Cooperative Control of Virtually Coupled Train Sets through the Fusion of Multiple Car-Following Models.

Saved in:

Bibliographic Details
Title:	Cooperative Control of Virtually Coupled Train Sets through the Fusion of Multiple Car-Following Models.
Authors:	Mingjun Qian¹ qianmingjun@mail.lzjtu.cn, Zhiwen Huang² 12241118@stu.lzjtu.edu.cn, Chao Yin² 2055375426@qq.com
Source:	Engineering Letters. Oct2025, Vol. 33 Issue 10, p4224-4237. 14p.
Subjects:	Cooperative control systems, Automatic train control, Railroads, Optimization algorithms, Mathematical programming, Traffic flow
Abstract:	To address the challenges of stability, safety, and computational efficiency in the cooperative control of virtually coupled train sets (VCTS) under complex operational scenarios, this study proposes an integrated OPO-MCF-DMPC method that combines Online Parameter Optimization (OPO), Multiple Car-Following models (MCF), and Distributed Model Predictive Control (DMPC). First, an MCF-DMPC architecture is developed for virtual coupling by enhancing and integrating the Intelligent Driver Model (IDM), Cooperative Adaptive Cruise Control (CACC), and Full Velocity Difference Model (FVD), thereby improving precision in velocity-displacement tracking and achieving the control objective. Next, to overcome the model selection challenge, a Multi-Strategy Moth-Flame Optimization (MSMFO) algorithm is designed, incorporating chaotic mapping, adaptive flame adjustment, and stochastic mutation. Compared to conventional optimization algorithms, MSMFO improves solution fitness by 2.2%-10.2% and reduces computation time by 4.4%-16.7%. Finally, an OPO mechanism is introduced for dynamic online correction of car-following model parameters, further enhancing adaptive control capabilities. Comprehensive simulations demonstrate that the proposed OPO-MCF-DMPC method achieves a 35.8% improvement in computational efficiency over standard DMPC under long prediction horizons while satisfying the stringent stability and real-time performance requirements of VCTS operations. This advancement provides a practical and efficient solution for realizing virtual coupling in railway systems. [ABSTRACT FROM AUTHOR]
	Copyright of Engineering Letters is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	To address the challenges of stability, safety, and computational efficiency in the cooperative control of virtually coupled train sets (VCTS) under complex operational scenarios, this study proposes an integrated OPO-MCF-DMPC method that combines Online Parameter Optimization (OPO), Multiple Car-Following models (MCF), and Distributed Model Predictive Control (DMPC). First, an MCF-DMPC architecture is developed for virtual coupling by enhancing and integrating the Intelligent Driver Model (IDM), Cooperative Adaptive Cruise Control (CACC), and Full Velocity Difference Model (FVD), thereby improving precision in velocity-displacement tracking and achieving the control objective. Next, to overcome the model selection challenge, a Multi-Strategy Moth-Flame Optimization (MSMFO) algorithm is designed, incorporating chaotic mapping, adaptive flame adjustment, and stochastic mutation. Compared to conventional optimization algorithms, MSMFO improves solution fitness by 2.2%-10.2% and reduces computation time by 4.4%-16.7%. Finally, an OPO mechanism is introduced for dynamic online correction of car-following model parameters, further enhancing adaptive control capabilities. Comprehensive simulations demonstrate that the proposed OPO-MCF-DMPC method achieves a 35.8% improvement in computational efficiency over standard DMPC under long prediction horizons while satisfying the stringent stability and real-time performance requirements of VCTS operations. This advancement provides a practical and efficient solution for realizing virtual coupling in railway systems. [ABSTRACT FROM AUTHOR]
ISSN:	1816093X