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 | |
Publication status | Published - Jul 2013 |
Externally published | Yes |
Bibliographical note
This paper was recommended for publication by Associate Editor H. Darabi and Editor Y. Narahari upon evaluation of the reviewers' comments.Funding
This work was supported in part by the National Basic Research Program of China (973 Program) under Grant 2009CB320601, the 111 Project of Ministry of Education of China under Grant B08015, the Natural Science Foundation of China under Grant 61020106003, Grant 61290323, and Grant 61104084, the State Administration of Foreign Experts Affairs of China's Special Program for Elite Overseas Experts (for S. Joe Qin), and funds for Creative Research Groups of China under Grant 60821063.
Keywords
- Fault diagnosis
- Industrial processes
- Principal component analysis (PCA)
- Process monitoring