Fault Diagnosis of Continuous Annealing Processes Using Reconstruction-based Block Contribution

Qiang LIU*, Tianyou CHAI, S. Joe QIN

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review

1 Citation (Scopus)

Abstract

Continuous annealing process line (CAPL) has complex process characteristics, such as strong correlation of large number of process variables, and the coexistence of multi- subsystems and multioperation zones. Practitioners are concerned with process faults, such as strip-break fault and roll slippage fault, whose effects often confine in a specific zone. Considering the process characteristics and fault characteristics, a fault diagnosis method is proposed. Reconstruction-based variable contribution (RBVC) is extended to reconstruction-based block contribution (RBBC) for principal component analysis (PCA) method in order to find the faulty block, and RBVC is used to determine the faulty variable. Simulation results show the effectiveness of the proposed methods, and it is applied successfully to a practical CAPL. © 2011 IFAC.
Original languageEnglish
Pages (from-to)4362-4367
Number of pages6
JournalIFAC Proceedings Volumes
Volume44
Issue number1
DOIs
Publication statusPublished - Aug 2011
Externally publishedYes
Event18th World Congress of the International Federation of Automatic Control (IFAC 2011) - , Italy
Duration: 28 Aug 20112 Sept 2011

Funding

This work was supported by the Key Project of Chinese National Programs for Fundamental Research and Development (2009CB320600), the 111 project of Ministry of Education of China (B08015), the Natural Science Foundation of China (60974091,61020106003), Program for New Century Excellent Talents in University (NCET-08-0105), and the Fundamental Research Funds for the Central Universities (N100508001).

Keywords

  • Continuous annealing processes
  • Fault diagnosis
  • Fault identification
  • Principal component analysis
  • Reconstruction-based block contribution

Fingerprint

Dive into the research topics of 'Fault Diagnosis of Continuous Annealing Processes Using Reconstruction-based Block Contribution'. Together they form a unique fingerprint.

Cite this