Multi-temporal sequential pattern mining based improvement of alarm management systems

Richard Karoly, J. Abonyi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Even in a case of a simple failure, modern process control systems can cause a vast number of alarms. Due to the overload of the operators these alarm floods may result in tragedical accidents. Alarm management systems can suppress correlated and predictable alarms to reduce the workload of the operators. Since the process units of complex production systems are strongly interconnected, the signals defined on different process variables generate complex multi-temporal patterns. We propose a multi-temporal sequence mining based approach to extract these patterns and form alarm suppression rules. We demonstrate the applicability of the concept in a vinyl-acetate production technology. The results illustrate the multi-temporal analysis of events defined on process variables can detect causes of alarm, and prevent alarm floods by pro-actively suppressing alarms based on the extracted sequences of events.

Original languageEnglish
Title of host publication2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3870-3875
Number of pages6
ISBN (Electronic)9781509018970
DOIs
Publication statusPublished - Feb 6 2017
Event2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Budapest, Hungary
Duration: Oct 9 2016Oct 12 2016

Other

Other2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016
CountryHungary
CityBudapest
Period10/9/1610/12/16

Fingerprint

Sequential Patterns
Mining
Process control
Chemical reactions
Accidents
Complex Variables
Overload
Production Systems
Operator
Process Control
Control systems
Workload
Complex Systems
Control System
Unit
Demonstrate

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Artificial Intelligence
  • Control and Optimization
  • Human-Computer Interaction

Cite this

Karoly, R., & Abonyi, J. (2017). Multi-temporal sequential pattern mining based improvement of alarm management systems. In 2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings (pp. 3870-3875). [7844838] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SMC.2016.7844838

Multi-temporal sequential pattern mining based improvement of alarm management systems. / Karoly, Richard; Abonyi, J.

2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 3870-3875 7844838.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Karoly, R & Abonyi, J 2017, Multi-temporal sequential pattern mining based improvement of alarm management systems. in 2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings., 7844838, Institute of Electrical and Electronics Engineers Inc., pp. 3870-3875, 2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016, Budapest, Hungary, 10/9/16. https://doi.org/10.1109/SMC.2016.7844838
Karoly R, Abonyi J. Multi-temporal sequential pattern mining based improvement of alarm management systems. In 2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 3870-3875. 7844838 https://doi.org/10.1109/SMC.2016.7844838
Karoly, Richard ; Abonyi, J. / Multi-temporal sequential pattern mining based improvement of alarm management systems. 2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 3870-3875
@inproceedings{de415da8ae334c89b82cd88aca507d76,
title = "Multi-temporal sequential pattern mining based improvement of alarm management systems",
abstract = "Even in a case of a simple failure, modern process control systems can cause a vast number of alarms. Due to the overload of the operators these alarm floods may result in tragedical accidents. Alarm management systems can suppress correlated and predictable alarms to reduce the workload of the operators. Since the process units of complex production systems are strongly interconnected, the signals defined on different process variables generate complex multi-temporal patterns. We propose a multi-temporal sequence mining based approach to extract these patterns and form alarm suppression rules. We demonstrate the applicability of the concept in a vinyl-acetate production technology. The results illustrate the multi-temporal analysis of events defined on process variables can detect causes of alarm, and prevent alarm floods by pro-actively suppressing alarms based on the extracted sequences of events.",
author = "Richard Karoly and J. Abonyi",
year = "2017",
month = "2",
day = "6",
doi = "10.1109/SMC.2016.7844838",
language = "English",
pages = "3870--3875",
booktitle = "2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Multi-temporal sequential pattern mining based improvement of alarm management systems

AU - Karoly, Richard

AU - Abonyi, J.

PY - 2017/2/6

Y1 - 2017/2/6

N2 - Even in a case of a simple failure, modern process control systems can cause a vast number of alarms. Due to the overload of the operators these alarm floods may result in tragedical accidents. Alarm management systems can suppress correlated and predictable alarms to reduce the workload of the operators. Since the process units of complex production systems are strongly interconnected, the signals defined on different process variables generate complex multi-temporal patterns. We propose a multi-temporal sequence mining based approach to extract these patterns and form alarm suppression rules. We demonstrate the applicability of the concept in a vinyl-acetate production technology. The results illustrate the multi-temporal analysis of events defined on process variables can detect causes of alarm, and prevent alarm floods by pro-actively suppressing alarms based on the extracted sequences of events.

AB - Even in a case of a simple failure, modern process control systems can cause a vast number of alarms. Due to the overload of the operators these alarm floods may result in tragedical accidents. Alarm management systems can suppress correlated and predictable alarms to reduce the workload of the operators. Since the process units of complex production systems are strongly interconnected, the signals defined on different process variables generate complex multi-temporal patterns. We propose a multi-temporal sequence mining based approach to extract these patterns and form alarm suppression rules. We demonstrate the applicability of the concept in a vinyl-acetate production technology. The results illustrate the multi-temporal analysis of events defined on process variables can detect causes of alarm, and prevent alarm floods by pro-actively suppressing alarms based on the extracted sequences of events.

UR - http://www.scopus.com/inward/record.url?scp=85015775620&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015775620&partnerID=8YFLogxK

U2 - 10.1109/SMC.2016.7844838

DO - 10.1109/SMC.2016.7844838

M3 - Conference contribution

AN - SCOPUS:85015775620

SP - 3870

EP - 3875

BT - 2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -