A multi-objective optimization approach for the virtual coupling train set driving strategy

Abstract This paper presents an improved virtual coupling train set (VCTS) operation control framework to deal with the lack of optimization of speed curves in the traditional techniques. The framework takes into account the temporary speed limit on the railway line and the communication delay betwe...

Full description

Saved in:
Bibliographic Details
Main Authors: Junting Lin, Maolin Li, Xiaohui Qiu
Format: Article
Language:English
Published: SpringerOpen 2025-01-01
Series:Railway Engineering Science
Subjects:
Online Access:https://doi.org/10.1007/s40534-024-00349-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850173073261592576
author Junting Lin
Maolin Li
Xiaohui Qiu
author_facet Junting Lin
Maolin Li
Xiaohui Qiu
author_sort Junting Lin
collection DOAJ
description Abstract This paper presents an improved virtual coupling train set (VCTS) operation control framework to deal with the lack of optimization of speed curves in the traditional techniques. The framework takes into account the temporary speed limit on the railway line and the communication delay between trains, and it uses a VCTS consisting of three trains as an experimental object. It creates the virtual coupling train tracking and control process by improving the driving strategy of the leader train and using the leader–follower model. The follower train uses the improved speed curve of the leader train as its speed reference curve through knowledge migration, and this completes the multi-objective optimization of the driving strategy for the VCTS. The experimental results confirm that the deep reinforcement learning algorithm effectively achieves the optimization goal of the train driving strategy. They also reveal that the intrinsic curiosity module prioritized experience replay dueling double deep Q-network (ICM-PER-D3QN) algorithm outperforms the deep Q-network (DQN) algorithm in optimizing the driving strategy of the leader train. The ICM-PER-D3QN algorithm enhances the leader train driving strategy by an average of 57% when compared to the DQN algorithm. Furthermore, the particle swarm optimization (PSO)-based model predictive control (MPC) algorithm has also demonstrated tracking accuracy and further improved safety during VCTS operation, with an average increase of 37.7% in tracking accuracy compared to the traditional MPC algorithm.
format Article
id doaj-art-27114ff46b6b44bb81e7b7956f32ae1a
institution OA Journals
issn 2662-4745
2662-4753
language English
publishDate 2025-01-01
publisher SpringerOpen
record_format Article
series Railway Engineering Science
spelling doaj-art-27114ff46b6b44bb81e7b7956f32ae1a2025-08-20T02:19:57ZengSpringerOpenRailway Engineering Science2662-47452662-47532025-01-0133216919110.1007/s40534-024-00349-1A multi-objective optimization approach for the virtual coupling train set driving strategyJunting Lin0Maolin Li1Xiaohui Qiu2School of Automation and Electrical Engineering, Lanzhou Jiaotong UniversitySchool of Automation and Electrical Engineering, Lanzhou Jiaotong UniversitySchool of Automation and Electrical Engineering, Lanzhou Jiaotong UniversityAbstract This paper presents an improved virtual coupling train set (VCTS) operation control framework to deal with the lack of optimization of speed curves in the traditional techniques. The framework takes into account the temporary speed limit on the railway line and the communication delay between trains, and it uses a VCTS consisting of three trains as an experimental object. It creates the virtual coupling train tracking and control process by improving the driving strategy of the leader train and using the leader–follower model. The follower train uses the improved speed curve of the leader train as its speed reference curve through knowledge migration, and this completes the multi-objective optimization of the driving strategy for the VCTS. The experimental results confirm that the deep reinforcement learning algorithm effectively achieves the optimization goal of the train driving strategy. They also reveal that the intrinsic curiosity module prioritized experience replay dueling double deep Q-network (ICM-PER-D3QN) algorithm outperforms the deep Q-network (DQN) algorithm in optimizing the driving strategy of the leader train. The ICM-PER-D3QN algorithm enhances the leader train driving strategy by an average of 57% when compared to the DQN algorithm. Furthermore, the particle swarm optimization (PSO)-based model predictive control (MPC) algorithm has also demonstrated tracking accuracy and further improved safety during VCTS operation, with an average increase of 37.7% in tracking accuracy compared to the traditional MPC algorithm.https://doi.org/10.1007/s40534-024-00349-1High-speed trainsVirtual couplingMulti-objective optimizationDeep reinforcement learningKnowledge transferModel predictive control
spellingShingle Junting Lin
Maolin Li
Xiaohui Qiu
A multi-objective optimization approach for the virtual coupling train set driving strategy
Railway Engineering Science
High-speed trains
Virtual coupling
Multi-objective optimization
Deep reinforcement learning
Knowledge transfer
Model predictive control
title A multi-objective optimization approach for the virtual coupling train set driving strategy
title_full A multi-objective optimization approach for the virtual coupling train set driving strategy
title_fullStr A multi-objective optimization approach for the virtual coupling train set driving strategy
title_full_unstemmed A multi-objective optimization approach for the virtual coupling train set driving strategy
title_short A multi-objective optimization approach for the virtual coupling train set driving strategy
title_sort multi objective optimization approach for the virtual coupling train set driving strategy
topic High-speed trains
Virtual coupling
Multi-objective optimization
Deep reinforcement learning
Knowledge transfer
Model predictive control
url https://doi.org/10.1007/s40534-024-00349-1
work_keys_str_mv AT juntinglin amultiobjectiveoptimizationapproachforthevirtualcouplingtrainsetdrivingstrategy
AT maolinli amultiobjectiveoptimizationapproachforthevirtualcouplingtrainsetdrivingstrategy
AT xiaohuiqiu amultiobjectiveoptimizationapproachforthevirtualcouplingtrainsetdrivingstrategy
AT juntinglin multiobjectiveoptimizationapproachforthevirtualcouplingtrainsetdrivingstrategy
AT maolinli multiobjectiveoptimizationapproachforthevirtualcouplingtrainsetdrivingstrategy
AT xiaohuiqiu multiobjectiveoptimizationapproachforthevirtualcouplingtrainsetdrivingstrategy