Batch process monitoring and fault diagnosis based on multi-time-scale dynamic PCA models

Yuan Yao*, Furong Gao

*Corresponding author for this work

Research output: Chapter in Book/Conference Proceeding/ReportConference Paper published in a bookpeer-review

Abstract

Dynamics are inherent characteristics of batch processes, which can be divided into short time-scale dynamics within a batch duration and long time-scale dynamics across several batches. The interactions between process variables make different types of dynamics confounded. Under such situations, it is difficult to perform efficient fault diagnosis. In this paper, a batch process monitoring scheme is proposed to separate different types of process variations for modeling and perform monitoring and fault diagnosis with multi-time-scale dynamic principal component analysis (PCA) models. Simulation results show that the fault diagnosis efficiency is enhanced.

Original languageEnglish
Title of host publicationInternational Symposium on Advanced Control of Chemical Processes, ADCHEM'09 - Proceedings
PublisherIFAC Secretariat
Pages940-945
Number of pages6
EditionPART 1
ISBN (Print)9783902661548
DOIs
Publication statusPublished - 2009

Publication series

NameIFAC Proceedings Volumes (IFAC-PapersOnline)
NumberPART 1
Volume7
ISSN (Print)1474-6670

Keywords

  • Batch process
  • Dynamics
  • Fault diagnosis
  • Monitoring
  • Principal component analysis

Fingerprint

Dive into the research topics of 'Batch process monitoring and fault diagnosis based on multi-time-scale dynamic PCA models'. Together they form a unique fingerprint.

Cite this