Data-Driven Koopman Model Predictive Control for Optimal Operation of High-Speed Trains

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.

[1]  Hui Yang,et al.  Online Regulation of High Speed Train Trajectory Control Based on T-S Fuzzy Bilinear Model , 2016, IEEE Transactions on Intelligent Transportation Systems.

[2]  B. O. Koopman,et al.  Hamiltonian Systems and Transformation in Hilbert Space. , 1931, Proceedings of the National Academy of Sciences of the United States of America.

[3]  V K Garg,et al.  Dynamics of railway vehicle systems , 1984 .

[4]  Singiresu S. Rao.  Engineering Optimization : Theory and Practice , 2010 .

[5]  Igor Mezic,et al.  Linear predictors for nonlinear dynamical systems: Koopman operator meets model predictive control , 2016, Autom..

[6]  Zehui Mao,et al.  Adaptive Actuator Compensation of Position Tracking for High-Speed Trains With Disturbances , 2018, IEEE Transactions on Vehicular Technology.

[7]  Oliver Sawodny,et al.  Thermal Management for the Cabin of a Battery Electric Vehicle Considering Passengers’ Comfort , 2020, IEEE Transactions on Control Systems Technology.

[8]  D. Limón,et al.  Input-to-State Stability: A Unifying Framework for Robust Model Predictive Control , 2009 .

[9]  R. Brent Gillespie,et al.  Data-Driven Control of Soft Robots Using Koopman Operator Theory , 2021, IEEE Transactions on Robotics.

[10]  Felix Schmid,et al.  A review of methods to measure and calculate train resistances , 2000 .

[11]  Xi Wang,et al.  Robust Distributed Cruise Control of Multiple High-Speed Trains Based on Disturbance Observer , 2021, IEEE Transactions on Intelligent Transportation Systems.

[12]  M. Branicky.  Multiple Lyapunov functions and other analysis tools for switched and hybrid systems , 1998, IEEE Trans. Autom. Control..

[13]  Na Qin,et al.  Tracking Control via Iterative Learning for High-Speed Trains With Distributed Input Constraints , 2019, IEEE Access.

[14]  Hui Yang,et al.  Real-time optimal control of tracking running for high-speed electric multiple unit , 2017, Inf. Sci..

[15]  Cheng Wang,et al.  Braking process identification of high-speed trains for automatic train stop control. , 2020, ISA transactions.

[16]  Jian-Xin Xu,et al.  D-Type ILC Based Dynamic Modeling and Norm Optimal ILC for High-Speed Trains , 2018, IEEE Transactions on Control Systems Technology.

[17]  Yuan Wang,et al.  Reinforcement learning approach for optimal control of multiple electric locomotives in a heavy-haul freight train: A Double-Switch-Q-network architecture , 2020, Knowl. Based Syst..

[18]  Tao Tang,et al.  An intelligent train control approach based on the monte carlo reinforcement learning algorithm , 2018, 2018 21st International Conference on Intelligent Transportation Systems (ITSC).

[19]  Hairong Dong,et al.  Adaptive Control for Automatic High-speed Trains Operation by Integral Reinforcement Learning and Parameter Identification , 2019, 2019 Chinese Control Conference (CCC).

[20]  Xiaoyun Feng,et al.  A Novel Iterative Learning Approach for Tracking Control of High-Speed Trains Subject to Unknown Time-Varying Delay , 2022, IEEE Transactions on Automation Science and Engineering.

[21]  H. J. Ferreau,et al.  An online active set strategy to overcome the limitations of explicit MPC , 2008 .

[22]  Hassan Arbabi.  Introduction to Koopman operator theory of dynamical systems , 2018 .

[23]  Tong Zhang,et al.  Adaptive Fault-Tolerant Sliding Mode Control for High-Speed Trains With Actuator Faults Under Strong Winds , 2020, IEEE Access.

[24]  Zehui Mao,et al.  Adaptive Control Design and Evaluation for Multibody High-speed Train Dynamic Models , 2020 .

[25]  Clarence W. Rowley,et al.  A Data–Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition , 2014, Journal of Nonlinear Science.

[26]  I. Mezić,et al.  Applied Koopmanism. , 2012, Chaos.

[27]  Kunpeng Zhang,et al.  Speed tracking control using an ANFIS model for high-speed electric multiple unit , 2014 .

[28]  Anders Rantzer,et al.  Computation of piecewise quadratic Lyapunov functions for hybrid systems , 1997, 1997 European Control Conference (ECC).

[29]  Peng Xiang,et al.  Cooperative $H_{\infty}$ Control of Multiple High-Speed Trains With Saturation Constraints , 2019, IEEE Access.

[30]  Dong Wei,et al.  Integrated Optimal Design of Speed Profile and Fuzzy PID Controller for Train With Multifactor Consideration , 2020, IEEE Access.

[31]  Eduardo F. Camacho,et al.  On the stability of constrained MPC without terminal constraint , 2006, IEEE Transactions on Automatic Control.

[32]  Constantinos Theodoropoulos,et al.  Stability Analysis of Piecewise Affine Systems with Multi-model Model Predictive Control , 2018, Autom..

[33]  A.G. Alleyne,et al.  A survey of iterative learning control , 2006, IEEE Control Systems.

[34]  Zheng Xu,et al.  Optimal Operation of High-Speed Trains Using Hybrid Model Predictive Control , 2018 .

[35]  Xiaoyun Feng,et al.  Robust Stochastic Control for High-Speed Trains With Nonlinearity, Parametric Uncertainty, and Multiple Time-Varying Delays , 2018, IEEE Transactions on Intelligent Transportation Systems.

[36]  Hui Yang,et al.  Multi-ANFIS Model Based Synchronous Tracking Control of High-Speed Electric Multiple Unit , 2018, IEEE Transactions on Fuzzy Systems.