Abstract
Automatic train operation systems of high-speed trains are critical to guarantee operational safety, comfort, and parking accuracy. However, implementing optimal automatic operation control is challenging due to the train's uncertain dynamics and actuator saturation. To address this issue, this paper develops a data-driven Koopman model based predictive control method for automatic train operation systems. The proposed control scheme is designed within a data-driven framework. First, using operational data of trains and the Koopman operator, an explicit linear Koopman model is built to characterize the train dynamics. Then, a model predictive controller is designed based on the Koopman model under comfort and actuator constraints. Furthermore, an online update mechanism for the Koopman model is developed to cope with the changing dynamic characteristics of trains, which reduces the accumulation errors and improves control performance. Stability analysis of the closed-loop control system is provided. Comparative simulation results validate the effectiveness of the proposed control approach.
Highlights
The automatic train operation (ATO) system plays a crucial part in ensuring the operational safety, punctuality, and comfort of high-speed trains
In this paper, a novel automatic speed tracking controller based on a data-driven Koopman model predictive control technique is proposed for automatic train operation systems of high-speed trains
An explicit linear Koopman model is employed to reflect the complex dynamics of a train, and a linear model predictive controller is designed under comfort and actuator constraints
Summary
The automatic train operation (ATO) system plays a crucial part in ensuring the operational safety, punctuality, and comfort of high-speed trains. A data-driven explicit control-oriented linear model based on Koopman operator theory is developed for the high-speed train. A novel automatic train operation controller for highspeed trains is developed by integrating the model predictive control method with the data-driven Koopman linear model, which can address the system nonlinearity and uncertainty It explicitly models the speed tracking objectives and train operating constraints to ensure the operational safety, and riding comfort. In order to capture the train dynamics with changes in environment accurately, the Koopman model is updated online when the error between the train’s speed and the reference speed exceeds a given threshold Such a design of the train model can further improve the control performance of MPC. The control method provides a feedback loop and has potential robustness with respect to system uncertainties
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
