• 查询稿件
  • 获取最新论文
  • 知晓行业信息
官方微信 欢迎关注

铁路基础设施位移数据预测模型研究

路志远, 潘佩芬, 白雪娇, 张吉峰, 张良会

路志远, 潘佩芬, 白雪娇, 张吉峰, 张良会. 铁路基础设施位移数据预测模型研究[J]. 铁路计算机应用, 2022, 31(3): 12-18. DOI: 10.3969/j.issn.1005-8451.2022.03.03
引用本文: 路志远, 潘佩芬, 白雪娇, 张吉峰, 张良会. 铁路基础设施位移数据预测模型研究[J]. 铁路计算机应用, 2022, 31(3): 12-18. DOI: 10.3969/j.issn.1005-8451.2022.03.03
LU Zhiyuan, PAN Peifen, BAI Xuejiao, ZHANG Jifeng, ZHANG Lianghui. Prediction model for displacement data of railway infrastructure[J]. Railway Computer Application, 2022, 31(3): 12-18. DOI: 10.3969/j.issn.1005-8451.2022.03.03
Citation: LU Zhiyuan, PAN Peifen, BAI Xuejiao, ZHANG Jifeng, ZHANG Lianghui. Prediction model for displacement data of railway infrastructure[J]. Railway Computer Application, 2022, 31(3): 12-18. DOI: 10.3969/j.issn.1005-8451.2022.03.03

铁路基础设施位移数据预测模型研究

基金项目: 四川省科技计划重点研发项目(2020GZYZF0010);中国铁路总公司科技研究开发计划课题(P2018G051);京沪高速铁路股份有限公司科技研究项目(京沪科研-2020-9)
详细信息
    作者简介:

    路志远,研究实习员

    潘佩芬,副研究员

  • 中图分类号: U2 : TP39

Prediction model for displacement data of railway infrastructure

  • 摘要: 线路安全是铁路运营的重要前提,我国铁路跨度广、行车环境复杂,当铁路基础设施稳定性产生改变时往往会严重影响行车安全。文章采用长短期记忆(LSTM ,Long Short-Term Memory)模型对基于全球导航卫星系统(GNSS,Global Navigation Satellite System)的铁路基础设施监测系统的形变监测数据进行建模预测,实现对铁路基础设施灾害的早期预警,并与多种传统时间序列预测模型进行对比,结果表明,LSTM模型具有更好的性能。
    Abstract: Railway safety is an important prerequisite for operation. Due to the wide span and complex driving environment of China's railway, when the stability of railway infrastructure changes, it will seriously affect the driving safety. This paper used Long Short-Term Memory(LSTM)model to model and predict the deformation monitoring data of railway infrastructure monitoring system based on Global Navigation Satellite System(GNSS), Achieved early warning of railway infrastructure disasters, and compared it with various traditional time series prediction models. The experimental results show that the LSTM model has better performance.
  • 图  1   铁路基础设施形变监测系统架构

    图  2   LSTM单元结构

    图  3   3种形变类型各维度位移曲线

    图  4   实验设计

    图  5   发育型监测数据位移预测曲线

    图  6   稳定型监测数据位移预测曲线

    图  7   波动稳定型监测数据位移预测曲线

    表  1   发育型监测数据预测精度指标

    东西南北垂直
    TimeRMSEMAETimeRMSEMAETimeRMSEMAE
    DT0.040.1010.0830.050.0450.0330.080.0440.034
    Linear0.060.0110.0080.060.0260.0190.080.0170.013
    SVM0.080.2400.2120.080.0730.0420.0170.0990.067
    RF0.110.0990.0790.120.0370.0260.100.0320.024
    GBRT0.160.1030.0830.160.0380.0250.080.0330.026
    ET0.190.1020.0840.210.0450.0330.100.0510.042
    ARD0.210.0110.0080.230.0260.0190.440.0170.013
    Byesian0.230.0110.0080.250.0260.0190.080.0170.013
    TheilSen0.250.0110.0080.270.0260.0190.120.0160.012
    RANSAC0.280.0110.0080.290.0260.0190.280.0170.012
    LSTM82.550.0300.0232.550.0250.0172.550.0180.013
    LSTM122.600.0350.0262.550.0270.0192.600.0210.015
    下载: 导出CSV

    表  2   稳定型监测数据预测精度指标

    东西南北垂直
    TimeRMSEMAETimeRMSEMAETimeRMSEMAE
    DT0.040.0600.0480.050.0480.0350.040.0520.042
    Linear0.060.0410.0330.060.0300.0230.060.0310.024
    SVM0.070.0680.0530.080.0530.0400.070.0910.066
    RF0.110.0490.0390.120.0340.0280.100.0450.034
    GBRT0.140.0480.0380.170.0350.0280.140.0460.035
    ET0.170.0660.0520.210.0550.0410.170.0560.045
    ARD0.190.0410.0330.230.0300.0230.190.0310.025
    Byesian0.200.0410.0330.250.0300.0230.210.0310.024
    TheilSen0.220.0470.0390.270.0310.0240.220.0310.025
    RANSAC0.230.0460.0380.290.0310.0240.240.0310.024
    LSTM82.550.0380.0312.580.0340.0272.590.0310.024
    LSTM122.530.0400.0322.600.0270.0212.600.0300.023
    下载: 导出CSV

    表  3   波动稳定型监测数据预测精度指标

    东西南北垂直
    TimeRMSEMAETimeRMSEMAETimeRMSEMAE
    DT0.040.0840.0670.050.0670.0530.040.0670.056
    Linear0.060.0490.0380.080.0400.0310.060.0480.039
    SVM0.080.0640.0470.100.0800.0510.080.0660.053
    RF0.110.0600.0470.130.0500.0390.110.0540.044
    GBRT0.150.0540.0430.170.0520.0400.160.0550.043
    ET0.180.0800.0640.210.0730.0560.190.0780.064
    ARD0.190.0490.0380.220.0400.0310.200.0470.039
    Byesian0.210.0490.0370.240.0400.0310.220.0480.039
    TheilSen0.220.0520.0400.260.0420.0330.240.0490.040
    RANSAC0.240.0520.0400.270.0410.0310.250.0510.041
    LSTM82.680.0410.0322.460.0360.0282.760.0460.037
    LSTM122.600.0430.0342.620.0350.0262.650.0480.038
    下载: 导出CSV
  • [1] 雷绍兰,孙才新,周 湶. 电力短期负荷的多变量时间序列线性回归预测方法研究 [J]. 中国电机工程学报,2006(2):25-29. DOI: 10.3321/j.issn:0258-8013.2006.02.005
    [2] 刘 静,关 伟. 交通流预测方法综述 [J]. 公路交通科技,2004(3):82-85. DOI: 10.3969/j.issn.1002-0268.2004.03.022
    [3] 杨秀媛,肖 洋,陈树勇. 风电场风速和发电功率预测研究 [J]. 中国电机工程学报,2005(11):1-5. DOI: 10.3321/j.issn:0258-8013.2005.11.001
    [4]

    CHO K, VAN MERRIëNBOER B, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation [J]. arXiv preprint arXiv:, 1406, 1078: 2014.

    [5]

    WERBOS P J. Generalization of backpropagation with application to a recurrent gas market model [J]. Neural networks, 1988, 1(4): 339-356. DOI: 10.1016/0893-6080(88)90007-X

    [6]

    HOCHREITER S. Untersuchungen zu dynamischen neuronalen Netzen [J]. Diploma, Technische Universität München, 1991, 91(1).

    [7]

    HOCHREITER S, SCHMIDHUBER J. Long short-term memory [J]. Neural computation, 1997, 9(8): 1735-1780. DOI: 10.1162/neco.1997.9.8.1735

    [8]

    GERS F A, SCHMIDHUBER J. LSTM recurrent networks learn simple context-free and context-sensitive languages [J]. IEEE transactions on neural networks, 2001, 12(6): 1333-1340. DOI: 10.1109/72.963769

    [9]

    Srivastava N , Mansimov E , Salakhutdinov R . Unsupervised Learning of Video Representations using LSTMs[J]. JMLR. org, 2015.

    [10]

    HANSON J, YANG Y, PALIWAL K, et al. Improving protein disorder prediction by deep bidirectional long short-term memory recurrent neural networks [J]. Bioinformatics, 2017, 33(5): 685-692.

    [11]

    ECK D, LAPALME J. Learning musical structure directly from sequences of music [J]. University of Montreal, Department of Computer Science, 2008.

    [12]

    GREFF K, SRIVASTAVA R K, KOUTNíK J, et al. LSTM: A search space odyssey [J]. IEEE transactions on neural networks and learning systems, 2016, 28(10): 2222-2232.

  • 期刊类型引用(3)

    1. 田朋溢,石雯,陈彪,高攀,蒋成成,刘鹏. 无线分布式轨道车辆平稳性测试技术研究. 铁道机车车辆. 2024(06): 110-116 . 百度学术
    2. 茅迿,高琦,梁师嵩. 城轨列车智能综合检测系统的研究与应用. 机车车辆工艺. 2023(01): 12-16 . 百度学术
    3. 刘国联,陈根,张敏海. 基于CAN总线的铁路道岔监测系统设计. 南方农机. 2020(09): 217-219 . 百度学术

    其他类型引用(1)

图(7)  /  表(3)
计量
  • 文章访问数:  181
  • HTML全文浏览量:  87
  • PDF下载量:  35
  • 被引次数: 4
出版历程
  • 收稿日期:  2021-10-24
  • 刊出日期:  2022-03-30

目录

    /

    返回文章
    返回