Monitoring of an industrial dearomatisation process

Samuli Bergman; Mauri Sourander; Sirkka-Liisa Jämsä-Jounela

doi:10.3182/20020721-6-ES-1901.01364

Monitoring of an industrial dearomatisation process

Samuli Bergman, Mauri Sourander, Sirkka-Liisa Jämsä-Jounela

Research output: Contribution to journal › Conference article › Scientific › peer-review

1 Citation (Scopus)

313 Downloads (Pure)

Abstract

Process monitoring methods have been studied widely in recent years, and several industrial applications have been published. Early detection and identification of abnormal and undesired process states and equipment failures are essential requirements for safe and reliable processes. This helps to reduce the amount of production losses during abnormal events. In this paper, statistical multivariate methods and neural networks applied in monitoring of an industrial dearomatisation process are compared. No appriori process knowledge for the methods were assumed. The data for the comparison were generated with a dynamic simulator model of the process. Special emphasis was put on a case of internal leak in a heat exchanger

Original language	English
Pages (from-to)	331-336
Journal	IFAC PROCEEDINGS VOLUMES
Volume	35
Issue number	1
DOIs	https://doi.org/10.3182/20020721-6-ES-1901.01364
Publication status	Published - 2002
MoE publication type	A4 Conference publication
Event	IFAC World Congress - Barcelona, Spain Duration: 21 Jul 2002 → 26 Jul 2002 Conference number: 19

Keywords

chemical industry
fault diagnosis
neural networks
statistical process control

Access to Document

10.3182/20020721-6-ES-1901.01364

monitoring of an industrial dearomatisation processAccepted author manuscript, 417 KB

Cite this

@article{cce482d3377547a49bbbeabc1160685e,

title = "Monitoring of an industrial dearomatisation process",

abstract = "Process monitoring methods have been studied widely in recent years, and several industrial applications have been published. Early detection and identification of abnormal and undesired process states and equipment failures are essential requirements for safe and reliable processes. This helps to reduce the amount of production losses during abnormal events. In this paper, statistical multivariate methods and neural networks applied in monitoring of an industrial dearomatisation process are compared. No appriori process knowledge for the methods were assumed. The data for the comparison were generated with a dynamic simulator model of the process. Special emphasis was put on a case of internal leak in a heat exchanger",

keywords = "chemical industry, fault diagnosis, neural networks, statistical process control, chemical industry, fault diagnosis, neural networks, statistical process control, chemical industry, fault diagnosis, neural networks, statistical process control",

author = "Samuli Bergman and Mauri Sourander and Sirkka-Liisa J{\"a}ms{\"a}-Jounela",

year = "2002",

doi = "10.3182/20020721-6-ES-1901.01364",

language = "English",

volume = "35",

pages = "331--336",

journal = "IFAC PROCEEDINGS VOLUMES",

issn = "1474-6670",

publisher = "International Federation of Automatic Control (IFAC)",

number = "1",

note = "IFAC World Congress, IFAC ; Conference date: 21-07-2002 Through 26-07-2002",

}

TY - JOUR

T1 - Monitoring of an industrial dearomatisation process

AU - Bergman, Samuli

AU - Sourander, Mauri

AU - Jämsä-Jounela, Sirkka-Liisa

N1 - Conference code: 19

PY - 2002

Y1 - 2002

N2 - Process monitoring methods have been studied widely in recent years, and several industrial applications have been published. Early detection and identification of abnormal and undesired process states and equipment failures are essential requirements for safe and reliable processes. This helps to reduce the amount of production losses during abnormal events. In this paper, statistical multivariate methods and neural networks applied in monitoring of an industrial dearomatisation process are compared. No appriori process knowledge for the methods were assumed. The data for the comparison were generated with a dynamic simulator model of the process. Special emphasis was put on a case of internal leak in a heat exchanger

AB - Process monitoring methods have been studied widely in recent years, and several industrial applications have been published. Early detection and identification of abnormal and undesired process states and equipment failures are essential requirements for safe and reliable processes. This helps to reduce the amount of production losses during abnormal events. In this paper, statistical multivariate methods and neural networks applied in monitoring of an industrial dearomatisation process are compared. No appriori process knowledge for the methods were assumed. The data for the comparison were generated with a dynamic simulator model of the process. Special emphasis was put on a case of internal leak in a heat exchanger

KW - chemical industry

KW - fault diagnosis

KW - neural networks

KW - statistical process control

KW - chemical industry

KW - fault diagnosis

KW - neural networks

KW - statistical process control

KW - chemical industry

KW - fault diagnosis

KW - neural networks

KW - statistical process control

U2 - 10.3182/20020721-6-ES-1901.01364

DO - 10.3182/20020721-6-ES-1901.01364

M3 - Conference article

SN - 1474-6670

VL - 35

SP - 331

EP - 336

JO - IFAC PROCEEDINGS VOLUMES

JF - IFAC PROCEEDINGS VOLUMES

IS - 1

T2 - IFAC World Congress

Y2 - 21 July 2002 through 26 July 2002

ER -

Monitoring of an industrial dearomatisation process

Abstract

Keywords

Access to Document

Fingerprint

Cite this