Work

A Neural Network‐Based Adaptive Event‐Triggered Control for Virtual Coupling High‐Speed Trains With Unknown Parameters

Year: 2025

Type: article

Abstract: ABSTRACT To cope with the effects of unknown resistance parameters, additional resistance, and high‐frequency controller updating in the cooperation control of virtual‐coupling high‐speed train systems, this paper proposes a neural network‐based adaptive event‐triggered control scheme for trains. Firstly, with the train‐to‐train communication mode, a synthetic tracking error and its converted form are proposed to restrain the speed and position errors of trains based on the train model. Then, for the unknown resistance parameters and bounded additional resistance, a radial basis function neural network (RBFNN) based adaptive control scheme is investigated to realize the cooperative operation of trains. By incorporating the event‐triggered mechanism, the communication source between the controller and actuator can be saved by reducing unnecessary controller updating. In addition, the stability condition of virtual coupling train systems is presented by the convergence analysis of the synthetic tracking error. Finally, simulation experiments are conducted to verify that the control scheme is able to realize cooperation of virtual coupling train systems in the presence of unknown parameters.

Source: International Journal of Adaptive Control and Signal Processing

DOI: 10.1002/acs.70010

Authors: Hui Zhao, Hanhong Cui, Xuewu Dai, Yuan Zhao

Institutions: Shenyang University of Technology, Northumbria University, Dalian University

Language: English

Topic: Railway Engineering and Dynamics

Subfield: Mechanical Engineering

Field: Engineering

Domain: Physical Sciences

SDG: Industry, innovation and infrastructure

Open Access status: bronze

Funders: National Natural Science Foundation of China, Natural Science Foundation of Liaoning Province