A fault detection technique for the steel manufacturing process based on a normal pattern library

Takehide Hirata, Yoshinobu Kawahara, Masashi Sugiyama, Kazuya Asano

Research output: Contribution to journalConference article

Abstract

Fault detection is increasingly important in the steel manufacturing process. If faults occur, the consequences can be extremely serious in terms of human life, environmental impact and/or economic loss. Therefore, it is necessary to prevent potential accidents by detecting faults as early as possible. However, there are various kinds of faults, and most faults have only a few or even no precedents in the past. Since it is very difficult to obtain time-series data during accidents, the key is to detect the difference from the normal state by utilizing only data under normal operation. As another problem in the steel manufacturing process, each process comprises many thousands of pieces of equipment, and it would be very difficult to construct a fault detection model manually for each of these devices. Therefore, a technique which makes it possible to construct each model and adjust its parameters automatically is required. In order to solve these two major problems, this study proposes a new fault detection concept based on the pattern library. Furthermore, a combination of a static pattern library and a dynamic pattern library is discussed as a means of covering as many pieces of equipment as possible. Offline numerical simulations for both static and dynamic equipment were conducted, and the possibility of the proposed technique was confirmed.

Original languageEnglish
Pages (from-to)871-876
Number of pages6
JournalIFAC-PapersOnLine
Volume28
Issue number21
DOIs
Publication statusPublished - Sep 1 2015
Event9th IFAC Symposium on Fault Detection, Supervision and Safety for Technical Processes, SAFEPROCESS 2015 - Paris, France
Duration: Sep 2 2015Sep 4 2015

Fingerprint

Fault detection
Steel
Accidents
Environmental impact
Time series
Economics
Computer simulation

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering

Cite this

A fault detection technique for the steel manufacturing process based on a normal pattern library. / Hirata, Takehide; Kawahara, Yoshinobu; Sugiyama, Masashi; Asano, Kazuya.

In: IFAC-PapersOnLine, Vol. 28, No. 21, 01.09.2015, p. 871-876.

Research output: Contribution to journalConference article

Hirata, Takehide ; Kawahara, Yoshinobu ; Sugiyama, Masashi ; Asano, Kazuya. / A fault detection technique for the steel manufacturing process based on a normal pattern library. In: IFAC-PapersOnLine. 2015 ; Vol. 28, No. 21. pp. 871-876.
@article{7688f019aa644ef8850fdd34a9d18553,
title = "A fault detection technique for the steel manufacturing process based on a normal pattern library",
abstract = "Fault detection is increasingly important in the steel manufacturing process. If faults occur, the consequences can be extremely serious in terms of human life, environmental impact and/or economic loss. Therefore, it is necessary to prevent potential accidents by detecting faults as early as possible. However, there are various kinds of faults, and most faults have only a few or even no precedents in the past. Since it is very difficult to obtain time-series data during accidents, the key is to detect the difference from the normal state by utilizing only data under normal operation. As another problem in the steel manufacturing process, each process comprises many thousands of pieces of equipment, and it would be very difficult to construct a fault detection model manually for each of these devices. Therefore, a technique which makes it possible to construct each model and adjust its parameters automatically is required. In order to solve these two major problems, this study proposes a new fault detection concept based on the pattern library. Furthermore, a combination of a static pattern library and a dynamic pattern library is discussed as a means of covering as many pieces of equipment as possible. Offline numerical simulations for both static and dynamic equipment were conducted, and the possibility of the proposed technique was confirmed.",
author = "Takehide Hirata and Yoshinobu Kawahara and Masashi Sugiyama and Kazuya Asano",
year = "2015",
month = "9",
day = "1",
doi = "10.1016/j.ifacol.2015.09.636",
language = "English",
volume = "28",
pages = "871--876",
journal = "IFAC-PapersOnLine",
issn = "2405-8963",
publisher = "IFAC Secretariat",
number = "21",

}

TY - JOUR

T1 - A fault detection technique for the steel manufacturing process based on a normal pattern library

AU - Hirata, Takehide

AU - Kawahara, Yoshinobu

AU - Sugiyama, Masashi

AU - Asano, Kazuya

PY - 2015/9/1

Y1 - 2015/9/1

N2 - Fault detection is increasingly important in the steel manufacturing process. If faults occur, the consequences can be extremely serious in terms of human life, environmental impact and/or economic loss. Therefore, it is necessary to prevent potential accidents by detecting faults as early as possible. However, there are various kinds of faults, and most faults have only a few or even no precedents in the past. Since it is very difficult to obtain time-series data during accidents, the key is to detect the difference from the normal state by utilizing only data under normal operation. As another problem in the steel manufacturing process, each process comprises many thousands of pieces of equipment, and it would be very difficult to construct a fault detection model manually for each of these devices. Therefore, a technique which makes it possible to construct each model and adjust its parameters automatically is required. In order to solve these two major problems, this study proposes a new fault detection concept based on the pattern library. Furthermore, a combination of a static pattern library and a dynamic pattern library is discussed as a means of covering as many pieces of equipment as possible. Offline numerical simulations for both static and dynamic equipment were conducted, and the possibility of the proposed technique was confirmed.

AB - Fault detection is increasingly important in the steel manufacturing process. If faults occur, the consequences can be extremely serious in terms of human life, environmental impact and/or economic loss. Therefore, it is necessary to prevent potential accidents by detecting faults as early as possible. However, there are various kinds of faults, and most faults have only a few or even no precedents in the past. Since it is very difficult to obtain time-series data during accidents, the key is to detect the difference from the normal state by utilizing only data under normal operation. As another problem in the steel manufacturing process, each process comprises many thousands of pieces of equipment, and it would be very difficult to construct a fault detection model manually for each of these devices. Therefore, a technique which makes it possible to construct each model and adjust its parameters automatically is required. In order to solve these two major problems, this study proposes a new fault detection concept based on the pattern library. Furthermore, a combination of a static pattern library and a dynamic pattern library is discussed as a means of covering as many pieces of equipment as possible. Offline numerical simulations for both static and dynamic equipment were conducted, and the possibility of the proposed technique was confirmed.

UR - http://www.scopus.com/inward/record.url?scp=84992489190&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84992489190&partnerID=8YFLogxK

U2 - 10.1016/j.ifacol.2015.09.636

DO - 10.1016/j.ifacol.2015.09.636

M3 - Conference article

AN - SCOPUS:84992489190

VL - 28

SP - 871

EP - 876

JO - IFAC-PapersOnLine

JF - IFAC-PapersOnLine

SN - 2405-8963

IS - 21

ER -