SIA OpenIR  > 数字工厂研究室
Correlated and weakly correlated fault detection based on variable division and ICA
Li S(李帅); Zhou XF(周晓锋); Pan FC(潘福成); Shi HB(史海波); Li KT(李开拓); Wang ZW(王中伟)
Department数字工厂研究室
Source PublicationComputers and Industrial Engineering
ISSN0360-8352
2017
Volume112Pages:320-335
Indexed BySCI ; EI
EI Accession number20173604128046
WOS IDWOS:000413126700026
Contribution Rank1
Funding OrganizationScience and Technology Project of Liaoning Province (2015106015) and the Key Laboratory of Network Control System, Chinese Academy of Sciences.
KeywordFault Detection Monitoring Variable Division Correlated And Weakly Correlated Variables Independent Component Analysis
AbstractIn many industrial processes, the correlations of multiple variables are complicated. Some variables are correlated and some are weakly correlated with others, which should be considered in process modelling and fault detection. This paper proposes a correlated and weakly correlated fault detection approach, which is mainly based on variable division and independent component analysis (ICA). A few variables are weakly correlated with others and fault detection should be implemented separately for correlated and weakly correlated subspaces. Firstly, variable division based on weighted proximity measure is presented to obtain correlated and weakly correlated variables. Then, ICA is used for fault detection in correlated subspace and weakly correlated subspace, which needs not kernel mapping or kernel parameter setting. Finally, comprehensive statistics are built based on different subspaces. The proposed method considers the correlated and weakly correlated characteristics of variables and the advantages of ICA in handling weakly correlated variables. The monitoring results of the numerical system and Tennessee Eastman (TE) process have been used to demonstrate effectiveness and superiority of the proposed approach.
Language英语
WOS HeadingsScience & Technology ; Technology
WOS SubjectComputer Science, Interdisciplinary Applications ; Engineering, Industrial
WOS KeywordINDEPENDENT COMPONENT ANALYSIS ; MAXIMAL INFORMATION COEFFICIENT ; MONITORING BATCH PROCESSES ; NONLINEAR PROCESSES ; CONTROL CHART ; DISTANCE CORRELATION ; STATISTICAL-ANALYSIS ; MULTIMODE PROCESSES ; BAYESIAN-INFERENCE ; PROCESS DISPERSION
WOS Research AreaComputer Science ; Engineering
Citation statistics
Cited Times:18[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/20964
Collection数字工厂研究室
Corresponding AuthorLi S(李帅)
Affiliation1.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
2.Key Laboratory of Network Control System, Chinese Academy of Sciences, Shenyang 110016, China
3.University of Chinese Academy of Sciences, Beijing 100049, China
Recommended Citation
GB/T 7714
Li S,Zhou XF,Pan FC,et al. Correlated and weakly correlated fault detection based on variable division and ICA[J]. Computers and Industrial Engineering,2017,112:320-335.
APA Li S,Zhou XF,Pan FC,Shi HB,Li KT,&Wang ZW.(2017).Correlated and weakly correlated fault detection based on variable division and ICA.Computers and Industrial Engineering,112,320-335.
MLA Li S,et al."Correlated and weakly correlated fault detection based on variable division and ICA".Computers and Industrial Engineering 112(2017):320-335.
Files in This Item:
File Name/Size DocType Version Access License
Correlated and weakl(1716KB)期刊论文作者接受稿开放获取ODC PDDLView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li S(李帅)]'s Articles
[Zhou XF(周晓锋)]'s Articles
[Pan FC(潘福成)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li S(李帅)]'s Articles
[Zhou XF(周晓锋)]'s Articles
[Pan FC(潘福成)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li S(李帅)]'s Articles
[Zhou XF(周晓锋)]'s Articles
[Pan FC(潘福成)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Correlated and weakly correlated fault detection based on variable division and ICA.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.