Decentralized Fault Diagnosis of Continuous Annealing Processes Based on Multilevel PCA

Qiang LIU; S. Joe QIN; Tianyou CHAI

doi:10.1109/TASE.2012.2230628

Decentralized Fault Diagnosis of Continuous Annealing Processes Based on Multilevel PCA

Qiang LIU^*, S. Joe QIN^*, Tianyou CHAI^*

^*Corresponding author for this work

Research output: Journal Publications › Journal Article (refereed) › peer-review

92 Citations (Scopus)

Abstract

Process monitoring and fault diagnosis of the continuous annealing process lines (CAPLs) have been a primary concern in industry. Stable operation of the line is essential to final product quality and continuous processing of the upstream and downstream materials. In this paper, amultilevel principal component analysis (MLPCA)-based fault diagnosis method is proposed to provide meaningful monitoring of the underlying process and help diagnose faults. First, multiblock consensus principal component analysis (CPCA) is extended to MLPCA to model the large scale continuous annealing process. Secondly, a decentralized fault diagnosis approach is designed based on the proposed MLPCA algorithm. Finally, experiment results on an industrial CAPL are obtained to demonstrate the effectiveness of the proposed method. © 2012 IEEE.

Original language	English
Pages (from-to)	687-698
Number of pages	12
Journal	IEEE Transactions on Automation Science and Engineering
Volume	10
Issue number	3
Early online date	24 Jan 2013
DOIs	https://doi.org/10.1109/TASE.2012.2230628
Publication status	Published - Jul 2013
Externally published	Yes

Keywords

Fault diagnosis
Industrial processes
Principal component analysis (PCA)
Process monitoring

Access to Document

10.1109/TASE.2012.2230628

Cite this

@article{012fa6e146e34df69ab5687f980e45d3,

title = "Decentralized Fault Diagnosis of Continuous Annealing Processes Based on Multilevel PCA",

abstract = "Process monitoring and fault diagnosis of the continuous annealing process lines (CAPLs) have been a primary concern in industry. Stable operation of the line is essential to final product quality and continuous processing of the upstream and downstream materials. In this paper, amultilevel principal component analysis (MLPCA)-based fault diagnosis method is proposed to provide meaningful monitoring of the underlying process and help diagnose faults. First, multiblock consensus principal component analysis (CPCA) is extended to MLPCA to model the large scale continuous annealing process. Secondly, a decentralized fault diagnosis approach is designed based on the proposed MLPCA algorithm. Finally, experiment results on an industrial CAPL are obtained to demonstrate the effectiveness of the proposed method. {\textcopyright} 2012 IEEE.",

keywords = "Fault diagnosis, Industrial processes, Principal component analysis (PCA), Process monitoring",

author = "Qiang LIU and QIN, {S. Joe} and Tianyou CHAI",

year = "2013",

month = jul,

doi = "10.1109/TASE.2012.2230628",

language = "English",

volume = "10",

pages = "687--698",

journal = "IEEE Transactions on Automation Science and Engineering",

issn = "1545-5955",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "3",

}

TY - JOUR

T1 - Decentralized Fault Diagnosis of Continuous Annealing Processes Based on Multilevel PCA

AU - LIU, Qiang

AU - QIN, S. Joe

AU - CHAI, Tianyou

PY - 2013/7

Y1 - 2013/7

N2 - Process monitoring and fault diagnosis of the continuous annealing process lines (CAPLs) have been a primary concern in industry. Stable operation of the line is essential to final product quality and continuous processing of the upstream and downstream materials. In this paper, amultilevel principal component analysis (MLPCA)-based fault diagnosis method is proposed to provide meaningful monitoring of the underlying process and help diagnose faults. First, multiblock consensus principal component analysis (CPCA) is extended to MLPCA to model the large scale continuous annealing process. Secondly, a decentralized fault diagnosis approach is designed based on the proposed MLPCA algorithm. Finally, experiment results on an industrial CAPL are obtained to demonstrate the effectiveness of the proposed method. © 2012 IEEE.

AB - Process monitoring and fault diagnosis of the continuous annealing process lines (CAPLs) have been a primary concern in industry. Stable operation of the line is essential to final product quality and continuous processing of the upstream and downstream materials. In this paper, amultilevel principal component analysis (MLPCA)-based fault diagnosis method is proposed to provide meaningful monitoring of the underlying process and help diagnose faults. First, multiblock consensus principal component analysis (CPCA) is extended to MLPCA to model the large scale continuous annealing process. Secondly, a decentralized fault diagnosis approach is designed based on the proposed MLPCA algorithm. Finally, experiment results on an industrial CAPL are obtained to demonstrate the effectiveness of the proposed method. © 2012 IEEE.

KW - Fault diagnosis

KW - Industrial processes

KW - Principal component analysis (PCA)

KW - Process monitoring

UR - http://www.scopus.com/inward/record.url?scp=84892564502&partnerID=8YFLogxK

U2 - 10.1109/TASE.2012.2230628

DO - 10.1109/TASE.2012.2230628

M3 - Journal Article (refereed)

SN - 1545-5955

VL - 10

SP - 687

EP - 698

JO - IEEE Transactions on Automation Science and Engineering

JF - IEEE Transactions on Automation Science and Engineering

IS - 3

ER -

Decentralized Fault Diagnosis of Continuous Annealing Processes Based on Multilevel PCA

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this