ISBN: 978-981-11-0008-6 DOI: 10.18178/wcse.2016.06.108
Train System Identification Based on the Analysis of Real-Time Running Data
Abstract— The train operation system is a time-varying nonlinear process. Most of the traditional train
system identifications cannot describe the uncertain changes in actual operation. In this paper, we propose a
time-varying nonlinear train model by analyzing the train operation process. AM-VFF-RLS method is
applied to identify the parameters online. The simulation results verify that the model and identification
method used in this paper can identify the characteristics of train operation system online and accurately.
Index Terms— ATO; system identification; auxiliary model; recursive least square method; forgetting factor.
Jiaxi Yuan, Xiangxian Chen
Department of Instrumentation Science and Engineering, Zhejiang University, CHINA
Zhujun Ling, Wenbin Tang, Guodong Teng
Research and Development Center, Zhejiang United Science and Technology Co., Ltd, CHINA
Cite: Jiaxi Yuan, Xiangxian Chen, Zhujun Ling, Wenbin Tang, Guodong Teng, "Train System Identification Based on the Analysis of Real-Time Running Data," Proceedings of 2016 6th International Workshop on Computer Science and Engineering, pp. 622-626, Tokyo, 17-19 June, 2016.