基于全过程的偶发性拥堵消散时间预测模型

doi:10.3969/j.issn.1007-7375.2022.03.019

工业工程 ›› 2022, Vol. 25 ›› Issue (3): 157-163.doi: 10.3969/j.issn.1007-7375.2022.03.019

基于全过程的偶发性拥堵消散时间预测模型

徐韬^1,2, 祝烨², 谢晓忠², 晏秋萍², 程龙春²

1. 重庆交通大学交通运输学院，重庆 400074;
2. 重庆市市政设计研究院有限公司，重庆 400020

收稿日期:2021-02-26 发布日期:2022-07-06
作者简介:徐韬(1992—)，男，重庆市人，中级工程师，博士研究生，主要研究方向为交通运输规划与管理
基金资助:
重庆市科研创新资助项目(CYS15188)

A Prediction Model of Occasional Congestion Dissipation Time Based on the Whole Process

XU Tao^1,2, ZHU Ye², XIE Xiaozhong², YAN Qiuping², CHENG Longchun²

1. Chongqing Jiaotong University College of Traffic &Transportation, Chongqing 400074, China;
2. Chongqing Municipal Design and Research Institute Limited Company, Chongqing 400020, China

Received:2021-02-26 Published:2022-07-06

摘要/Abstract

摘要： 为减少偶发性交通拥堵消散时间预测误差，基于事故全过程将拥堵消散时间分为驻留时间、处置时间及恢复时间，从驾驶员性格特征、事故等级特征值、初始速度建立驻留时间和处置时间回归模型，利用线性递减时变权重及速度限制改进标准粒子群算法优化RBF神经网络权重，以TransModeler仿真数据及实测数据为训练样本，建立偶发拥堵恢复时间RBF神经网络模型。仿真结果表明，模型平均绝对误差为245.3 s，其中改进PSO-RBF网络对恢复时间预测相对误差为11.2%，均方根误差为102.3，平均相对误差较单一RBF网络、标准PSO-RBF网络分别下降38.1%、23.8%。

关键词: 交通工程, 全过程, 消散时间, 神经网络, 粒子群优化

Abstract: In order to reduce the prediction error of occasional traffic congestion dissipation time, based on the whole process of the accident, the congestion dissipation time is divided into dwell time, disposal time and recovery time, and the regression models of dwell time and disposal time are established from the driver's personality characteristics, accident grade characteristic value and initial speed. The weight of RBF neural network is optimized by using linear decreasing time-varying weight and speed limiting improved standard particle swarm optimization algorithm. The RBF neural network model of occasional congestion recovery time is established by taking Transmodeler simulation data and measured data as training samples. The simulation results show that the average absolute error of the model is 245.3 s. The relative error of improved PSO-RBF network for prediction of recovery time is 11.2%, the root mean square error is 102.3, the average relative error is 38.1% and 23.8% lower than that of single RBF network and standard PSO-RBF network respectively.

Key words: traffic engineering, whole process, dissipation time, neural network, particle swarm optimization

中图分类号:

U491

徐韬, 祝烨, 谢晓忠, 晏秋萍, 程龙春. 基于全过程的偶发性拥堵消散时间预测模型[J]. 工业工程, 2022, 25(3): 157-163.

XU Tao, ZHU Ye, XIE Xiaozhong, YAN Qiuping, CHENG Longchun. A Prediction Model of Occasional Congestion Dissipation Time Based on the Whole Process[J]. Industrial Engineering Journal, 2022, 25(3): 157-163.

参考文献

[1] 崔德冠. 基于公交车GPS数据的城市道路偶发性拥堵检测与系统实现[D]. 重庆: 重庆大学, 2015.
CUI Deguan. The detection and system implementation of urban road contingency jam based on bus GPS data [D]. Chongqing: Chongqing University, 2015.
[2] 周映雪, 杨小宝, 环梅, 等. 基于生存分析的城市道路交通拥堵持续时间研究[J]. 应用数学和力学, 2013, 34(1): 98-106
ZHOU Yingxue, YANG Xiaobao, HUAN Mei, et al. Survival analysis approach for estimating urban traffic congestion duration[J]. Applied Mathematics and Mechanics, 2013, 34(1): 98-106
[3] 吴义虎, 李意芬, 喻伟, 等. 基于元胞自动机的城市道路偶发性拥堵交通行为模拟[J]. 交通科学与工程, 2014, 30(2): 72-78
WU Yihu, LI Yifen, YU Wei, et al. A simulation of the traffic behavior of the propagation of urban coincidental traffic jams based on the cellular automata model[J]. Traffic Science and Engineering, 2014, 30(2): 72-78
[4] 秦韬. 城市道路偶发性局部拥堵快速识别办法研究[D]. 长沙: 长沙理工大学, 2014.
QIN Tao. Research on quickly recognition ways of the urban road non-recurrent local congestion [D]. Changsha: Changsha University of Technology, 2014.
[5] 李狄. 城市偶发性局部拥堵协调控制策略研究[D]. 长沙: 长沙理工大学, 2014.
LI di. Research of coordinated control strategy on city traffic occasional congestion [D]. Changsha: Changsha University of Technology, 2014.
[6] MALERCZYK J, LERCH S, TIBKEN B, et al. Impact of intelligent agents on the avoidance of spontaneous traffic jams on two-lane motorways[J]. MATEC Web of Conferences, 2020, 308(9): 05003
[7] COLD-RAVNKILDE S M, JACOBSEN K L. Disentangling the security traffic jam in the Sahel: constitutive effects of contemporary interventionism[J]. International Affairs, 2020, 96(4): 855-874
[8] SUDATTA M, ALEXEY P, MICHAEL C. Region-wide congestion prediction and control using deep learning[J]. Transportation Research, 2020, 116(7): 102624.1-102624.21
[9] ABEER A H, ZIAD A, TIMOTHY M, et al. Novel Congestion-estimation and routability-prediction methods based on machine learning for modern FPGAs[J]. ACM Transactions On Reconfigurable Technology and Systems, 2019, 3(12): 16.1-16.25
[10] KOBAYASHI H, KITANO T, OKAMOTO M, et al. MAGONIA (DPB: distributed processing base) applied to a traffic congestion prediction and signal control system[J]. NTT Technical Review, 2016, 14(10): 1-4
[11] 管硕. 基于SVM和K-均值聚类的RBF神经网络短时交通流预测[D]. 青岛: 青岛大学, 2015.
GUAN Shuo. Short term traffic flow prediction of RBF neural network based on SVM and K-means clustering [D]. Qingdao: Qingdao University, 2015.
[12] 章国勇, 伍永刚, 顾巍. 基于精英学习的量子行为粒子群算法[J]. 控制与决策, 2013, 28(9): 1341-1348
ZHANG Guoyong, WU Yonggang, GU Wei. Quantum-behaved particle swarm optimization algorithm based on elitist learning[J]. Control and Decision, 2013, 28(9): 1341-1348
[13] 朱震曙, 薄煜明, 吴盘龙, 等. Short-term power load forecasting model based on QPSO-RBFNN[J]. 南京理工大学学报, 2016, 40(1): 97-101
ZHU Zhenshu, BO Yuming, WU Panlong, et al. Short term power load forecasting model based on QPSO-RBFNN[J]. Journal of Nanjing University of Science and Technology, 2016, 40(1): 97-101
[14] LIU J, Sun J, XU W B. Improving quantum-behaved particle swarm optimization by simulated annealing[J]. Computational Intelligence and Bioinformatics, 2006, 4115: 130-136
[15] CHEN D B, WANG J T. An improved group search optimizer with operation of quantum-behaved swarm and its application[J]. Applied Soft Computing, 2012, 12(2): 712-725
[16] SUN J, FANG W, PALADE V, et al. Quantum-behaved particle swarm optimization with Gaussian distributed local attractor point[J]. Applied Mathematics and Computation, 2011, 218(7): 3763-3775

基于全过程的偶发性拥堵消散时间预测模型

A Prediction Model of Occasional Congestion Dissipation Time Based on the Whole Process

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	周康渠, 张朝武, 屈清, 唐蔗湛. M型变速箱总成密封质量预测方法研究[J]. 工业工程, 2022, 25(2): 22-27,41.
[2]	周昊飞. 基于GRU神经网络的自相关过程残差控制图[J]. 工业工程, 2022, 25(1): 108-113.
[3]	卢皎, 禹建丽, 黄春雷, 陈洪根. 基于卷积神经网络的ZPW-2000R轨道电路智能故障诊断方法[J]. 工业工程, 2021, 24(4): 127-133.
[4]	樊博, 马筱栎, 雷小诗, 马新露. 基于支持向量机的高速公路事故实时风险预测[J]. 工业工程, 2021, 24(4): 143-149.
[5]	王玖河, 刘欢, 高辉. 基于粗糙PSO-BP神经网络的冷链物流服务商选择研究[J]. 工业工程, 2021, 24(2): 10-18.
[6]	唐红涛, 方博, 高晓灵, 李香怡, 殷伟铭. 基于GSA-GA神经网络的铸造企业订单准入评价研究[J]. 工业工程, 2020, 23(4): 121-130.
[7]	王海燕, 侯琳娜. 基于随机森林的统计控制图模式识别研究[J]. 工业工程, 2019, 22(5): 118-125.
[8]	曹涛涛, 蒋阳升, 赵斌, 姚志洪, 谭宇. 考虑多交叉口相互影响的干道相位差仿真优化研究[J]. 工业工程, 2018, 21(6): 40-45.
[9]	王逸, 姚志洪, 蒋阳升, 赵斌, 谭宇. 基于自适应遗传算法的双环信号配时优化模型[J]. 工业工程, 2018, 21(5): 72-80.
[10]	李彦瑾, 罗霞, 王莹. 考虑多节点拥堵的城市道路网级联失效仿真[J]. 工业工程, 2018, 21(4): 1-7.
[11]	姚志洪, 蒋阳升, 王逸. 车路协同环境下自适应信号配时优化模型[J]. 工业工程, 2018, 21(4): 8-14,33.
[12]	夏蓓鑫，陈鑫，魏鑫. 基于数据驱动仿真的两设备系统元模型[J]. 工业工程, 2016, 19(5): 51-57.
[13]	刘炳辉，江小云. 切削参数的两阶段优化系统[J]. 工业工程, 2014, 17(6): 30-35.
[14]	庞金茹1，李国威2,3，江志斌1, 耿娜1. 报废汽车回收再制造企业特征属性与生产性服务需求匹配预测[J]. 工业工程, 2014, 17(3): 114-120.
[15]	温海骏1,2, 侯世旺2. 基于维信息共享的粒子群优化算法在作业车间调度中的应用[J]. 工业工程, 2014, 17(1): 30-36.