Hierarchical frequent sequence mining algorithm for the analysis of alarm cascades in chemical processes

Gyula Dorgo, Kristof Varga, J. Abonyi

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Faults and malfunctions on complex chemical production systems generate alarm cascades that hinder the work of the operators and make fault diagnosis a complex and challenging task. The core concept of our work is the incorporation of the hierarchical structure of the technology in a multi-temporal sequence mining algorithm to group the large number of variables. The spreading of the effect of malfunctions over the plant is thoroughly traceable on the higher levels of the hierarchy, while the critical elements of the spillover effect can be detected on the lower levels. Confidence-based goal-oriented measures have been proposed to describe the orientation of fault propagation providing a good insight into the causality on a local level of the process, while the network-based representation yields a global view of causal connections. The effectiveness of the proposed methodology is presented in terms of the analysis of the alarm and event-log database of an industrial delayed-coker plant, where the complexity of the problem and the size of the event-log database requires a hierarchical constraint-based representation.

Original languageEnglish
JournalIEEE Access
DOIs
Publication statusAccepted/In press - Aug 31 2018

Fingerprint

Alarm systems
Failure analysis

Keywords

  • alarm management
  • Chemical processes
  • Chemicals
  • Data mining
  • Databases
  • Fault detection
  • fault detection and diagnosis
  • hierarchical analysis
  • Monitoring
  • multi-temporal sequence mining
  • networks
  • Production systems

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

Hierarchical frequent sequence mining algorithm for the analysis of alarm cascades in chemical processes. / Dorgo, Gyula; Varga, Kristof; Abonyi, J.

In: IEEE Access, 31.08.2018.

Research output: Contribution to journalArticle

@article{becb1faa224b421595d98c1d953f2376,
title = "Hierarchical frequent sequence mining algorithm for the analysis of alarm cascades in chemical processes",
abstract = "Faults and malfunctions on complex chemical production systems generate alarm cascades that hinder the work of the operators and make fault diagnosis a complex and challenging task. The core concept of our work is the incorporation of the hierarchical structure of the technology in a multi-temporal sequence mining algorithm to group the large number of variables. The spreading of the effect of malfunctions over the plant is thoroughly traceable on the higher levels of the hierarchy, while the critical elements of the spillover effect can be detected on the lower levels. Confidence-based goal-oriented measures have been proposed to describe the orientation of fault propagation providing a good insight into the causality on a local level of the process, while the network-based representation yields a global view of causal connections. The effectiveness of the proposed methodology is presented in terms of the analysis of the alarm and event-log database of an industrial delayed-coker plant, where the complexity of the problem and the size of the event-log database requires a hierarchical constraint-based representation.",
keywords = "alarm management, Chemical processes, Chemicals, Data mining, Databases, Fault detection, fault detection and diagnosis, hierarchical analysis, Monitoring, multi-temporal sequence mining, networks, Production systems",
author = "Gyula Dorgo and Kristof Varga and J. Abonyi",
year = "2018",
month = "8",
day = "31",
doi = "10.1109/ACCESS.2018.2868415",
language = "English",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Hierarchical frequent sequence mining algorithm for the analysis of alarm cascades in chemical processes

AU - Dorgo, Gyula

AU - Varga, Kristof

AU - Abonyi, J.

PY - 2018/8/31

Y1 - 2018/8/31

N2 - Faults and malfunctions on complex chemical production systems generate alarm cascades that hinder the work of the operators and make fault diagnosis a complex and challenging task. The core concept of our work is the incorporation of the hierarchical structure of the technology in a multi-temporal sequence mining algorithm to group the large number of variables. The spreading of the effect of malfunctions over the plant is thoroughly traceable on the higher levels of the hierarchy, while the critical elements of the spillover effect can be detected on the lower levels. Confidence-based goal-oriented measures have been proposed to describe the orientation of fault propagation providing a good insight into the causality on a local level of the process, while the network-based representation yields a global view of causal connections. The effectiveness of the proposed methodology is presented in terms of the analysis of the alarm and event-log database of an industrial delayed-coker plant, where the complexity of the problem and the size of the event-log database requires a hierarchical constraint-based representation.

AB - Faults and malfunctions on complex chemical production systems generate alarm cascades that hinder the work of the operators and make fault diagnosis a complex and challenging task. The core concept of our work is the incorporation of the hierarchical structure of the technology in a multi-temporal sequence mining algorithm to group the large number of variables. The spreading of the effect of malfunctions over the plant is thoroughly traceable on the higher levels of the hierarchy, while the critical elements of the spillover effect can be detected on the lower levels. Confidence-based goal-oriented measures have been proposed to describe the orientation of fault propagation providing a good insight into the causality on a local level of the process, while the network-based representation yields a global view of causal connections. The effectiveness of the proposed methodology is presented in terms of the analysis of the alarm and event-log database of an industrial delayed-coker plant, where the complexity of the problem and the size of the event-log database requires a hierarchical constraint-based representation.

KW - alarm management

KW - Chemical processes

KW - Chemicals

KW - Data mining

KW - Databases

KW - Fault detection

KW - fault detection and diagnosis

KW - hierarchical analysis

KW - Monitoring

KW - multi-temporal sequence mining

KW - networks

KW - Production systems

UR - http://www.scopus.com/inward/record.url?scp=85052792360&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052792360&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2018.2868415

DO - 10.1109/ACCESS.2018.2868415

M3 - Article

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -