文章基本信息

标题：Fault Diagnosis of Shield Machine Based on RFE and ELM
本地全文：下载
作者：Xuanyu Liu ; Wenbo Qi ; Yudong Wang 等
期刊名称：Engineering Letters
印刷版ISSN：1816-093X
电子版ISSN：1816-0948
出版年度：2021
卷号：29
期号：2
页码：759-764
语种：English
出版社：Newswood Ltd
摘要：Shield machine is a complex large-scale tunnelingequipment with multiple systems and driving sources. In orderto improve the accuracy of fault diagnosis for shield machine, amethod based on the combination of reverse feature elimination(RFE) and extreme learning machine (ELM) is proposed. Forthe characteristics of shield machine operation data with manydimensions and large quantity, the RFE method is introduced toreduce the dimension of the data, eliminate the redundantdimension and remove the correlation between features. Toimprove the accuracy and efficiency of fault diagnosis, the ELMneural network classifier model is built based on the extremelylearning mechanism for fault diagnosis of shield machine. Thesimulation results based on the field construction data showthat this method improves the accuracy of fault diagnosis ofshield machine significantly and has good engineeringapplication value.
关键词：Shield machine; fault diagnosis; extremely learning machine; reverse feature elimination