Convolutional kernel-based classification of industrial alarm floods

Alarm flood classification (AFC) methods are crucial in assisting human operators to identify and mitigate the overwhelming occurrences of alarm floods in industrial process plants, a challenge exacerbated by the complexity and data-intensive nature of modern process control systems. These alarm flo...

Full description

Saved in:
Bibliographic Details
Main Authors: Gianluca Manca, Alexander Fay
Format: Article
Language:English
Published: Cambridge University Press 2024-01-01
Series:Data-Centric Engineering
Subjects:
Online Access:https://www.cambridge.org/core/product/identifier/S2632673624000224/type/journal_article
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850225800986492928
author Gianluca Manca
Alexander Fay
author_facet Gianluca Manca
Alexander Fay
author_sort Gianluca Manca
collection DOAJ
description Alarm flood classification (AFC) methods are crucial in assisting human operators to identify and mitigate the overwhelming occurrences of alarm floods in industrial process plants, a challenge exacerbated by the complexity and data-intensive nature of modern process control systems. These alarm floods can significantly impair situational awareness and hinder decision-making. Existing AFC methods face difficulties in dealing with the inherent ambiguity in alarm sequences and the task of identifying novel, previously unobserved alarm floods. As a result, they often fail to accurately classify alarm floods. Addressing these significant limitations, this paper introduces a novel three-tier AFC method that uses alarm time series as input. In the transformation stage, alarm floods are subjected to an ensemble of convolutional kernel-based transformations (MultiRocket) to extract their characteristic dynamic properties, which are then fed into the classification stage, where a linear ridge regression classifier ensemble is used to identify recurring alarm floods. In the final novelty detection stage, the local outlier probability (LoOP) is used to determine a confidence measure of whether the classified alarm flood truly belongs to a known or previously unobserved class. Our method has been thoroughly validated using a publicly available dataset based on the Tennessee-Eastman process. The results show that our method outperforms two naive baselines and four existing AFC methods from the literature in terms of overall classification performance as well as the ability to optimize the balance between accurately identifying alarm floods from known classes and detecting alarm flood classes that have not been observed before.
format Article
id doaj-art-ad4d8890c488451dac59136fd92ef46f
institution OA Journals
issn 2632-6736
language English
publishDate 2024-01-01
publisher Cambridge University Press
record_format Article
series Data-Centric Engineering
spelling doaj-art-ad4d8890c488451dac59136fd92ef46f2025-08-20T02:05:14ZengCambridge University PressData-Centric Engineering2632-67362024-01-01510.1017/dce.2024.22Convolutional kernel-based classification of industrial alarm floodsGianluca Manca0https://orcid.org/0000-0001-5951-8590Alexander Fay1Institute of Automation Technology, Helmut-Schmidt-University Hamburg, Hamburg, Germany Industrial AI, ABB Corporate Research Center, Ladenburg, GermanyInstitute of Automation Technology, Helmut-Schmidt-University Hamburg, Hamburg, GermanyAlarm flood classification (AFC) methods are crucial in assisting human operators to identify and mitigate the overwhelming occurrences of alarm floods in industrial process plants, a challenge exacerbated by the complexity and data-intensive nature of modern process control systems. These alarm floods can significantly impair situational awareness and hinder decision-making. Existing AFC methods face difficulties in dealing with the inherent ambiguity in alarm sequences and the task of identifying novel, previously unobserved alarm floods. As a result, they often fail to accurately classify alarm floods. Addressing these significant limitations, this paper introduces a novel three-tier AFC method that uses alarm time series as input. In the transformation stage, alarm floods are subjected to an ensemble of convolutional kernel-based transformations (MultiRocket) to extract their characteristic dynamic properties, which are then fed into the classification stage, where a linear ridge regression classifier ensemble is used to identify recurring alarm floods. In the final novelty detection stage, the local outlier probability (LoOP) is used to determine a confidence measure of whether the classified alarm flood truly belongs to a known or previously unobserved class. Our method has been thoroughly validated using a publicly available dataset based on the Tennessee-Eastman process. The results show that our method outperforms two naive baselines and four existing AFC methods from the literature in terms of overall classification performance as well as the ability to optimize the balance between accurately identifying alarm floods from known classes and detecting alarm flood classes that have not been observed before.https://www.cambridge.org/core/product/identifier/S2632673624000224/type/journal_articleabnormal situationsindustrial alarm floodsindustrial process diagnosisopen-set classificationtime series classification
spellingShingle Gianluca Manca
Alexander Fay
Convolutional kernel-based classification of industrial alarm floods
Data-Centric Engineering
abnormal situations
industrial alarm floods
industrial process diagnosis
open-set classification
time series classification
title Convolutional kernel-based classification of industrial alarm floods
title_full Convolutional kernel-based classification of industrial alarm floods
title_fullStr Convolutional kernel-based classification of industrial alarm floods
title_full_unstemmed Convolutional kernel-based classification of industrial alarm floods
title_short Convolutional kernel-based classification of industrial alarm floods
title_sort convolutional kernel based classification of industrial alarm floods
topic abnormal situations
industrial alarm floods
industrial process diagnosis
open-set classification
time series classification
url https://www.cambridge.org/core/product/identifier/S2632673624000224/type/journal_article
work_keys_str_mv AT gianlucamanca convolutionalkernelbasedclassificationofindustrialalarmfloods
AT alexanderfay convolutionalkernelbasedclassificationofindustrialalarmfloods