Citation

Song L, Guo W, Li F, Liu L. China Saf. Sci. J. 2022; 32(6): 131-136.

Copyright

(Copyright © 2022, China Occupational Safety and Health Association, Publisher Gai Xue bao)

DOI

10.16265/j.cnki.issn1003-3033.2022.06.2683

PMID

unavailable

Abstract

Considering time-varying problems and nonlinear model of high-speed trains during operation, an ADRC algorithm for train velocity based on radial basis function (RBF) neural network (RBFNN) optimization was proposed. Firstly, a train dynamics equation was established based on single mass point model. Secondly, ADRC technology was applied to trains. With their external interference as expansion part, ADRC controller based on RBFNN optimization was designed by using nonlinear error feedback control law to observe and compensate system disturbance in real time. Then, target speed curve was simulated and tracked with parameters of crh380 train to verify tracking performance of RBF-ADRC controller. Finally, it was compared with the traditional ADRC controller in tracking accuracy and tracking error. The results show that its tracking accuracy is higher than that of the traditional one, and tracking error is smaller, which is suitable for strict operation conditions of trains. © 2022 China Safety Science Journal. All rights reserved.

Language: zh