基于MLE-LM算法估计的交通流断面速度Weibull分布模型

交通运输系统工程与信息 ›› 2018, Vol. 18 ›› Issue (3): 126-132.

基于MLE-LM算法估计的交通流断面速度Weibull分布模型

符锌砂，郑伟，王晓飞^*

华南理工大学土木与交通学院，广州 510641

收稿日期:2018-01-25 修回日期:2018-03-18 出版日期:2018-06-25 发布日期:2018-06-25
作者简介:符锌砂(1955-)，男，湖南长沙人，教授.
基金资助:
国家自然科学基金/National Natural Science Foundation of China(51778242)；广东省交通运输厅科技项目/Science and Technology Project of Guangdong Transportation Department(科技 2014-02-010, 2015-02-004).

Section Velocity Distribution of Traffic Flow Model with Weibull Distribution Based on MLE-LM Algorithm Estimation

FU Xin-sha, ZHENG Wei, WANG Xiao-fei

School of Civil Engineering and Transportation, South China University of Technology, Guangzhou 510641, China

Received:2018-01-25 Revised:2018-03-18 Online:2018-06-25 Published:2018-06-25

摘要/Abstract

摘要：

针对传统断面交通流速度分布假设关系较片面、回归数据不全面和拟合模型不具有普遍性和精确性等问题，本文采用二分K-FCM结合算法对连续收集的大样本交通流数据中速度、交通量和占有率三者进行聚类划分，再利用自主建立的MLE-LM算法拟合运行车速三参数Weibull分布，并将其拟合结果与正态分布和高斯多峰拟合结果对比.该算法模型收敛快，拟合结果精度高，不易收敛于局部极值，且对样本容量的适应能力强.研究结果表明：各交通流状态下高斯多峰非参数估计拟合效果最好，但其自由度最小，即被限制的变量最多，难以反映数据的分布特征；而参数估计中Weibull-3分布拟合结果均比正态分布拟合结果好，且Adj R-square值都大于0.7，故总体认为不同交通流状态下速度分布基本服从Weibull-3分布.

关键词: 交通工程, 断面速度分布, Levenberg Marquardt算法, Weibull分布

Abstract:

For the problems that one-sided hypothetical relations, incomplete regression data and fitting models lacking of universality and accuracy in the traditional velocity distribution of section traffic flow, the paper uses the bisecting K-FCM clustering algorithm to cluster partition the large sample traffic flow data of velocity, flow and occupancy. Then, MLE-LM algorithm model is established to fit three parameters Weibull distribution of section velocity, and compares its fitting results with the normal distribution and multi- peaks gaussian fitting. Such an algorithm model is featured with fast convergence, high precision of fitting results and simple steps of solutions, and it is not easy to converge in local extremum and sample capacity has the strong adaptive capacity. The results show that non-parametric estimation of multi-peaks Gaussian has the best fitting effect, but its degree of freedom is smaller than the parameter estimation. That means the variables is limited, and it is difficult to reflect the distribution characteristics of the expressed data. The fitting results of Weibull-3 distribution are all greater than 0.7, which is better than the normal distribution. The overall results show that the velocity distribution obeys the Weibull-3 distribution in different traffic flow.

Key words: traffic engineering, section velocity distribution, Levenberg Marquardt algorithm, Weibull distribution

中图分类号:

U491.1+12

符锌砂，郑伟，王晓飞. 基于MLE-LM算法估计的交通流断面速度Weibull分布模型[J]. 交通运输系统工程与信息, 2018, 18(3): 126-132.

FU Xin-sha, ZHENG Wei, WANG Xiao-fei. Section Velocity Distribution of Traffic Flow Model with Weibull Distribution Based on MLE-LM Algorithm Estimation[J]. Journal of Transportation Systems Engineering and Information Technology, 2018, 18(3): 126-132.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/abstract/abstract19636.shtml

http://www.tseit.org.cn/CN/Y2018/V18/I3/126

参考文献

[1] LEONG H J W. The distribution and trend of free speeds on two-lane two-way rural highways in New South Wales[C]// Australian Road Research Board (ARRB) Conference, 4th, 1968, Melbourne,1900.

[2] MCLEAN J R. Observed speed distributions and rural road traffic operations[C]// Proc 9th Australian Road Research Board Conference, 1979: 235-244.

[3] HAIGHT F A, MOSHER W W. A practical method for improving the accuracy of vehicular speed distribution measurements[J]. Highway Research Board Bulletin, 1962.

[4] 王祺, 李力, 胡坚明, 等. 不同车头间距下交通流的速度分布[J]. 清华大学学报(自然科学版), 2011(3): 309- 312. [WANG Q, LI L, HU J M, et al. Traffic velocity distributions for different spacings[J]. Journal of Tsinghua University(Science and Technology), 2011(3): 309-312.]

[5] 徐程. 基于高斯混合模型的车辆自由流速度分布 [J]. 公路交通科技, 2012, 29(8): 132-135. [XU C, Distribution of vehicle free flow speeds based on gaussian mixture model[J]. Journal of Highway and Transportation Research and Development, 2012, 29(8): 132-135.]

[6] GLEN H LEMON. Maximum likelihood estimation for the three parameter weibull distribution based on censored samples[J]. Technometrics, 1975, 17(2): 247-254.

[7] 杨谋存, 聂宏. 三参数Weibull分布参数的极大似然估计数值解法[J]. 南京航空航天大学学报, 2007, 39(1): 22- 25. [YANG M C, NIE H. Advanced algorithm for maximum likelihood estimation of three parameter weibull distribution[J]. Journal of Nanjing University of Aeronautics ＆ Astronautics, 2007, 39(1): 22-25.]

[8] 衣俸君. 基于威布尔分布模拟法的高压直流输电系统可靠性分析 [D]. 济南: 山东大学, 2016. [YI F J. Reliability analysis of HVDC system based on weibull distribution simulation method[D]. Jinan: Shandong University, 2016.]

[9] 邹争, 董从林, 袁成清, 等. 基于二参数威布尔分布的水润滑橡胶尾轴承可靠性寿命分析[J]. 舰船科学技术, 2015(2): 48-52. [ZOU Z, DONG C L, YUAN C Q, et al. Analysis reliability life of water lubricated rubber stern tube bearing based on two- parameter weibull distribution[J]. Ship Science and Technology, 2015(2): 48-52.]

[10] CHAN K Y, DILLON T S, SINGH J, et al. Neuralnetwork-based models for short- term traffic flow forecasting using a hybrid exponential smoothing and levenberg-marquardt algorithm[J]. IEEE Transactions on Intelligent Transportation Systems, 2012, 13(2): 644-654.

[11] 沈旻宇. 随机用户均衡下考虑学习行为的逐日动态模型研究[D]. 成都: 西南交通大学, 2016. [SHEN M Y. Day- to- day flow dynamics with user learning under stochastic user equilibrium[D]. Chengdu: Southwest Jiaotong University, 2016.]

[12] 李芳, 陆安祥, 王纪华. 基于列文伯格-马夸尔特- 反向传播人工神经网络的 X射线荧光光谱定量分析方法[J]. 食品安全质量检测学报, 2016(3): 1152-1158. [LI F, LU A X, WANG J H. Quantitative analysis method based on levenberg-marquardt back- propagation artificial neural network for X-ray fluorescence spectrometry[J]. Journal of Food Safety and Quality, 2016(3): 1152-1158.]

[1]	林建新, 刘博, 赵霞, 张蕾. 基于混合约束自编码器的机动车工况智能构建方法[J]. 交通运输系统工程与信息, 2022, 22(2): 109-116.
[2]	戢晓峰, 耿昭师. 山区双车道公路货车碰撞预测的双变量冲突极值模型[J]. 交通运输系统工程与信息, 2022, 22(2): 230-238.
[3]	张建波, 孙建平, 徐春玲, 郭镜霞, 温慧敏, 宋国华. 考虑交通运行条件影响的驾驶员特征聚类[J]. 交通运输系统工程与信息, 2022, 22(2): 330-336.
[4]	马景峰, 任刚, 李豪杰, 曹奇, 杜建玮. 电动自行车与机动车事故严重性影响因素分析[J]. 交通运输系统工程与信息, 2022, 22(2): 337-348.
[5]	宗芳, 王猛, 贺正冰. 考虑多车影响的分子动力学智能网联跟驰模型[J]. 交通运输系统工程与信息, 2022, 22(1): 37-48.
[6]	马小龙, 余强, 刘建蓓. 基于路侧毫米波雷达的车辆碰撞概率计算方法[J]. 交通运输系统工程与信息, 2022, 22(1): 57-66.
[7]	廖鹏, 唐铁桥. 基于车辆动力传动和转向系统的换道轨迹优化策略[J]. 交通运输系统工程与信息, 2022, 22(1): 98-105.
[8]	刘永红, 罗霞, 胡剑鹏. 考虑临时和预约需求的共享泊位动态分配方法[J]. 交通运输系统工程与信息, 2022, 22(1): 171-181.
[9]	袁振洲, 郭曼泽, 彭泳鑫, 杨洋. 基于梯度关联规则的老年行人交通事故风险识别[J]. 交通运输系统工程与信息, 2022, 22(1): 195-208.
[10]	张玉婷, 陈波佑, 张双焱, 闫学东, 李晓梦. 抵近信控交叉口分心驾驶识别模型[J]. 交通运输系统工程与信息, 2022, 22(1): 217-224.
[11]	宋浪, 王健, 杨滨毓, 安实. 连续流交叉口左转非机动车交通组织创新设计[J]. 交通运输系统工程与信息, 2022, 22(1): 225-233.
[12]	白婧荣, 唐伯明, 孙宗元, 毕辉云, 向恬君. 毗邻互通立交特长隧道驾驶负荷研究[J]. 交通运输系统工程与信息, 2022, 22(1): 301-310.
[13]	郭彦茹, 罗志雄, 王家川, 何方. 数据驱动的共享单车停放区规划方法研究[J]. 交通运输系统工程与信息, 2021, 21(6): 9-16.
[14]	李君羡, 沈宙彪, 童文聪, 吴志周. 基于分类车头时距的城市道路大型车影响分析[J]. 交通运输系统工程与信息, 2021, 21(6): 55-62.
[15]	卢凯, 周志洁, 张勇刚, 赵世杰, 徐广辉. 面向单向交通路网的绿波协调设计方法[J]. 交通运输系统工程与信息, 2021, 21(6): 74-83.