• ISSN 0258-2724
  • CN 51-1277/U
  • EI Compendex
  • Scopus 收录
  • 全国中文核心期刊
  • 中国科技论文统计源期刊
  • 中国科学引文数据库来源期刊

基于多车型CNN-GRU性能预测模型的轨道状态评价

杨飞 郝晓莉 杨建 孙宪夫 高彦嵩 张煜

杨飞, 郝晓莉, 杨建, 孙宪夫, 高彦嵩, 张煜. 基于多车型CNN-GRU性能预测模型的轨道状态评价[J]. 西南交通大学学报, 2023, 58(2): 322-331. doi: 10.3969/j.issn.0258-2724.20211030
引用本文: 杨飞, 郝晓莉, 杨建, 孙宪夫, 高彦嵩, 张煜. 基于多车型CNN-GRU性能预测模型的轨道状态评价[J]. 西南交通大学学报, 2023, 58(2): 322-331. doi: 10.3969/j.issn.0258-2724.20211030
YANG Fei, HAO Xiaoli, YANG Jian, SUN Xianfu, GAO Yansong, ZHANG Yu. Track Condition Evaluation for Multi-vehicle Performance Prediction Model Based on Convolutional Neural Network and Gated Recurrent Unit[J]. Journal of Southwest Jiaotong University, 2023, 58(2): 322-331. doi: 10.3969/j.issn.0258-2724.20211030
Citation: YANG Fei, HAO Xiaoli, YANG Jian, SUN Xianfu, GAO Yansong, ZHANG Yu. Track Condition Evaluation for Multi-vehicle Performance Prediction Model Based on Convolutional Neural Network and Gated Recurrent Unit[J]. Journal of Southwest Jiaotong University, 2023, 58(2): 322-331. doi: 10.3969/j.issn.0258-2724.20211030

基于多车型CNN-GRU性能预测模型的轨道状态评价

doi: 10.3969/j.issn.0258-2724.20211030
基金项目: 国家自然科学基金(61771042);中国国家铁路集团有限公司科技研究开发计划(P2021T013)
详细信息
    作者简介:

    杨飞(1985—),男,副研究员,硕士,研究方向为轨道管理,E-mail:13811807268@163.com

    通讯作者:

    郝晓莉(1970—),女,副教授,博士,研究方向为信号处理,E-mail:xlhao@bjtu.edu.cn

  • 中图分类号: U216.3

Track Condition Evaluation for Multi-vehicle Performance Prediction Model Based on Convolutional Neural Network and Gated Recurrent Unit

  • 摘要:

    不同车型高速综合检测列车的动力学传递特性不同,使得其对同一线路的车体加速度评价结果存在一定差异. 为解决上述问题,本文基于多列动检车的检测数据,将卷积神经网络(convolutional neural network,CNN)与门控循环单元(gated recurrent unit,GRU)相结合,建立了多车型车辆动力学响应预测模型,通过输入多项实测轨道不平顺和车速预测各车型的车体垂向和横向加速度,并将多车型车体加速度预测值的最大包络作为轨道状态评价依据. 结果表明:将高低、轨向不平顺等8项轨道不平顺和车速共同作为输入参数的模型预测性能最优,车体垂向和横向加速度预测的评估指标分别提升了5%~13%和25%~36%;CNN-GRU模型所预测的车体加速度在时域和频域均与实测结果吻合较好,相关系数最大达到0.902;且相比于BP (back propagation)神经网络,各项车体垂向和横向加速度预测的评估指标分别提升了36%~109%和11%~167%;针对某轨道几何状态不良区段应用效果,预测6种车型中有4种车型达到车体垂向加速度Ⅰ级或Ⅱ级超限,有1种车型达到车体横向加速度Ⅰ级超限,提高了轨道状态评价的准确性和一致性.

     

  • 图 1  一维CNN结构

    Figure 1.  Structure of one-dimensional CNN

    图 2  GRU单元结构

    Figure 2.  Unit structure of GRU

    图 3  CNN-GRU网络结构

    Figure 3.  Network structure of CNN-GRU

    图 4  超参数对车体加速度预测性能的影响

    Figure 4.  Influence of super parameters on prediction performance of vehicle body acceleration

    图 5  车速200 km/h的CRH2A-2010车预测与实测结果对比

    Figure 5.  Comparison between predicted and measured results of CRH2A-2010 at the speed of 200 km/h

    图 6  实测轨道不平顺

    Figure 6.  Measured track irregularity

    图 7  不同车型的CNN-GRU模型测试结果

    Figure 7.  Test results of CNN-GRU model for various track inspection vehicles

    表  1  轨道不平顺输入组合的CNN-GRU评价指标

    Table  1.   CNN-GRU evaluation index of track irregularity input combination

    组号输入加速度EMAE/
    (m·s−2
    ERMSE/
    (m·s−2
    UTICρ
    车速 + 长波高低 + 长波轨向垂向0.0780.0980.2910.839
    横向0.0530.0670.4040.701
    ① + 高低 + 轨向垂向0.0740.0930.2740.858
    横向0.0490.0620.3890.737
    ② + 水平垂向0.0690.0870.2590.875
    横向0.0400.0510.2940.855
    ③ + 三角坑垂向0.0700.0880.2570.875
    横向0.0410.0530.3120.831
    ④ + 超高垂向0.0700.0880.2620.872
    横向0.0380.0490.2790.847
    ⑤ + 轨距垂向0.0680.0860.2530.880
    横向0.0340.0440.2560.879
    ⑥ (去除车速)垂向0.0710.0890.2640.869
    横向0.0380.0490.2890.848
    下载: 导出CSV

    表  2  不同车型的训练集和测试集里程

    Table  2.   Kilometrages of training set and test set for various track inspection vehicles km

    序号车型训练集总里程测试集总里程
    1CRH2A-2010400 (上行)200 (上行)
    2CRH2C-2150840 (上行)200 (下行)
    3CRH380BJ-A-0504400 (上行)210 (上行)
    4CRH5J-0501400 (下行)100 (下行)
    5CRH380AJ-0201940 (上行)200 (上行)
    6CRH380BJ-0301200 (下行)100 (上行)
    下载: 导出CSV

    表  3  小波分解层及波长范围

    Table  3.   Wavelet decomposition layer and wavelength range

    小波层D1D2D3D4D5D6D7D8A8
    波长范围/m(0.5, 1.0](1.0, 2.0](2.0, 4.0](4.0, 8.0](8.0, 16.0](16.0, 32.0](32.0, 64.0](64.0, 128.0]>128.0
    下载: 导出CSV

    表  4  多车型的不同模型评估指标对比

    Table  4.   Comparison of the evaluation index of different models for multi-vehicle

    模型车型加速度EMAE/
    (m·s−2)
    ERMSE/
    (m·s−2)
    UTICρ
    BPCRH2A-2010垂向0.1130.1520.6920.214
    横向0.0590.0780.6980.233
    CRH2C-2150垂向0.1180.1510.7160.343
    横向0.0540.0710.6930.345
    CRH380BJ-A-0504垂向0.0640.0810.6180.468
    横向0.0600.0640.7520.161
    CRH5J-0501垂向0.0510.0660.6330.440
    横向0.0550.0710.8550.223
    CRH380AJ-0201垂向0.1160.1480.7390.434
    横向0.0450.0590.8930.139
    CRH380BJ-0301垂向0.0700.0910.6820.339
    横向0.0600.0810.7800.104
    GRUCRH2A-2010垂向0.0650.0860.3170.820
    横向0.0410.0560.3960.711
    CRH2C-2150垂向0.0830.1060.3660.753
    横向0.0450.0610.4850.600
    CRH380BJ-A-0504垂向0.0550.0700.4130.670
    横向0.0370.0480.3460.782
    CRH5J-0501垂向0.0410.0520.4130.701
    横向0.0540.0710.6200.333
    CRH380AJ-0201垂向0.0690.0880.2960.841
    横向0.0430.0560.6110.383
    CRH380BJ-0301垂向0.0560.0740.4200.667
    横向0.0530.0710.5430.491
    CNN-GRUCRH2A-2010垂向0.0500.0650.2270.902
    横向0.0440.0590.4260.671
    CRH2C-2150垂向0.0790.1000.3370.789
    横向0.0460.0610.4430.621
    CRH380BJ-A-0504垂向0.0540.0680.4080.691
    横向0.0370.0480.3500.784
    CRH5J-0501垂向0.0410.0520.3910.714
    横向0.0600.0780.6310.243
    CRH380AJ-0201垂向0.0580.0740.2450.888
    横向0.0410.0530.5470.479
    CRH380BJ-0301垂向0.0560.0730.3980.693
    横向0.0620.0800.5450.416
    下载: 导出CSV

    表  5  各车型预测的加速度最大幅度值及偏差等级

    Table  5.   Maximum amplitude value and deviation level of the acceleration predicted by each track inspection vehicle

    车型垂向加速度/
    (m·s−2
    横向加速度/
    (m·s−2
    最大值超限等级最大值超限等级
    CRH2A-21501.120.57未超限
    CRH2C-20101.920.53未超限
    CRH380BJ-A-05041.220.30未超限
    CRH5J-05010.73未超限0.59未超限
    CRH380AJ-02011.580.40未超限
    CRH380BJ-03010.98未超限0.84
    下载: 导出CSV
  • [1] 刘金朝,刘秀波. 轨道质量状态评价方法[J]. 铁路技术创新,2012(1): 106-109. doi: 10.19550/j.issn.1672-061x.2012.01.030
    [2] 关庆华,赵鑫,温泽峰,等. 基于Hertz接触理论的法向接触刚度计算方法[J]. 西南交通大学学报,2021,56(4): 883-890.

    GUAN Qinghua, ZHAO Xin, WEN Zefeng, et al. Calculation method of hertz normal contact stiffness[J]. Journal of Southwest Jiaotong University, 2021, 56(4): 883-890.
    [3] LUBER B. Railway track quality assessment method based on vehicle system identification[J]. e & i Elektrotechnik und Informationstechnik, 2009, 126(5): 180-185.
    [4] LUBER B, HAIGERMOSER A, GRABNER G. Track geometry evaluation method based on vehicle response prediction[J]. Vehicle System Dynamics, 2010, 48(S1): 157-173.
    [5] FURUKAWA A, YOSHIMURA A. A method to predict track geometry-induced vertical vehicle motion[J]. Quarterly Report of RTRI, 2004, 45(3): 142-148. doi: 10.2219/rtriqr.45.142
    [6] FURUKAWA A. A method to predict vertical vehicle motion caused by track irregularities[J]. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 2017, 231(4): 431-443. doi: 10.1177/0954409716634394
    [7] LI M X D, BERGGREN E G, BERG M, et al. Assessing track geometry quality based on wavelength spectra and track-vehicle dynamic interaction[J]. Vehicle System Dynamics, 2008, 46(S1): 261-276.
    [8] BERGGREN E G, LI M X D, SPÄNNAR J. A new approach to the analysis and presentation of vertical track geometry quality and rail roughness[J]. Wear, 2008, 265(9/10): 1488-1496.
    [9] LI M X D, BERGGREN E G, BERG M. Assessment of vertical track geometry quality based on simulations of dynamic track-vehicle interaction[J]. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 2009, 223(2): 131-139. doi: 10.1243/09544097JRRT220
    [10] WANG J K, HE Y L, LU H Y, et al. Study on vibration acceleration prediction model of track inspection vehicle based on BP neural network[J]. IOP Conference Series: Materials Science and Engineering, 2018, 435: 012041.1-012041.8.
    [11] LI D, MEDDAH A, HASS K, et al. Relating track geometry to vehicle performance using neural network approach[J]. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 2006, 220(3): 273-281. doi: 10.1243/09544097JRRT39
    [12] 徐磊,陈宪麦. 轨道不平顺作用下铁路列车车体振动状态的PCA-SVM预测分析[J]. 铁道学报,2014,36(7): 16-23. doi: 10.3969/j.issn.1001-8360.2014.07.003

    XU Lei, CHEN Xianmai. PCA-SVM forecast of car-body vibration states of railway locomotives and vehicles under the action of track irregularities[J]. Journal of the China Railway Society, 2014, 36(7): 16-23. doi: 10.3969/j.issn.1001-8360.2014.07.003
    [13] 耿松,柴晓冬,郑树彬. 基于递阶神经网络的轨道车辆振动状态预测[J]. 城市轨道交通研究,2015,18(12): 94-98. doi: 10.16037/j.1007-869x.2015.12.021

    GENG Song, CHAI Xiaodong, ZHENG Shubin. Prediction of rail transit vehicle vibration state based on hierarchical neural network[J]. Urban Mass Transit, 2015, 18(12): 94-98. doi: 10.16037/j.1007-869x.2015.12.021
    [14] 李立明,柴晓冬,郑树彬. 基于径向基函数神经网络的轨道交通车辆振动状态预测[J]. 城市轨道交通研究,2017,20(12): 18-21. doi: 10.16037/j.1007-869x.2017.12.005

    LI Liming, CHAI Xiaodong, ZHENG Shubin. Prediction of rail vehicle vibration state based on radial basis function nerve network[J]. Urban Mass Transit, 2017, 20(12): 18-21. doi: 10.16037/j.1007-869x.2017.12.005
    [15] 刘秀波, 马帅, 高利民, 等. 基于轨道几何和LSTM的车辆响应预测模型[C]//第十三届全国振动理论及应用学术会议. 西安: 中国振动工程学会, 2019: 15-21.
    [16] MA S, GAO L, LIU X B, et al. Deep learning for track quality evaluation of high-speed railway based on vehicle-body vibration prediction[J]. IEEE Access, 2019, 7: 185099-185107. doi: 10.1109/ACCESS.2019.2960537
    [17] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324. doi: 10.1109/5.726791
    [18] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780. doi: 10.1162/neco.1997.9.8.1735
    [19] CHO K, VAN MERRIENBOER B, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Doha: Association for Computational Linguistics, 2014: 1724-1734
    [20] CHUNG J, GULCEHRE C, CHO K H, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling[EB/OL]. (2014-12-11)[2021-11-10]. https://arxiv.org/abs/1412.3555.
    [21] 康熊,刘秀波,李红艳,等. 高速铁路无砟轨道不平顺谱[J]. 中国科学(技术科学),2014,44(7): 687-696. doi: 10.1360/N092014-00088

    KANG Xiong, LIU Xiubo, LI Hongyan, et al. PSD of ballastless track irregularities of high-speed railway[J]. Scientia Sinica (Technologica), 2014, 44(7): 687-696. doi: 10.1360/N092014-00088
  • 加载中
图(7) / 表(5)
计量
  • 文章访问数:  459
  • HTML全文浏览量:  172
  • PDF下载量:  75
  • 被引次数: 0
出版历程
  • 收稿日期:  2021-12-14
  • 修回日期:  2022-06-16
  • 网络出版日期:  2022-11-19
  • 刊出日期:  2022-07-14

目录

    /

    返回文章
    返回