|
Train ride comfort evaluation method using ensemble fuzzy reasoning and its application
|
|
|
Xiangyu Zeng1,Dewang Chen2,Zan Hou3
1, State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Email : 11120319@bjtu.edu.cn
*2, State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University, Email : dwchen@bjtu.edu.cn
3, State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University, Email : 09120300@bjtu.edu.cn
|
|
|
|
Abstract
.This paper adopts acceleration rate to evaluate the train ride comfort. Three comfort evaluation models are developed by using fuzzy system theory and the parameters of fuzzy sets are determined according to the measured data. Furthermore, the outputs of the three models are integrated by an ensemble learning method to give a comprehensive evaluation index for the ride comfort. The measured data of the train operation control system in Beijing subway Yizhuang line are used to validate the models. Moreover, a field experiment is conducted, and the experiment results have a good consistency with this paper’s methods. The results indicate that the three fuzzy models have good uniformity and the ensemble learning can enhance accuracy and robustness of the comfort evaluation.
|
|
|
|
Keywords
:
acceleration rate ; comfort ; fuzzy system ; ensemble learning
|
|
|
|
URL: http://dx.doi.org/10.7321/jscse.v3.n3.9
|
|
|
|
|