IMECH-IR  > 非线性力学国家重点实验室
Wheel Wear Prediction of High-Speed Train Using NAR and BP Neural Networks
Fan N; Wang SW; Liu CX; Liu XM(刘小明)
会议录名称2017 IEEE INTERNATIONAL CONFERENCE ON INTERNET OF THINGS (ITHINGS) AND IEEE GREEN COMPUTING AND COMMUNICATIONS (GREENCOM) AND IEEE CYBER, PHYSICAL AND SOCIAL COMPUTING (CPSCOM) AND IEEE SMART DATA (SMARTDATA)
2017
会议名称EEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData)
会议日期JUN 21-23, 2017
会议地点Exeter, ENGLAND
摘要In this paper, the field measured wheel wear data of high-speed trains are studied by variance analysis, and prediction models are developed using NAR and BP neural networks. The results show that the wheel position has a significant effect on the wheel wear, and the position of the carriage has little influence on the wheel wear. The NAR neural network can be used to predict the dynamic change of wheel diameter and therefore to predict the wheel wear of high-speed trains. The wheel diameter data are classified and the range of wheel wear can be predicted by means of training the BP neural network.
关键词Big Data Wheel Wear Variance Analysis Nar Neural Network Prediction
WOS记录号WOS:000426972400018
资助信息The authors gratefully acknowledge the financial support from the National Natural Science Foundation of China (No. 51275126).
ISBN号978-1-5386-3066-2
URL查看原文
收录类别CPCI-S ; EI
语种英语
引用统计
文献类型会议论文
条目标识符http://dspace.imech.ac.cn/handle/311007/75556
专题非线性力学国家重点实验室
推荐引用方式
GB/T 7714
Fan N,Wang SW,Liu CX,et al. Wheel Wear Prediction of High-Speed Train Using NAR and BP Neural Networks[C],2017.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
CPCI2017011.pdf(753KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Fan N]的文章
[Wang SW]的文章
[Liu CX]的文章
百度学术
百度学术中相似的文章
[Fan N]的文章
[Wang SW]的文章
[Liu CX]的文章
必应学术
必应学术中相似的文章
[Fan N]的文章
[Wang SW]的文章
[Liu CX]的文章
相关权益政策
暂无数据
收藏/分享
文件名: CPCI2017011.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。