Representation of process trends-IV. Induction of real-time patterns from operating data for diagnosis and supervisory control

B. R. Bakshi, George Stephanopoulos

Research output: Contribution to journalArticle

82 Citations (Scopus)

Abstract

A methodology for pattern-based supervisory control and fault diagonsis is presented, based on the multi-scale extraction of trends from process data described in Part III of this series (Bakshi and Stephanopoulos, Computers Chem. Engng 17, 1993). An explicit mapping is learned between the features extracted at multiple scales, and the corresponding process conditions, using the technique of induction by decision trees. Simple rules may be derived from the induced decision tree, to relate the relevant qualitative or quantitative features in the measured process data to process conditions. These rules are often physically interpretable and provide physical insight into the process. Industrial case studies from fine chemicals manufacturing, reactive crystallization and fed-batch fermentation are used to illustrate the characteristics of the pattern-based learning methodology and its application to process supervision and diagnosis.

Original languageEnglish (US)
Pages (from-to)303-332
Number of pages30
JournalComputers and Chemical Engineering
Volume18
Issue number4
DOIs
StatePublished - Jan 1 1994
Externally publishedYes

Fingerprint

Decision trees
Crystallization
Fermentation

ASJC Scopus subject areas

  • Chemical Engineering(all)
  • Computer Science Applications

Cite this

@article{31ef371eb9814b83859351f6d3528d6a,
title = "Representation of process trends-IV. Induction of real-time patterns from operating data for diagnosis and supervisory control",
abstract = "A methodology for pattern-based supervisory control and fault diagonsis is presented, based on the multi-scale extraction of trends from process data described in Part III of this series (Bakshi and Stephanopoulos, Computers Chem. Engng 17, 1993). An explicit mapping is learned between the features extracted at multiple scales, and the corresponding process conditions, using the technique of induction by decision trees. Simple rules may be derived from the induced decision tree, to relate the relevant qualitative or quantitative features in the measured process data to process conditions. These rules are often physically interpretable and provide physical insight into the process. Industrial case studies from fine chemicals manufacturing, reactive crystallization and fed-batch fermentation are used to illustrate the characteristics of the pattern-based learning methodology and its application to process supervision and diagnosis.",
author = "Bakshi, {B. R.} and George Stephanopoulos",
year = "1994",
month = "1",
day = "1",
doi = "10.1016/0098-1354(94)85029-1",
language = "English (US)",
volume = "18",
pages = "303--332",
journal = "Computers and Chemical Engineering",
issn = "0098-1354",
publisher = "Elsevier BV",
number = "4",

}

TY - JOUR

T1 - Representation of process trends-IV. Induction of real-time patterns from operating data for diagnosis and supervisory control

AU - Bakshi, B. R.

AU - Stephanopoulos, George

PY - 1994/1/1

Y1 - 1994/1/1

N2 - A methodology for pattern-based supervisory control and fault diagonsis is presented, based on the multi-scale extraction of trends from process data described in Part III of this series (Bakshi and Stephanopoulos, Computers Chem. Engng 17, 1993). An explicit mapping is learned between the features extracted at multiple scales, and the corresponding process conditions, using the technique of induction by decision trees. Simple rules may be derived from the induced decision tree, to relate the relevant qualitative or quantitative features in the measured process data to process conditions. These rules are often physically interpretable and provide physical insight into the process. Industrial case studies from fine chemicals manufacturing, reactive crystallization and fed-batch fermentation are used to illustrate the characteristics of the pattern-based learning methodology and its application to process supervision and diagnosis.

AB - A methodology for pattern-based supervisory control and fault diagonsis is presented, based on the multi-scale extraction of trends from process data described in Part III of this series (Bakshi and Stephanopoulos, Computers Chem. Engng 17, 1993). An explicit mapping is learned between the features extracted at multiple scales, and the corresponding process conditions, using the technique of induction by decision trees. Simple rules may be derived from the induced decision tree, to relate the relevant qualitative or quantitative features in the measured process data to process conditions. These rules are often physically interpretable and provide physical insight into the process. Industrial case studies from fine chemicals manufacturing, reactive crystallization and fed-batch fermentation are used to illustrate the characteristics of the pattern-based learning methodology and its application to process supervision and diagnosis.

UR - http://www.scopus.com/inward/record.url?scp=0027949580&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027949580&partnerID=8YFLogxK

U2 - 10.1016/0098-1354(94)85029-1

DO - 10.1016/0098-1354(94)85029-1

M3 - Article

AN - SCOPUS:0027949580

VL - 18

SP - 303

EP - 332

JO - Computers and Chemical Engineering

JF - Computers and Chemical Engineering

SN - 0098-1354

IS - 4

ER -