基于GRA 与SVM-mixed 的货运量预测方法

交通运输系统工程与信息 ›› 2016, Vol. 16 ›› Issue (6): 94-99.

基于GRA 与SVM-mixed 的货运量预测方法

梁宁1，耿立艳*2, 4，张占福3，梁毅刚2

1. 河北省高速公路廊坊北三县管理处，河北廊坊065000；2. 石家庄铁道大学经济管理学院，石家庄050043； 3. 石家庄铁道大学四方学院，石家庄051132；4. 曼彻斯特城市大学商学院，英国曼彻斯特M15 6BH

收稿日期:2016-06-12 修回日期:2016-08-21 出版日期:2016-12-25 发布日期:2016-12-26
作者简介:梁宁（1974-），男，河北石家庄人，高级工程师.
基金资助:
国家自然科学基金青年项目/ National Natural Science Foundation for Young Scholars of China(61503261)；河北省交通运输厅2015 年科技计划项目/ 2015 Science and Technology Project of Department of Transportation in Hebei Province ( Y- 2010024)；河北省软科学研究计划项目/Soft Science Research Program of Hebei Province (15456106D)；河北省高等学校青年拔尖人才计划项目/ Young Talents Program of Higher School of Hebei Province (BJ2014097)；河北省社会科学发展重点课题/ Key Project of Social Science Development of Hebei Province (2015020206)；河北省软科学研究基地项目/Project of Soft Science Research Base in Hebei Province (12457206D-14)；国家留学基金委(CSC)资助公派留学地方合作项目/Local Cooperation Project Funded by China Scholarship Council (CSC) (201608130165).

A Prediction Method of Railway Freight Volumes Using GRA and SVM-mixed

LIANG Ning1, GENG Li-yan2,4, ZHANG Zhan-fu3, LIANG Yi-gang2

1. Langfang Beisanxian County Management Department, Hebei Province Expressway , Langfang 065000, China; 2. School of Economics and Management, ShijiazhuangTiedao University, Shijiazhuang 050043, China; 3. Sifang College, ShijiazhuangTiedao University, Shijiazhuang 051132, China; 4.Business School, Manchester Metropolitan University, Manchester,M15 6BH,UK

Received:2016-06-12 Revised:2016-08-21 Online:2016-12-25 Published:2016-12-26

摘要/Abstract

摘要：

铁路货运量与其影响因素之间关系复杂，单一核函数支持向量机(SVM)难以进行准确描述，而且各因素对铁路货运量的影响程度具有差异性，若忽略这种差异性，将难以获得理想的铁路货运量预测结果.为此，本文提出一种基于灰色关联分析(GRA)与混合核函数支持向量机(SVM-mixed)的铁路货运量预测方法.该方法采用灰色关联分析确定各影响因素的权重，再将赋予权重的影响因素作为输入变量，构建多项式核函数与径向基核函数线性组合的SVM-mixed 预测模型.针对SVM-mixed 参数难以确定问题，采用果蝇优化算法(FOA)选择SVM-mixed 最优参数.基于中国铁路货运量的实例分析表明，该方法可有效提高铁路货运量的预测精度，为准确预测铁路货运量提供了一种新途径.

关键词: 铁路运输, 货运量, 预测, 灰色关联分析, 混合核函数支持向量机

Abstract:

The relationship between railway freight volumes and its influence factors is complex. It is difficult for support vector machines with single kernel function (SVM) to describe the complex relationship. At the same time, the impact of the factors on railway freight volumes is different. If we ignored this difference, it would be difficult to obtain the desired predicting results of railway freight volumes. To solve these problems, this paper proposes a novel method for predicting railway freight volumes based on grey relational analysis (GRA) and SVM with mixed kernel function (SVM- mixed). The weights of influence factors of railway freight volume are determined by GRA. Being as the input variables, the influence factors with weights are used to construct SVM- mixed whose kernel function combined polynomial kernel with radial basis kernel. Fruit fly optimization algorithm (FOA) is adopted to adjust the parameters in SVM-mixed to solve the problem of parameters selection of SVM-mixed. The example analysis of China railway freight volumes shows that the proposed method can effectively enhance accuracy in forecasting railway freight volumes, which provides a new approach for the accurate forecasting of railway freight volumes.

Key words: railway transportation, freight volumes, prediction, grey relational analysis, SVM with mixed kernel function

中图分类号:

U268.6

梁宁，耿立艳，张占福，梁毅刚. 基于GRA 与SVM-mixed 的货运量预测方法[J]. 交通运输系统工程与信息, 2016, 16(6): 94-99.

LIANG Ning, GENG Li-yan, ZHANG Zhan-fu, LIANG Yi-gang. A Prediction Method of Railway Freight Volumes Using GRA and SVM-mixed[J]. Journal of Transportation Systems Engineering and Information Technology, 2016, 16(6): 94-99.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/abstract/abstract19331.shtml

http://www.tseit.org.cn/CN/Y2016/V16/I6/94

参考文献

[1] 郭玉华，陈治亚，冯芬玲，等. 基于经济周期的铁路货运量神经网络预测研究[J]. 铁道学报, 2010, 32(5): 1- 6. [GUO Y H, CHEN Z Y, FENG F L, et al. Railway freight volume forecasting of neural network based on economic cycles[J]. Journal of the China Railway Society, 2010, 32(5): 1-6.]

[2] VAPNIK V N. An overview of statistical learning theory[J]. IEEE Transactions on Neural Networks, 1999, l0(5): 988-999.

[3] 赵闯，刘凯，李电生. 支持向量机在货运量预测中的应用研究[J]. 铁道学报, 2004, 26(4): 10-14. [ZHAO C, LIU K, LI D S. Research on application of support vector machine in freight volumes forecast[J]. Journal of the China Railway Society, 2004, 26(4): 10-14.]

[4] 唐奇，王红瑞，许新宜，等. 基于混合核函数SVM水文时序模型及其应用[J]. 系统工程理论与实践, 2014, 34 (2): 521-529. [TANG Q, WANG H R, XU X Y, et al . Hydrological time series model based on SVM with mixed kernel function and its application[J]. Systems Engineering-Theory & Practice, 2014, 34(2): 521-529.]

[5] 刘思峰，谢乃明. 灰色系统理论及其应用(第七版)[M]. 北京：科学出版社, 2014. [LIU S F, XIE N M. Grey system theory and its applications (the seventh edition)[M]. Beijing: Science Press, 2014.]

[6] 耿立艳，张天伟，赵鹏. 基于灰色关联分析的LS-SVM 铁路货运量预测[J]. 铁道学报, 2012, 34(3): 1-6. [GENG L Y, ZHANG T W, ZHAO P. Forecast on railway freight volumes based on LS-SVM with grey correlation analysis[J]. Journal of the China Railway Society, 2012, 34(3): 1-6.]

[7] PAN W T. A new fruit fly optimization algorithm: taking the financial distress model as an example[J]. Knowledge-Based Systems, 2012, 26(1): 69-74.

[8] CHEN F F, TANG B P, SONG T, et al. Multi- fault diagnosis study on roller bearing based on multi-kernel support vector machine with chaotic particle swarm optimization[J]. Measurement, 2014(47): 576-590.

[9] 申卯兴，薛西锋，张小水. 灰色关联分析中分辨系数的选取[J]. 空军工程大学学报(自然科学版), 2003, 4 (1): 68-70. [SHEN M X, XUE X F, ZHANG X S. Determination of discrimination coefficient in grey incidence analysis[J]. Journal of Air Force Engineering University (Natural Science Edition), 2003, 4(1): 68-70.]

[1]	耿庆桥, 贾元华, 陈军团. 基于变权可拓物元的铁路“走出去”公私合营项目风险决策[J]. 交通运输系统工程与信息, 2022, 22(2): 64-71.
[2]	王国栋, 刘立, 孟宇, 马智萍, 郑淏清, 顾青, 白国星. 一体式车辆避撞轨迹规划与跟踪控制[J]. 交通运输系统工程与信息, 2022, 22(2): 127-136.
[3]	戚建国, 周厚盛, 杨立兴, 周亚茹, 张春田. 灵活编组条件下轨道交通客货协同运输方案优化[J]. 交通运输系统工程与信息, 2022, 22(2): 197-205.
[4]	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.
[5]	张培文, 杜福民, 汪瑜. 基于链路预测的中小机场连接机制研究[J]. 交通运输系统工程与信息, 2022, 22(2): 298-304.
[6]	张晓明, 徐芳, 江文辉, 蒋朝哲. 考虑资金约束的中欧班列运价与运量决策分析[J]. 交通运输系统工程与信息, 2022, 22(1): 30-36.
[7]	张春田, 戚建国, 杨立兴, 高原, 高自友. 基于不确定旅客需求的高速铁路鲁棒列车开行方案研究[J]. 交通运输系统工程与信息, 2022, 22(1): 115-123.
[8]	周勇, 张杰, 钟祾充, 李文锋, 王国栋. 铁路集装箱中心站多轨道吊柔性协同调度优化[J]. 交通运输系统工程与信息, 2022, 22(1): 133-141.
[9]	胡杰, 何陈, 朱雪玲, 杨光宇. 基于实车数据的电动汽车电池剩余使用寿命预测[J]. 交通运输系统工程与信息, 2022, 22(1): 292-300.
[10]	孙启鹏, 曾开邦, 张锴琦, 杨艺琛, 张士行. 北京市共享单车出行的时空规律与需求预测研究[J]. 交通运输系统工程与信息, 2022, 22(1): 332-338.
[11]	王福建, 俞佳浩, 赵锦焕, 梅振宇. 基于站点实时关联度的短时公交客流预测方法[J]. 交通运输系统工程与信息, 2021, 21(6): 131-144.
[12]	陈丰, 张婷, 黄雅迪, 陈慈河, 张曙光, 吕明. 越江越海隧道入口段追尾事故风险预测模型研究[J]. 交通运输系统工程与信息, 2021, 21(6): 167-175.
[13]	胡笳, 罗书源, 赖金涛, 徐恬, 杨晓光. 自动驾驶对交通运输系统规划的影响综述[J]. 交通运输系统工程与信息, 2021, 21(5): 52-65.
[14]	牛惠民. 轨道列车时刻表问题研究综述[J]. 交通运输系统工程与信息, 2021, 21(5): 114-124.
[15]	钟鸣, 董一鸣, 汉特·道格拉斯, 孙江涛, 马晓凤, 刘少博, 吴宁宁. 面向新城的土地利用-交通整体规划建模方法[J]. 交通运输系统工程与信息, 2021, 21(3): 13-25.