The authors propose a novel multi-model direct generalised predictive control based on predictive function control (PFC) algorithm for automatic train operation system. The proposed method facilitates autonomous driving of a train through a given guidance trajectory. Firstly, they present a multi-model architecture based on fuzzy c-means clustering algorithm. In order to obtain the optimal number of sub-linear models, they apply Xie–Beni cluster validity index. In this regards, the multi-model set is established off-line. Secondly, the proper sub-linear model is selected as the predictive model by using switching performance index at each time slot. The control variables are calculated by direct generalised predictive controller based on PFC. The control algorithm is simple, and can reduce the on-line computation time by directly identifies the unknown parameters in the controller. It can avoid recursively solving the Diophantine equations. The calculation of compensation value becomes simple by introducing PFC. Finally, simulation results are provided to show the effectiveness of the proposed scheme.


    Access

    Access via TIB


    Export, share and cite



    Multi‐model direct generalised predictive control for automatic train operation system

    Wen, Shuhuan / Yang, Jingwei / Rad, Ahmad B. et al. | Wiley | 2015

    Free access

    Automatic train operation system based on predictive fuzzy control

    Oshima, H. / Yasunobu, S. / Sekino, S.-i. | Tema Archive | 1988


    Train operation and automatic train control

    Latimer, J.B. | Engineering Index Backfile | 1921


    AUTOMATIC TRAIN OPERATION ASSISTANCE DEVICE, AUTOMATIC TRAIN OPERATION ASSISTANCE SYSTEM, AND AUTOMATIC TRAIN OPERATION ASSISTANCE METHOD

    TACHIBANA HIRONORI / SHIMAYOSHI SHOTA / UEDA KENJI et al. | European Patent Office | 2023

    Free access

    TRAIN GROUP CONTROL DEVICE AND AUTOMATIC TRAIN OPERATION SYSTEM

    YOSHIHARA KENJI / YOKOYAMA HIROYUKI | European Patent Office | 2021

    Free access