Multilevel Residual Prophet Network Time Series Model for Prediction of Irregularities on High-Speed Railway Track
Publication: Journal of Transportation Engineering, Part A: Systems
Volume 149, Issue 4
Abstract
Accurate prediction of the change in track irregularity plays an essential role in keeping the high-speed railway safe and stable. Regular maintenance is an important measure to guarantee track smoothness, which has a great influence on the change of track state. This paper introduces the time series anomaly detection model (AD) to detect changes by tracking the difference between the mean values of two sliding time windows. These changes are taken as one of the holidays of the prophet model which is called the AD_ Prophet model. Moreover, this paper proposes a multilevel residual prophet (Re-Prophet) prediction network which can make full use of the information of residual data to predict the results. The final predicted result is the sum of the value of each prediction. To explore the characteristics of the time series, the Hodrick-Prescott filter is used to explore the trend. A multi-month-wise box plot is used to explore the seasonal volatility and the wavelet transform is used to explore the cyclical variation. Based on these characteristics, the fitting model can be chosen. Finally, to verify the high accuracy of the model, the surface irregularities of the high-speed railway are used as the research objects. Compared with conventional prediction algorithms, the proposed model has the smallest prediction deviation and the highest accuracy based on the evaluation indicators such as mean squared error, root mean squared error, mean absolute error, and mean absolute percentage error.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This research was supported by National Natural Science Foundation of China (No. 51975038), Natural Science Foundation of Beijing Municipal (No. KZ202010016025), Fundamental Research Funds for Beijing University of Civil Engineering and Architecture (Nos. X18027 and X19022), and the BUCEA Doctor Graduate Scientific Research Ability Improvement Project (DG2021005). The authors gratefully acknowledge the support.
References
Adhikari, R., and R. Agrawal. 2013. “An introductory study on time series modeling and forecasting Ratnadip Adhikari R. K. Agrawal.” Preprint, submitted February 26, 2013. http://arxiv.org/abs/1302.6613.
Bai, L., R. Liu, Q. Sun, F. Wang, and F. Wang. 2016. “Classification-learning-based framework for predicting railway track irregularities.” Proc. Inst. Mech. Eng., Part F: J. Rail Rapid Transit 230 (2): 598–610. https://doi.org/10.1177/0954409714552818.
Box, G. E. P., G. M. Jenkins, G. C. Reinsel, and G. M. Ljung. 2010. “Time series analysis: Forecasting and control.” J. Time 31 (3): 303. https://doi.org/10.1111/j.1467-9892.2009.00643.x.
Du, X.-R., Y.-Q. Yang, P. Xu, C. Yang, and X. Wu. 2022. “Identification of creep camber state of 32-m box girders on high-speed railway and prediction of geometry of track over girder.” J. Transp. Eng. Part A Syst. 148 (3): 1–11. https://doi.org/10.1061/jtepbs.0000611.
Hassani, H., and M. R. Yeganegi. 2019. “Sum of squared ACF and the ljung–box statistics.” Physica A 520 (Apr): 81–86. https://doi.org/10.1016/j.physa.2018.12.028.
Hodrick, R. J., and E. C. Prescott. 1997. “Postwar U.S. business cycles: An empirical investigation.” J. Money Credit Banking 29 (1): 1–16. https://doi.org/10.2307/2953682.
Kedia, N. K., A. Kumar, and Y. Singh. 2021. “Effect of rail irregularities and rail pad on track vibration and noise.” KSCE J. Civ. Eng. 25 (4): 1341–1352. https://doi.org/10.1007/s12205-021-1345-6.
Lee, J. S., S. H. Hwang, I. Y. Choi, and Y. Choi. 2020. “Deterioration prediction of track geometry using periodic measurement data and incremental support vector regression model.” J. Transp. Eng. Part A Syst. 146 (1): 1–12. https://doi.org/10.1061/jtepbs.0000291.
Li, H., F. Pan, X. Ao, Y. Zhao, L. Min, P. Junewei, L. Dapeng, L. Xiao, and Q. He. 2021a. “Follow the prophet: Accurate online conversion rate prediction in the face of delayed feedback.” In Proc. 44th Int. ACM SIGIR Conf. on Research and Development in Information Retrieval (SIGIR’21), 1915–1919. New York: Association for Computing Machinery. https://doi.org/10.1145/3404835.3463045.
Li, H., T. Wang, and G. Wu. 2021b. “Dynamic response prediction of vehicle-bridge interaction system using feedforward neural network and deep long short-term memory network.” Structures 34 (Dec): 2415–2431. https://doi.org/10.1016/j.istruc.2021.09.008.
Li, W., T. Lu, X. He, and R. Liu. 2021c. “Interpolation analysis of prophet model in GNSS coordinate time series.” J. Geod. Geodyn. 41 (4): 362–367. https://doi.org/10.14075/j.jgg.2021.04.007.
Li, W., T. Lu, X. He, and W. Qian. 2021d. “Prediction and analysis of GNSS vertical coordinate time series based on prophet-RF model.” J. Geod. Geodyn. 41 (2): 116–121. https://doi.org/10.14075/j.jgg.2021.02.002.
Li, Y., Y. Yang, K. Zhu, and J. Zhang. 2021e. “Clothing sale forecasting by a composite GRU–prophet model with an attention mechanism.” IEEE Trans. Ind. Inf. 17 (12): 8335–8344. https://doi.org/10.1109/TII.2021.3057922.
Lyu, B. 2019. “Research on inspection of ballast track irregularity defects in high-speed railway and related treatment measures.” Railway Constr. Technol. 314 (7): 114–129. https://doi.org/10.3969/j.issn.1009-4539.2019.07.027.
Mandrikova, O., N. Fetisova, and Y. Polozov. 2021. “Hybrid model for time series of complex structure with ARIMA components.” Mathematics 9 (10): 1122. https://doi.org/10.3390/math9101122.
Niu, L., J. Liu, J. Qu, and F. Yin. 2020. “Study of relation between track irregularity and lateral acceleration of vehicle based on state-space model.” J. China Railway Soc. 42 (8): 123–129. https://doi.org/10.3969/j.issn.1001-8360.2020.08.016.
Song, K., X. Zhang, W. Hou, X. Chen, and Z. Han. 2021. “Prophet-DCRNN traffic forecasting method with multi-modal information.” J. CAEIT 16 (3): 250–264. https://doi.org/10.3969/j.issn.1673-5692.2021.03.007.
Tang, W., and A. Rollin. 2021. “Model identification for ARMA time series through convolutional neural networks.” Decis. Support Syst. 146 (Jul): 113544. https://doi.org/10.1016/j.dss.2021.113544.
Taylor, S. J., and B. Letham. 2017. “Forecasting at scale.” PeerJ Preprints 5 (Sep): 1–25. https://doi.org/10.7287/peerj.preprints.3190v2.
Triebe, O., H. Hewamalage, P. Pilyugina, N. Laptev, C. Bergmeir, and R. Rajagopal. 2021. “NeuralProphet: Explainable forecasting at scale.” Preprint, submitted November 29, 2021. http://arxiv.org/abs/2111.15397.
Tucker, M. 2021. “A diagnostic for seasonality based upon polynomial roots of ARMA models.” J. Off. Stat. 37 (2): 367–394. https://doi.org/10.2478/jos-2021-0016.
Vera, A., and S. Banerjee. 2021. “The Bayesian prophet: A low-regret framework for online decision making.” Manage. Sci. 67 (3): 1368–1391. https://doi.org/10.1287/mnsc.2020.3624.
Wang, J., J. Yang, Y. Lin, and Y. He. 2022a. “Analytical investigation of profile shifts on the mesh stiffness and dynamic characteristics of spur gears.” Mech. Mach. Theory 167 (Jan): 104529. https://doi.org/10.1016/j.mechmachtheory.2021.104529.
Wang, J., J. Yang, Y. Wang, Y. Bai, T. Zhang, and D. Yao. 2021a. “Ensemble decision approach with dislocated time–frequency representation and pre-trained CNN for fault diagnosis of railway vehicle gearboxes under variable conditions.” Int. J. Rail Transp. 10 (5): 1–19. https://doi.org/10.1080/23248378.2021.2000897.
Wang, X., J. Yang, Y. Du, J. Wang, Y. Wang, and F. Liu. 2022b. “Risk identification method for high-speed railway track based on track quality index and time-optimal degree.” ASCE-ASME J. Risk Uncertainty Eng. Syst. Part A: Civ. Eng. 8 (2): 1–12. https://doi.org/10.1061/AJRUA6.0001218.
Wang, X., J. Yang, J. Wang, Y. Wang, and F. Liu. 2021b. “Risk assessment method for high-speed railway track based on dynamically weighted acceleration.” J. Infrastruct. Syst. 27 (4): 04021030. https://doi.org/10.1061/(ASCE)IS.1943-555X.0000643.
Xu, N., S. Ding, and Y. Gong. 2021. “Advances in grey GM(1,1) forecasting model and its extension.” Math. Pract. Theory 51 (13): 52–59.
Ye, Y., B. Zhu, P. Huang, and B. Peng. 2022. “OORNet: A deep learning model for on-board condition monitoring and fault diagnosis of out-of-round wheels of high-speed trains.” Measurement 199 (Aug): 111268. https://doi.org/10.1016/j.measurement.2022.111268.
Zhang, R., L. Meng, Z. Mao, and H. Sun. 2021. “Spatiotemporal deep learning for bridge response forecasting.” J. Struct. Eng. 147 (6): 1–9. https://doi.org/10.1061/(ASCE)ST.1943-541X.0003022.
Zhao, Y., Y. Zhai, J. Chen, and J. Teng. 2020. “Time series forecasting model based on LSTM-prophet nonlinear combination.” Jisuanji Yu Xiandaihua 2020 (9): 6–18. https://doi.org/10.3969/j.issn.1006-2475.2020.09.002.
Zhou, J., and H. Wang. 2017. “A dynamic logistic regression for network link prediction.” Sci. China Math. 60 (1): 165–176. https://doi.org/10.1007/s11425-015-0807-8.
Zhu, J., X. Zou, W. Xiong, X. Yuan, X. Ai, and Y. Peng. 2021. “Short-term power load forecasting based on prophet and XGBoost mixed model.” Mod. Electr. Power 38 (3): 325–331. https://doi.org/10.19725/j.cnki.1007-2322.2020.0321.
Information & Authors
Information
Published In
Journal of Transportation Engineering, Part A: Systems
Volume 149 • Issue 4 • April 2023
Copyright
© 2023 American Society of Civil Engineers.
History
Received: Mar 20, 2022
Accepted: Sep 14, 2022
Published online: Jan 24, 2023
Published in print: Apr 1, 2023
Discussion open until: Jun 24, 2023
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
Cited by
- Xue Lin, Caiqing Ma, Qianling Wang, Dual Jitter Suppression Mechanism-Based Cooperation Control for Multiple High-Speed Trains with Parametric Uncertainty, Mathematics, 10.3390/math11081786, 11, 8, (1786), (2023).