Integration of additional information sources for improved alarm flood detection

J. Kinghorst, H. Bloch, A. Fay, B. Vogel-Heuser

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

The aim of alarm flood detection is the identification of similar, frequently occurring sequences of alarm messages in historical alarm data and uses the results for root cause analysis or alarm flood reduction. Various promising approaches for alarm data of automated production systems exist. However, due to the high amount of alarm messages transmitted by industrial alarm systems, floods are often interrupted by alarms stemming from different root causes, leading to non-relevant or invalid results of purely data-driven flood detection approaches. To improve the results of data-driven approaches, this paper suggests considering a process plant's hierarchy to divide historical alarm data into independent sub-datasets. For this reason, the paper discusses necessary plant information to explain a process plant's hierarchy and analyzes existing approaches to extract this hierarchy automatically from information sources. It then discusses whether existing approaches for alarm flood detection consider this hierarchy and how it could improve the approaches' results.

Original languageEnglish
Title of host publicationINES 2017 - IEEE 21st International Conference on Intelligent Engineering Systems, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages19-25
Number of pages7
ISBN (Electronic)9781479976775
DOIs
StatePublished - 22 Nov 2017
Externally publishedYes
Event21st IEEE International Conference on Intelligent Engineering Systems, INES 2017 - Larnaca, Cyprus
Duration: 20 Oct 201723 Oct 2017

Publication series

NameINES 2017 - IEEE 21st International Conference on Intelligent Engineering Systems, Proceedings
Volume2017-January

Conference

Conference21st IEEE International Conference on Intelligent Engineering Systems, INES 2017
Country/TerritoryCyprus
CityLarnaca
Period20/10/1723/10/17

Fingerprint

Dive into the research topics of 'Integration of additional information sources for improved alarm flood detection'. Together they form a unique fingerprint.

Cite this