Fault detection based on functional relationship among process variables by autoassociative neural networks

Takeshi Fujiwara, Takeshi Tsushi, Hirokazu Nishitani

Research output: Contribution to journalArticle

Abstract

Some process variables measured in a plant are strictly constrained by the material and heat balance equations, rate equations and correlations. In this study, we propose a method to judge whether the state of plant operation is normal or not, by examining whether a set of process variables maintains the functional relationship specified at normal operation. The functional relationship at normal operation is identified by an autoassociative neural network (AANN) which approximates the identity mapping for a set of measured values of process variables. An effective method to search for an adequate configuration of the AANN is also presented. Abnormal operation or fault is detected by the magnitude of discrepancy between the input vector and the output vector of the trained AANN. This fault detection method is applied to a continuous flow polymerization process and compared with the conventional 3 sigma fault detection method for a single process variable.

Original languageEnglish
Pages (from-to)846-853
Number of pages8
JournalKagaku Kogaku Ronbunshu
Volume22
Issue number4
DOIs
Publication statusPublished - Jan 1 1996
Externally publishedYes

Fingerprint

Fault detection
Neural networks
Polymerization

Keywords

  • Fault detection
  • Functional relationship analysis
  • Neural network
  • Process system
  • System identification

ASJC Scopus subject areas

  • Chemistry(all)
  • Chemical Engineering(all)

Cite this

Fault detection based on functional relationship among process variables by autoassociative neural networks. / Fujiwara, Takeshi; Tsushi, Takeshi; Nishitani, Hirokazu.

In: Kagaku Kogaku Ronbunshu, Vol. 22, No. 4, 01.01.1996, p. 846-853.

Research output: Contribution to journalArticle

@article{075a0c507a4845799cae118a4bb293f2,
title = "Fault detection based on functional relationship among process variables by autoassociative neural networks",
abstract = "Some process variables measured in a plant are strictly constrained by the material and heat balance equations, rate equations and correlations. In this study, we propose a method to judge whether the state of plant operation is normal or not, by examining whether a set of process variables maintains the functional relationship specified at normal operation. The functional relationship at normal operation is identified by an autoassociative neural network (AANN) which approximates the identity mapping for a set of measured values of process variables. An effective method to search for an adequate configuration of the AANN is also presented. Abnormal operation or fault is detected by the magnitude of discrepancy between the input vector and the output vector of the trained AANN. This fault detection method is applied to a continuous flow polymerization process and compared with the conventional 3 sigma fault detection method for a single process variable.",
keywords = "Fault detection, Functional relationship analysis, Neural network, Process system, System identification",
author = "Takeshi Fujiwara and Takeshi Tsushi and Hirokazu Nishitani",
year = "1996",
month = "1",
day = "1",
doi = "10.1252/kakoronbunshu.22.846",
language = "English",
volume = "22",
pages = "846--853",
journal = "Kagaku Kogaku Ronbunshu",
issn = "0386-216X",
publisher = "Society of Chemical Engineers, Japan",
number = "4",

}

TY - JOUR

T1 - Fault detection based on functional relationship among process variables by autoassociative neural networks

AU - Fujiwara, Takeshi

AU - Tsushi, Takeshi

AU - Nishitani, Hirokazu

PY - 1996/1/1

Y1 - 1996/1/1

N2 - Some process variables measured in a plant are strictly constrained by the material and heat balance equations, rate equations and correlations. In this study, we propose a method to judge whether the state of plant operation is normal or not, by examining whether a set of process variables maintains the functional relationship specified at normal operation. The functional relationship at normal operation is identified by an autoassociative neural network (AANN) which approximates the identity mapping for a set of measured values of process variables. An effective method to search for an adequate configuration of the AANN is also presented. Abnormal operation or fault is detected by the magnitude of discrepancy between the input vector and the output vector of the trained AANN. This fault detection method is applied to a continuous flow polymerization process and compared with the conventional 3 sigma fault detection method for a single process variable.

AB - Some process variables measured in a plant are strictly constrained by the material and heat balance equations, rate equations and correlations. In this study, we propose a method to judge whether the state of plant operation is normal or not, by examining whether a set of process variables maintains the functional relationship specified at normal operation. The functional relationship at normal operation is identified by an autoassociative neural network (AANN) which approximates the identity mapping for a set of measured values of process variables. An effective method to search for an adequate configuration of the AANN is also presented. Abnormal operation or fault is detected by the magnitude of discrepancy between the input vector and the output vector of the trained AANN. This fault detection method is applied to a continuous flow polymerization process and compared with the conventional 3 sigma fault detection method for a single process variable.

KW - Fault detection

KW - Functional relationship analysis

KW - Neural network

KW - Process system

KW - System identification

UR - http://www.scopus.com/inward/record.url?scp=84945550197&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84945550197&partnerID=8YFLogxK

U2 - 10.1252/kakoronbunshu.22.846

DO - 10.1252/kakoronbunshu.22.846

M3 - Article

AN - SCOPUS:84945550197

VL - 22

SP - 846

EP - 853

JO - Kagaku Kogaku Ronbunshu

JF - Kagaku Kogaku Ronbunshu

SN - 0386-216X

IS - 4

ER -