987-），男，副教授，博士.研究方向：公路运输规划，智慧交通工程.E-mail：Leo9574@163.com
基金资助:
国家重点研发计划项目(2023YFB3209803);长安大学中央高校基本科研业务费专项资金项目(300102224206);陕西省教育厅科学研究计划项目(23JK0335);陕西省重点研发计划项目(2025CY-YBXM-064)

Algorithm for adapting transportation capacity of mountainous scenic areas in festival based on highway traffic data

Sheng-yu YAN¹(),Fu-hua WEN¹,Jin WU¹,Yi ZHENG²(),Shi-jie HAO¹,Wen-bo YOU¹

^1.School of Automobile，Chang'an University，Xi'an 710018，China
^2.Development of Big Data Resource，Yunnan Communications Investment & Construction Group Co. ，Ltd. ，Kunming 650032，China

Received:2024-06-21 Online:2025-05-01 Published:2025-07-18
Contact: Yi ZHENG E-mail:Leo9574@163.com;11403297@qq.com

摘要/Abstract

摘要：

为确定节假日期间山地景区承运旅客所需的运力水平，提出了基于短时客流预测的景区运力适配方法。基于公路通行数据，将车流量换算为客流量，建立用于短时客流预测的CNN-LSTM混合模型；运用高斯函数拟合客流预测的离散数据，采用广度搜索算法，得到适配客流曲线的发车班次；确定山地景区车辆运营的合理约束条件，结合发车班次、客车核载人数、单程行驶时间等关键参数，运用逆差函数构建运力适配模型；选取金丝峡景区进行模型验证与实例分析。结果表明：CNN-LSTM混合模型可有效预测山地景区短时客流量，在15 min的时间粒度下，模型的R²可达到0.92；运力适配模型相较于传统“客满即走”的调度模式，运力需求从57辆降至28辆，有效降低了车队规模。研究可用于山地景区客流短时预测和节假日景区运力需求的精确测算。

关键词: 交通工程, 收费数据, 景区运力适配, 短时客流预测, 循环神经网络, 广度搜索算法

Abstract:

To determine the transport capacity by mountain scenic spots to carry tourists during holidays， an adaptation method of scenic spot transport capacity based on short-term passenger flow forecast was proposed. Based on highway traffic data， the traffic flow was converted into passenger flow， and a CNN-LSTM hybrid model for short-term passenger flow prediction was proposed； Gaussian function was used to fit the discrete data of passenger flow forecast， and breadth-first search algorithm was used to obtain the departure frequency that fitted the passenger flow curve； The paper determined the reasonable constraint conditions of vehicle operation in mountain scenic spots， considering the key parameters such as departure frequency， the number of passengers carrying capacity and traveling tiem of the trip， a capacity adaptation model by deficit function was proposed. Taking Jinsixia scenic area as a case study， the models proposed were verified. The results show that the CNN-LSTM hybrid model can effectively predict the short-term passenger flow in mountain scenic spots， and the R² of the model can reach 0.92 at the time granularity of 15 min. Compared with the traditional "full-passenger-ready-to-go" scheduling mode， the capacity adaptation model reduces the capacity demand from 57 to 28， effectively reducing the fleet supply. The research will be beneficial for short-term prediction of passenger flow in mountain scenic spots and accurate calculation of transportation capacity demand in holidays.

Key words: traffic engineering, toll collection data, adaptation of transportation capacity for scenic area, short-time passenger flow forecast, recurrent neural network, breadth-first search algorithm

中图分类号:

U492.2

闫晟煜,温福华,武瑾,郑毅,郝时杰,尤文博. 基于公路通行数据的节假日山地景区运力适配方法[J]. 吉林大学学报(工学版), 2025, 55(5): 1576-1587.

Sheng-yu YAN,Fu-hua WEN,Jin WU,Yi ZHENG,Shi-jie HAO,Wen-bo YOU. Algorithm for adapting transportation capacity of mountainous scenic areas in festival based on highway traffic data[J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(5): 1576-1587.

图/表 17

图1

表1

图2

表2

图3

图4

图5

图6

图7

表3

3种模型预测效果对比"

客流预测模型	预测效果评价指标
客流预测模型	$R M S E$ /%	$R 2$
CNN	34.64	0.14
LSTM	20.14	0.34
CNN-LSTM	18.86	0.46

表3

图8

表4

LSTM与CNN-LSTM预测情况对比"

模型	$R M S E$ /%	$R 2$	程序运行时间/s
LSTM	32.01	0.86	120
CNN-LSTM	29.12	0.92	146

表4

图9

图10

图11

图12

图13

参考文献 26

[1]	孙九霞. 国内旅游业更新升级的新动向与新挑战[J]. 人民论坛, 2024(7): 94-98.
	Sun Jiu-xia. New trends and challenges in the renewal and upgrading of the domestic tourism industry[J]. People's Tribune, 2024(7): 94-98.
[2]	闫晟煜, 王钊龙, 武瑾, 等.省域高速公路网车辆碳排放量测算方法[J]. 中国环境科学, 2024, 44(12): 7095-7104.
	Yan Sheng-yu, Wang Zhao-long, Wu Jin, et al. Estimation model of vehicle carbon emission for provincial expressway networks[J]. China Environmental Science, 2024, 44(12): 7095-7104.
[3]	Song H Y, Richard T Q, Jinah P. Review of research on tourism demand forecasting: launching the annals of tourism research curated collection on tourism demand forecasting[J]. Journals of Tourism Research, 2019, 75: 338-362.
[4]	Hu Y C. Predicting foreign tourists for the tourism industry using soft computing-based Grey-Markov models[J]. Sustainability, 2017, 9(7): 1-12.
[5]	Li S W, Chen T, Wang L, et al. Effective tourist volume forecasting supported by PCA and improved BPNN using Baidu index[J]. Tourism Management, 2018, 68(10): 116-126.
[6]	Sun S L, Wei Y J, Tsui K L, et al. Forecasting tourist arrivals with machine learning and internet search index[J]. Tourism Management, 2019, 70(2): 1-10.
[7]	Bi J W, Liu Y, Li H, et al. Daily tourism volume forecasting for tourist attractions[J]. Annals of Tourism Research, 2020, 83(3): No.102923.
[8]	Bi J W, Li C X, Xu H, et al. Forecasting daily tourism demand for tourist attractions with big data: an ensemble deep learning method[J]. Journal of Travel Research, 2022, 61(8): 1719-1737.
[9]	Han W, Li Y, Li Y, et al. A deep learning model based on multi-source data for daily tourist volume forecasting[J]. Current Issues in Tourism, 2024, 27(5): 768-786.
[10]	廖治学, 戈鹏, 任佩瑜, 等. 基于AB@G集成模型的九寨沟景区游客量预测研究[J].旅游学刊, 2013, 28(4): 88-93.
	Liao Zhi-xue, Ge Peng, Ren Pei-yu, et al. Research on prediction of tourists quantity in Jiuzhai Valley based on AB@G integration model[J]. Tourism Science, 2013, 28 (4): 88-93.
[11]	Mohd A, Wu J Z, Chakrabortty R K, et al. Attention-based STL-BiLSTM network to forecast tourist arrival[J]. Processes, 2021, 9(10): No.09101759.
[12]	《中国公路学报》编辑部. 中国公路交通学术研究综述2012[J].中国公路学报, 2012, 25(3): 2-50.
	Editorial Department of China Journal of Highway and Transport. An academic research summary on china highway and transport: 2012[J]. China Journal of Highway and Transport, 2012, 25(3): 2-50.
[13]	Ceder A, Helman I S. Deficit function bus scheduling with deadheading trip insertions for fleet size reduction[J]. Transportation Science, 1981, 11: 338-363.
[14]	刘涛, 尤海林. 基于人机协同决策的运输调度优化研究[J]. 交通运输系统工程与信息, 2024, 24(2): 136-148.
	Liu Tao, You Hai-lin. Human-machine collaborative decision-making for transportation scheduling optimization [J].Journal of Transportation Systems Engineering and Information Technology, 2024, 24(2): 136-148.
[15]	闫晟煜, 赵佳琪, 尤文博, 等. 高速公路货车差异化通行费折扣的双层规划模型[J/OL]. 清华大学学报:自然科学版,2025,
	Yan Sheng-yu, Zhao Jia-qi, You Wen-bo, et al. Bi-level programming model for differential toll discounts for expressway trucks[J]. Journal of Tsinghua University (Science and Technology), 2025,
[16]	董强. 基于遗传算法的风景区电瓶摆渡车发车管理[J].佳木斯大学学报: 自然科学版, 2017, 35(3): 488-491.
	Dong Qiang. The bus scheduling based on genetic algorithm[J]. Journal of Jiamusi University (Natural Science Edition), 2017, 35(3): 488-491.
[17]	张建华. 基于实时客流信息的快速公交车辆组合调度优化研究[D]. 成都: 西南交通大学交通运输与物流学院, 2013.
	Zhang Jian-hua. Research on the optimization of combinational scheduling bat based on real-time passenger flow[D]. Chengdu: School of Transportation and Logistics, Southwest Jiaotong University, 2013.
[18]	杨凤满. 基于人工神经网络的交通流预测方法综述[J].公路交通科技, 2020, 37():130-135.
	Yang Feng-man. Review of traffic flow prediction methods based on artificial neural network[J]. Journal of Highway and Transportation Research and Development, 2020, 37(Sup.1): 130-135.
[19]	陈晓雷, 孙永峰, 李策, 等. 基于卷积神经网络和双向长短期记忆的稳定抗噪声滚动轴承故障诊断[J]. 吉林大学学报: 工学版, 2022, 52(2): 296-309.
	Chen Xiao-lei, Sun Yong-feng, Li Ce, et al. Stable anti⁃noise fault diagnosis of rolling bearing based on CNN⁃BiLSTM[J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(2): 296-309.
[20]	Yang D, Chen K R, Yang M N, et al. Urban rail transit passenger flow forecast based on LSTM with enhanced long-term features[J]. IET Intelligent Transport Systems, 2019, 13(10): 1475-1482.
[21]	苏恩杰, 叶飞, 何乔, 等. 基于卷积神经网络-长短期记忆的施工期盾构管片上浮过程预测模型[J]. 同济大学学报: 自然科学版, 2023, 51(9): 1352-1361.
	Su En-jie, Ye Fei, He Qiao, et al. Prediction model of shield segment floating process during construction based on convolutional neural networks and long short-term memory[J]. Journal of Tongji University(Natural Science), 2023, 51(9): 1352-1361.
[22]	戢晓峰, 孔晓丽, 陈方, 等. 基于ETC数据和A-BiLSTM神经网络的高速公路节假日短时交通流预测模型[J]. 交通信息与安全, 2023, 41(3): 166-174.
	Ji Xiao-feng, Kong Xiao-li, Chen Fang, et al. A forecasting model of short-term traffic flow on expressways during holidays based on ETC data and A-BiLSTM neural network models[J]. Journal of Transport Information and Safety, 2023, 41(3): 166-174.
[23]	赵阳阳, 夏亮, 江欣国. 基于经验模态分解与长短时记忆神经网络的短时地铁客流预测模型[J]. 交通运输工程学报, 2020, 20(4): 194-204.
	Zhao Yang-yang, Xia Liang, Jiang Xin-guo. Short-term metro passenger flow predication based on EMD-LSTM[J]. Journal of Traffic and Transportation Engineering, 2020, 20(4): 194-204.
[24]	Cao Z C, Ceder A A. Autonomous shuttle bus service timetabling and vehicle scheduling using skip-stop tactic[J]. Transportation Research Part C: Emerging Technologies, 2019, 102(5): 370-395.
[25]	范厚明, 田攀俊, 吕迎春, 等. 越库配送下考虑时空距离的库门分配与车辆调度优化[J]. 中国管理科学, 2022, 30(2):137-149.
	Fan Hou-ming, Tian Pan-jun, Ying-chun Lyu, et al. Cross-dock door assignment and vehicle routing problem of considering temporal-spatial distance[J]. Chinese Journal of Management Science, 2022, 30(2): 137-149.
[26]	李翠玉, 胡雅梦, 康亚伟, 等. 应用自适应遗传算法的电动汽车充放电协同调度[J]. 吉林大学学报: 工学版, 2022, 52(11): 2508-2513.
	Li Cui-yu, Hu Ya-meng, Kang Ya-wei, et al. Coordination scheduling of electric vehicle charge and discharge using adaptive genetic algorithm[J]. Journal of Jilin University (Engineering and Technology Edition), 2022, 52(11): 2508-2513.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

数据类型	字段名称	字符类型	字段说明	字段用途
高速公路收费数据	入口站代码	Varchar	每个收费站对应的唯一数字ID	精确定位客车驶入或驶出收费站位置及所属的高速公路编号
	出口站代码	Varchar	每个收费站对应的唯一数字ID	精确定位客车驶入或驶出收费站位置及所属的高速公路编号
	入口时间	Datetime	车辆驶入或驶出收费站的时间，精确到秒级	精准确定客车驶入或驶出收费站的时间，可计算全程平均速度
	出口时间	Datetime	车辆驶入或驶出收费站的时间，精确到秒级	精准确定客车驶入或驶出收费站的时间，可计算全程平均速度
	车型	Varchar	核定载客人数范围划分为Ⅰ、Ⅱ、Ⅲ、Ⅳ型	区分客车车型，可分车型计算高速公路客流量
	车牌号	Varchar	数据中识别车辆的唯一标识	追踪行驶轨迹，确定客流来源，标记Ⅲ、Ⅳ客车
国省道交通量观测数据	观测时间段	Datetime	可将观测时间段缩小到短时预测级别	可按每分钟统计国省道分车型车流量
	车型	Varchar	分为小型客车（Ⅰ、Ⅱ型）、大型客车（Ⅲ、Ⅳ型）	区分客车车型，可分车型计算国道、省道客流量
	车流量计数	Int	记录短时时段内各车型车流量	用于推算各车型客流量
	行驶方向	Varchar	标记车辆单向行驶方向	区分客车上行、下行方向

客车车型	核定载客数/人	平均座位数/座	假期平均乘坐人数/人	样本量/个
Ⅰ类	9座及以下	5.22	3.01	466
Ⅱ类	8~19座	12.25	9.20	69
Ⅲ类	20~39座	35.32	29.71	85
Ⅳ类	40座及以上	50.97	42.32	76

基于公路通行数据的节假日山地景区运力适配方法

Algorithm for adapting transportation capacity of mountainous scenic areas in festival based on highway traffic data

RICH HTML

PDF (PC)

摘要/Abstract

引用本文

使用本文

图/表 17

参考文献 26

相关文章 15

Metrics

本文评价

推荐阅读 10

[1]	方华珍,刘立,顾青,肖小凤,孟宇. 基于轨迹预测和极限梯度提升的驾驶意图识别[J]. 吉林大学学报(工学版), 2025, 55(2): 623-630.
[2]	李怀鑫,晏长根,林斌,石玉玲. 黏土-混凝土组合体强度及全过程统计损伤模型[J]. 吉林大学学报(工学版), 2025, 55(1): 245-255.
[3]	姚荣涵,祁文彦,胡宏宇,杜筱婧,乔延峰,王立冰. 考虑公交-合乘车道的多车道元胞自动机模型[J]. 吉林大学学报(工学版), 2025, 55(1): 162-174.
[4]	周荣贵,高沛,李雨璇,周建. 基于轨迹数据的高速公路小客车异常驾驶行为[J]. 吉林大学学报(工学版), 2024, 54(9): 2581-2587.
[5]	许清津,付锐,郭应时,吴付威. 载货汽车弯道侧翻路侧预测方法[J]. 吉林大学学报(工学版), 2024, 54(5): 1302-1310.
[6]	蒲云,徐银,刘海旭,谭一帆. 考虑多车影响的智能网联车跟驰模型[J]. 吉林大学学报(工学版), 2024, 54(5): 1285-1292.
[7]	马庆禄,闫浩,聂振宇,李杨梅. 匝道合流区智能网联车辆协同控制方法[J]. 吉林大学学报(工学版), 2024, 54(5): 1332-1346.
[8]	曹倩,李志慧,陶鹏飞,李海涛,马永建. 面向交通事故检测及预防的异质传感器布设方法[J]. 吉林大学学报(工学版), 2024, 54(4): 969-978.
[9]	张鑫,胡启洲,何君,吴啸宇. 考虑交通梗塞的合流区交通状况诊断[J]. 吉林大学学报(工学版), 2024, 54(2): 478-484.
[10]	张卫华,刘嘉茗,解立鹏,丁恒. 网联混合环境快速路交织区自动驾驶车辆换道模型[J]. 吉林大学学报(工学版), 2024, 54(2): 469-477.
[11]	宋慧,曲大义,王少杰,王韬,杨子奕. 考虑多车响应的网联混行车流跟驰模型及稳态分析[J]. 吉林大学学报(工学版), 2024, 54(11): 3220-3230.
[12]	潘义勇,吴静婷,缪炫烨. 老年驾驶员事故严重程度影响因素时间不稳定性分析[J]. 吉林大学学报(工学版), 2024, 54(10): 2819-2826.
[13]	温惠英,何梓琦,李秋灵,赵胜. 高速公路货车换道冲突预测及其影响因素分析[J]. 吉林大学学报(工学版), 2024, 54(10): 2827-2836.
[14]	岳昊,张琦悦,杨子玉,任孟杰,张旭. 拥堵空间排队的静态交通流分配迭代加权算法[J]. 吉林大学学报(工学版), 2024, 54(1): 136-145.
[15]	杜筱婧,姚荣涵. 智能网联公交车出站强制换道的演化博弈机制[J]. 吉林大学学报(工学版), 2024, 54(1): 124-135.