Infrequent adverse event prediction in low carbon energy production using machine learning
Infrequent adverse event prediction in low carbon energy production using machine learning
We address the problem of predicting the occurrence of infrequent adverse events in the context of predictive maintenance. We cast the corresponding machine learning task as an imbalanced classification problem and propose a framework for solving it that is capable of leveraging different classifiers in order to predict the occurrence of an adverse event before it takes place. In particular, we focus on two applications arising in low-carbon energy production: foam formation in anaerobic digestion and condenser tube leakage in the steam turbines of a nuclear power station. The results of an extensive set of omputational experiments show the effectiveness of the techniques that we propose.
cs.LG, math.OC
Coniglio, Stefano
03838248-2ce4-4dbc-a6f4-e010d6fdac67
Dunn, Anthony J.
161d9c8e-6813-4909-95ea-6c11bbbca287
Zemkoho, Alain B.
30c79e30-9879-48bd-8d0b-e2fbbc01269e
Coniglio, Stefano
03838248-2ce4-4dbc-a6f4-e010d6fdac67
Dunn, Anthony J.
161d9c8e-6813-4909-95ea-6c11bbbca287
Zemkoho, Alain B.
30c79e30-9879-48bd-8d0b-e2fbbc01269e
Coniglio, Stefano, Dunn, Anthony J. and Zemkoho, Alain B.
(2020)
Infrequent adverse event prediction in low carbon energy production using machine learning.
arXiv.
(In Press)
Abstract
We address the problem of predicting the occurrence of infrequent adverse events in the context of predictive maintenance. We cast the corresponding machine learning task as an imbalanced classification problem and propose a framework for solving it that is capable of leveraging different classifiers in order to predict the occurrence of an adverse event before it takes place. In particular, we focus on two applications arising in low-carbon energy production: foam formation in anaerobic digestion and condenser tube leakage in the steam turbines of a nuclear power station. The results of an extensive set of omputational experiments show the effectiveness of the techniques that we propose.
Text
2001.06916
- Author's Original
Text
2001.06916v2
- Author's Original
More information
Accepted/In Press date: 27 January 2020
Keywords:
cs.LG, math.OC
Identifiers
Local EPrints ID: 448030
URI: http://eprints.soton.ac.uk/id/eprint/448030
ISSN: 2331-8422
PURE UUID: ed62e85f-b7db-4d7f-beef-3fb63e65af61
Catalogue record
Date deposited: 30 Mar 2021 16:35
Last modified: 17 Mar 2024 03:40
Export record
Contributors
Author:
Anthony J. Dunn
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics