Paper WeBT7.3
Luo, Xiaolin (Beijing Jiaotong University), Wang, Dongming (University of California, Riverside), TANG, Tao (Beijing Jiaotong University), Zhang, Yong (Beijing Jiaotong University), Liu, Hongjie (Beijing Jiaotong University)
Data-Driven Model Predictive Control for Virtually Coupled Train Set Using Behavioral Systems Theory
Scheduled for presentation during the Invited Session "Control, Communication and Emerging Technologies in Smart Rail Systems II" (WeBT7), Wednesday, September 25, 2024,
15:10−15:30, Salon 15
2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada
This information is tentative and subject to change. Compiled on October 7, 2024
|
|
Keywords Multi-autonomous Vehicle Studies, Models, Techniques and Simulations, Cooperative Techniques and Systems, Automated Vehicle Operation, Motion Planning, Navigation
Abstract
Virtual coupling is effective to improve the flexibility and efficiency of railway services, by forming multiple train units as a virtually coupled train set (VCTS). To separate units safely by a minimal distance, relative-braking distance (RBD) is employed. However, it is numerically calculated without explicit models in practice, which makes the design of VCTS control approaches challenging. To solve this problem, this paper proposes a data-driven model predictive control (DDMPC) approach that deploys behavioral systems theory and does not need an explicit model of RBD. Specifically, Hankel matrices are constructed to formulate the unknown dynamics of VCTS, based on the prior-measured trajectories of VCTS operation. Then, using the past data and information received from the preceding unit, the controller of each unit is yielded by solving a quadratic programming problem, which is computationally efficient. Finally, experimental results demonstrate that our approach can stably operate VCTS, and saves by over 99% computation time than the nonlinear model predictive control approach.
|
|