基于组合预测模型的铁路集装箱运量预测

摘要/Abstract

摘要： 为了克服单项预测模型的单一性和片面性等缺点，本文应用组合预测模型对铁路集装箱运量进行预测，以提高预测的准确性。通过对运量的历史数据分别采用多项式曲线模型和灰色预测模型建立单项预测模型，再利用径向基神经网络对两个单项预测模型的结果进行组合预测。研究结果表明，相比于两单项预测方法，组合预测方法所得运量的相对误差分别提高了3.19%和12.76%。最后，应用马尔科夫链模型对组合预测的结果进行分析和修正，增加预测结果的可靠性。

关键词: 铁路集装箱, 预测, 径向基神经网络, 马尔科夫链

Abstract: The forecast of railway container freight volume has significant effect on the operation and development of the railway. The existing forecast models can forecast a single index only, which is not accurate enough. To overcome this disadvantage, the combinatorial forecast model is adopted to forecast railway container freight volume. Based on the historical data, individual index forecast models are derived by using linear polynomial and grey models, respectively. Then, the individual index forecast models are combined by using radial basis function (RBF) neural network. Analysis shows that, in comparison with two single index forecast models, the combinatorial forecast model can improve the forecast result of relative error by 3.19% and 12.76%, respectively. Finally, the combinatorial forecast result is analyzed and modified by Markov chain model.

Key words: railway container, forecast, radial basis function(RBF) neural network, Markov chain

林炳焜，程文明，于兰峰. 基于组合预测模型的铁路集装箱运量预测[J]. 工业工程, 2012, 15(4): 1-6.

Lin Bing-kun, Cheng Wen-ming, Yu Lan-feng. Forecast of Railway Container Freight Volume by Using a Combinatorial Model[J]. Industrial Engineering Journal , 2012, 15(4): 1-6.

参考文献

［1］钟学燕，岳辉.铁路集装箱运量预测与影响因素分析［J］.铁道运输与经济，2006，27（9）：75-78.Zhong Xueyan, Yue Hui. The forecast of railway container transport volume and analysis on its effecting factors［J］. Railway Transport and Economy,2006,27（9）：75-78. ［2］彭恺.基于灰色预测法的铁路集装箱运量预测［J］.现代物流，2009(6)：47-48.Peng Kai. The forecast of railway container transport volume based on grey model［J］. Modern Logistics,2009(6)：47-48. ［3］Yu Yang, Yang Xuebin, Du Wen. Railway container key station freight volumes prediction based on grey-markov chain method［C］∥Proc. of the 2nd International Conference on Transportation Engineering. Chengdu：ASCE Press,2009:404-409. ［4］王如义,王慈光,郭孜政,等.铁路货物周转量的半参数回归模型预测［J］.西南交通大学学报,2008,43(1):96-100.Wang Ruyi,Wang Ciguang,Guo Zizheng,et al.Forecast of railway freight tonkilometers based on semi-parametric regression［J］.Journal of Southwest Jiaotong University,2008,43(1):96-100. ［5］吴璇，王烈.组合预测模型在铁路集装箱运量预测中的应用［J］.铁道运输与经济，2010，32（10）：90-94.Wu Xuan, Wang Lie. Application of combined forecast model on the forecast of railway container traffic volume［J］. Railway Transport and Economy,2010,32（10）：90-94. ［6］朱昌锋.基于模型组合的铁路集装箱运量预测［J］. 交通运输系统工程与信息，2010，10（5）：149-153.Zhu Changfeng. Freight volume forecasting of railway container based on model combination［J］. Journal of Transportation Systems Engineering and Information Technology,2010,10（5）：149-153. ［7］魏海坤，徐嗣鑫，宋文忠.神经网络的泛化理论和泛化方法［J］.自动化学报，2001,27（6）: 806-815. 〖DW〗Wei Haikun, Xu Sixin, Song Wenzhong. Generalization theory and generalization methods for neural networks［J］. Acta Automatica Sinica,2001,27(6): 806-815. ［8］朱劲松，肖汝诚.大跨度PC斜拉桥结构快速分析神经网络模型［J］.中国铁道科学，2007，28(1):33-39.Zhu Jinsong, Xiao Rucheng. Neural network model to structural simulation of large-span PC cablestayed bridges［J］. China Railway Science,2007,28(1):33-39. ［9］柏坚,俞乐.径向基神经网络模型在滇东南金矿潜力预测中的应用［J］.浙江大学学报:理学版,2011,38(3):354-361.Bai Jian, Yu Le. Application of radial basis function neural networks to prospectively mapping for gold deposits in southeastern Yunnan China［J］. Journal of Zhejiang University:Science Edition,2011,38(3):354-361.〖ZK)〗 ［10］胡穗华,徐辉.基于径向基神经网络模型的企业高管胜任力评价［J］.系统工程,2010,28(5):122-126.Hu Suihua, Xu Hui. Evaluation of enterprises executive competence based on radial basis function model［J］. Systems Engineering,2010,28(5):122-126. ［11］Luis Antonio Aguirre, Gladstone Barbosa Alves, Marcelo Vieira Correab. Steady-state performance constraints for dynamical models based on RBF networks［J］. Engineering Applications of Artificial Intelligence,2007，20（7）:924-935. ［12］Bipan Tudua, Arun Janab, Animesh Metlaa, et al. Electronic nose for black tea quality evaluation by an incremental RBF network［J］. Sensors and Actuators B: Chemical,2009(138):90-95. ［13］张国平.BG组合预测理论剖析［J］.预测,1988(5):22-25.Zhang Guoping. B-G combination forecasting theory analysis［J］.Forecasting,1988（5）: 22-25. ［14］闻新，周露，王丹力，等.MATLAB神经网络应用设计［M］.北京：科学出版社，2000：245. ［15］耿睿，崔德光，徐冰.应用支持向量机的空中交通流量组合预测模型［J］.清华大学学报:自然科学版，2008，48（7）：1205-1208.Geng Rui, Cui Deguang, Xu Bing. Support vector machine-based combinational model for air traffic forecasts［J］.J Tsinghua Univ: Science and Technolog,2008,48（7）：1205-1208.

[1]	董海, 冯晔. 基于XGBoost的车身尺寸装配质量智能预测模型[J]. 工业工程, 2021, 24(3): 77-82.
[2]	汪瑜, 车通, 鄢仕林. 基于灰色周期外延的航线客流量区间序列预测模型[J]. 工业工程, 2021, 24(3): 89-95.
[3]	王铁骊, 彭恒明. 基于改进GM(1,1)-Markov模型的国内生产安全事故预测研究[J]. 工业工程, 2020, 23(6): 60-67.
[4]	唐中君, 周亚丽. 结合区间理论熵权和TOPSIS的映前总票房区间预测[J]. 工业工程, 2020, 23(4): 75-83.
[5]	万鹏, 宋乃绪, 原丕业, 谢亚雯. 具有缺陷品的双渠道供应链库存优化策略[J]. 工业工程, 2019, 22(2): 49-56,66.
[6]	邓明明, 朱郭奇. 检验THERP合理性及不足的实验研究——以汽车冷媒加注工序为例[J]. 工业工程, 2019, 22(1): 85-89.
[7]	常建娥, 李帅, 莫易敏, 张峰, 王天生. 基于装配相似性与灰色模型的汽车装配工时预测[J]. 工业工程, 2018, 21(3): 87-92.
[8]	滕少华, 苏庆佳, 刘冬宁, 张巍. 符号网络预测准确度及时间代价的优化[J]. 工业工程, 2017, 20(1): 59-64.
[9]	万方华1, 王晓琪2, 张洪3, 丁诗泳3, 陈建国1, 王通德1, 潘文斌1. 基于KPLS的滚动轴承装配质量预测[J]. 工业工程, 2016, 19(4): 136-139.
[10]	何国光1,2, 李树刚1. 基于系统动力学仿真的医疗资源配置[J]. 工业工程, 2016, 19(2): 121-127.
[11]	殷旅江1，2，杨立君1, 何波1. 基于主成分分析与支持向量机的汽柴油需求预测[J]. 工业工程, 2015, 18(2): 20-27.
[12]	钟映竑，黄鑫. 基于粗糙集和支持向量机理论的物流需求预测研究[J]. 工业工程, 2015, 18(2): 28-33.
[13]	孙瑞山，张思远. 人的可靠性综合分析模式及应用[J]. 工业工程, 2014, 17(2): 49-54.
[14]	范丹丹，徐琪. 基于马尔科夫链的双渠道供应链库存优化决策[J]. 工业工程, 2014, 17(2): 85-91.
[15]	方卫国，蔡伟宁. 基于Gram'Schmidt回归的军用无人机研制费用预测[J]. 工业工程, 2013, 16(6): 29-33.