Representation of process trends-Part I. A formal representation framework

J. T Y Cheung, George Stephanopoulos

Research output: Contribution to journalArticle

190 Citations (Scopus)

Abstract

A formal methodology capable of transforming time-records of process variables into meaningful and explicit descriptions of process trends in real-time is presented in this paper. The representation is based on the formal definition of "temporal episodes," which provide descriptions of trends by constructing "histories of episodes" making explicitly all the important "domain landmark values" specified by the user as well as the "geometric landmark values" generic to trends. Model inaccuracies are confined by establishing specific measures of information lost in the descriptions and keeping them below those of the process models. Despite the simplicity of the representation primitives, it is shown that the representation can provide complete, correct, robust and very compact models for process trend histories. In contrast to pure qualitative descriptions, the new representation contains sufficient quantitative information to allow for powerful inferences of the trends of the unmeasure variables.

Original languageEnglish (US)
Pages (from-to)495-510
Number of pages16
JournalComputers and Chemical Engineering
Volume14
Issue number4-5
DOIs
StatePublished - Jan 1 1990
Externally publishedYes

ASJC Scopus subject areas

  • Chemical Engineering(all)
  • Control and Systems Engineering

Cite this

Representation of process trends-Part I. A formal representation framework. / Cheung, J. T Y; Stephanopoulos, George.

In: Computers and Chemical Engineering, Vol. 14, No. 4-5, 01.01.1990, p. 495-510.

Research output: Contribution to journalArticle

@article{ffdca7cc03304453adfa59c886c4ca70,
title = "Representation of process trends-Part I. A formal representation framework",
abstract = "A formal methodology capable of transforming time-records of process variables into meaningful and explicit descriptions of process trends in real-time is presented in this paper. The representation is based on the formal definition of {"}temporal episodes,{"} which provide descriptions of trends by constructing {"}histories of episodes{"} making explicitly all the important {"}domain landmark values{"} specified by the user as well as the {"}geometric landmark values{"} generic to trends. Model inaccuracies are confined by establishing specific measures of information lost in the descriptions and keeping them below those of the process models. Despite the simplicity of the representation primitives, it is shown that the representation can provide complete, correct, robust and very compact models for process trend histories. In contrast to pure qualitative descriptions, the new representation contains sufficient quantitative information to allow for powerful inferences of the trends of the unmeasure variables.",
author = "Cheung, {J. T Y} and George Stephanopoulos",
year = "1990",
month = "1",
day = "1",
doi = "10.1016/0098-1354(90)87023-I",
language = "English (US)",
volume = "14",
pages = "495--510",
journal = "Computers and Chemical Engineering",
issn = "0098-1354",
publisher = "Elsevier BV",
number = "4-5",

}

TY - JOUR

T1 - Representation of process trends-Part I. A formal representation framework

AU - Cheung, J. T Y

AU - Stephanopoulos, George

PY - 1990/1/1

Y1 - 1990/1/1

N2 - A formal methodology capable of transforming time-records of process variables into meaningful and explicit descriptions of process trends in real-time is presented in this paper. The representation is based on the formal definition of "temporal episodes," which provide descriptions of trends by constructing "histories of episodes" making explicitly all the important "domain landmark values" specified by the user as well as the "geometric landmark values" generic to trends. Model inaccuracies are confined by establishing specific measures of information lost in the descriptions and keeping them below those of the process models. Despite the simplicity of the representation primitives, it is shown that the representation can provide complete, correct, robust and very compact models for process trend histories. In contrast to pure qualitative descriptions, the new representation contains sufficient quantitative information to allow for powerful inferences of the trends of the unmeasure variables.

AB - A formal methodology capable of transforming time-records of process variables into meaningful and explicit descriptions of process trends in real-time is presented in this paper. The representation is based on the formal definition of "temporal episodes," which provide descriptions of trends by constructing "histories of episodes" making explicitly all the important "domain landmark values" specified by the user as well as the "geometric landmark values" generic to trends. Model inaccuracies are confined by establishing specific measures of information lost in the descriptions and keeping them below those of the process models. Despite the simplicity of the representation primitives, it is shown that the representation can provide complete, correct, robust and very compact models for process trend histories. In contrast to pure qualitative descriptions, the new representation contains sufficient quantitative information to allow for powerful inferences of the trends of the unmeasure variables.

UR - http://www.scopus.com/inward/record.url?scp=0025418386&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025418386&partnerID=8YFLogxK

U2 - 10.1016/0098-1354(90)87023-I

DO - 10.1016/0098-1354(90)87023-I

M3 - Article

VL - 14

SP - 495

EP - 510

JO - Computers and Chemical Engineering

JF - Computers and Chemical Engineering

SN - 0098-1354

IS - 4-5

ER -