Time-Position Trajectory Prediction of Trains in Virtual Coupling Based on ATT-CNN-BiLSTM

被引：0

作者：

Chai M. ^{[1
,2
]}

Liu H. ^{[3
]}

Su H. ^{[3
]}

Tang T. ^{[1
]}

Liu H. ^{[3
]}

机构：

[1] State Key Laboratory of Advanced Rail Autonomous Operation, Beijing Jiaotong University, Beijing

[2] National Engineering Research Center of Rail Transportation Operation and Control System, Beijing Jiaotong University, Beijing

[3] School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing

来源：

Tiedao Xuebao/Journal of the China Railway Society | 2024年 / 46卷 / 06期

关键词：

attention mechanism; bi-directional LSTM; deep learning; train state prediction; virtual coupling;

D O I：

10.3969/j.issn.1001-8360.2024.06.009

中图分类号：

学科分类号：

摘要：

In virtual coupling, predicting operation states of trains accurately is a central problem in ensuring the smooth tracking of trains. Considering the ever-changing characteristics of train operations, a spatio-temporal trajectory prediction method was proposed based on convolutional bidirectional long short-term memory neural network with attention mechanism (ATT-CNN-BiLSTM). To address the problem of imbalanced data caused by few abnormal train operation scenarios in historical train operation data, convolutional neural network and bi-directional long short-term memory network were used to extract feature correlations between dimensions of train operation data, with attention mechanism added to enhance generalization ability. Meanwhile, the runtime verification method was introduced to monitor the prediction results online to reduce the operational risks caused by prediction errors. Based on the data of Chengdu Metro Line 8 for experiment, the ATT-CNN-BiLSTM model proposed in this paper was evaluated by baseline model and ablation experiment with 5 evaluation indexes. The results show that the prediction error of the model for abnormal scenes is reduced by at least 9. 626%. © 2024 Science Press. All rights reserved.

引用

页码：80 / 89

页数：9

共 18 条

[1] BOCK U, BIKKER G., Design and Development of a Future Freight Train Concept-Virtually Coupled Train Formations, IFAC Proceedings Volumes, 33, 9, pp. 395-400, (2000)
[2] LIU Y, LIU R, WEI C, Et al., Distributed Model Predictive Control Strategy for Constrained High-speed Virtually Coupled Train Set, IEEE Transactions on Vehicular Technology, 71, 1, pp. 171-183, (2021)
[3] SU S, LIU W, ZHU Q, Et al., A Cooperative Collision-avoidance Control Methodology for Virtual Coupling Trains, Accident Analysis & Prevention, 173, (2022)
[4] FELEZ J, KIM Y, BORRELLI F., A Model Predictive Control Approach for Virtual Coupling in Railways [J], IEEE Transactions on Intelligent Transportation Systems, 20, 7, pp. 2728-2739, (2019)
[5] LUO X, TANG T, YIN J, Et al., A Robust Mpc Approach with Controller Tuning for Close Following Operation of Virtually Coupled Train Set, Transportation Research Part C : Emerging Technologies, 151, (2023)
[6] LIU Y, ZHOU Y, SU S, Et al., An Analytical Optimal Control Approach for Virtually Coupled High-speed Trains with Local and String Stability, Transportation Research Part C :Emerging Technologies, 125, (2021)
[7] PARK J, LEE B H, EUN Y., Virtual Coupling of Railway Vehicles : Gap Reference for Merge and Separation, Robust Control and Position Measurement, IEEE Transactions on Intelligent Transportation Systems, 23, 2, pp. 1085-1096, (2020)
[8] WEI Wei, ZHAO Xiaoqiang, DING Yanhua, Et al., Fault Diagnosis of Vehicle On-board Equipment Based on BiLSTM and Attention Mechanism, Journal of the China Railway Society, 44, 11, pp. 53-62, (2022)
[9] WANG H, HAN Z, LIU Z, Et al., Deep Reinforcement Learning Based Active Pantograph Control Strategy in Highspeed Railway, IEEE Transactions on Vehicular Technology, 72, 1, pp. 227-238, (2022)
[10] LIU H, CHAI M, LIU H, Et al., A Novel Long Short Term Memory Network Based Train Dynamic Identification for Virtual Coupling, 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC), pp. 1427-1432, (2022)

← 1 2 →