An autonomous valve stiction detection system based on data characterization

Alexey Zakharov, Elena Zattoni, Lei Xie, Octavio Pozo Garcia, Sirkka-Liisa Jämsä-Jounela

Research output: Contribution to journalArticleScientificpeer-review

23 Citations (Scopus)
200 Downloads (Pure)

Abstract

This paper proposes a valve stiction detection system which selects valve stiction
detection algorithms based on characterizations of the data. For this purpose, novel data feature indexes are proposed, which quantify the presence of oscillations, meannonstationarity, noise and nonlinearities in a given data sequence. The selection is then performed according to the conditions on the index values in which each method can be applied successfully. Finally, the stiction detection decision is given by combining the detection decisions made by the selected methods. The paper ends demonstrating the effectiveness of the proposed valve stiction detection system with benchmark industrial data.
Original languageEnglish
Pages (from-to)1507-1518
JournalControl Engineering Practice
Volume21
Issue number11
DOIs
Publication statusPublished - 2013
MoE publication typeA1 Journal article-refereed

Keywords

  • valves
  • stiction
  • oscillations
  • control loops
  • fault detection
  • diagnosis
  • industrial applications

Fingerprint Dive into the research topics of 'An autonomous valve stiction detection system based on data characterization'. Together they form a unique fingerprint.

  • Cite this