Download the full-sized PDF of Similarity analysis of industrial alarm flood dataDownload the full-sized PDF



Permanent link (DOI):


Export to: EndNote  |  Zotero  |  Mendeley


This file is in the following communities:

Graduate Studies and Research, Faculty of


This file is in the following collections:

Theses and Dissertations

Similarity analysis of industrial alarm flood data Open Access


Other title
Alarm management
Pattern classification
Similarity analysis
Alarm flood
Type of item
Degree grantor
University of Alberta
Author or creator
Ahmed, Kabir
Supervisor and department
Dr. Tongwen Chen (Electrical and Computer Engineering)
Examining committee member and department
Dr. Sirish L. Shah (Chemical and Materials Engineering)
Dr. Mahdi Tavakoli (Electrical and Computer Engineering)
Department of Electrical and Computer Engineering

Date accepted
Graduation date
Master of Science
Degree level
Alarm floods are a crucial problem in the process industry. An alarm flood makes it difficult for an operator to react and take necessary actions, which often can lead to risking an emergency shutdown or a major upset. In many cases, alarm floods are caused by interrelated process variables, which can be identified via similar patterns in alarm annunciations. This similarity can be investigated through alarm pattern analysis of industrial alarm flood data. In this work, alarm floods are discussed based on the standards presented in the new ISA 18.2 guidelines and the discussion given in EEMUA 191. A new analysis method is proposed to identify alarm floods that are similar from the historical alarm data and group them on the basis of patterns of alarm occurrences. Patterns in alarm sequences can be investigated through different distance measures. To calculate a distance between alarm patterns in two different sequences, preprocessing of industrial alarm data and effective flood period isolation are required. Hence, definitions of alarm floods and alarm flood periods are given based on the new ISA 18.2 standards. The effect of chattering alarms on alarm floods is also discussed. Three different distance scores, suitable for capturing alarm patterns in alarm flood sequences, are introduced. Finally, a case study on real industrial alarm data is presented to demonstrate the utility of the proposed analysis.
Permission is hereby granted to the University of Alberta Libraries to reproduce single copies of this thesis and to lend or sell such copies for private, scholarly or scientific research purposes only. Where the thesis is converted to, or otherwise made available in digital form, the University of Alberta will advise potential users of the thesis of these terms. The author reserves all other publication and other rights in association with the copyright in the thesis and, except as herein before provided, neither the thesis nor any substantial portion thereof may be printed or otherwise reproduced in any material form whatsoever without the author's prior written permission.
Citation for previous publication

File Details

Date Uploaded
Date Modified
Audit Status
Audits have not yet been run on this file.
File format: pdf (Portable Document Format)
Mime type: application/pdf
File size: 2164006
Last modified: 2015:10:12 12:06:19-06:00
Filename: Ahmed_Kabir_Fall 2011.pdf
Original checksum: 2a33b67ba4656c083045b58bce5ee67c
Well formed: true
Valid: true
Page count: 71
Activity of users you follow
User Activity Date