Alert Systems for production Plants: A Methodology Based on Conflict Analysis

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

5 Citations (Scopus)
488 Downloads (Pure)

Abstract

We present a new methodology for detecting faults and abnormal behavior in production plants. The methodology stems from a joint project with a Danish energy consortium. During the course of the project we encountered several problems that we believe are common for projects of this type. Most notably, there was a lack of both knowledge and data concerning possible faults, and it therefore turned out to be infeasible to learn/construct a standard classification model for doing fault detection. As an alternative we propose a method for doing on-line fault detection using only a model of normal system operation, i.e., it does not rely on information about the possible faults. We illustrate the proposed method using real-world data from a coal driven power plant as well as simulated data from an oil production facility.
Original languageEnglish
Title of host publicationProceedings of the Eighth European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty
PublisherIEEE Computer Society Press
Publication date2005
Pages76-87
ISBN (Print)3540273263
Publication statusPublished - 2005
EventEuropean Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty - Barcelona, Spain
Duration: 6 Jul 20058 Jul 2005

Conference

ConferenceEuropean Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty
CountrySpain
CityBarcelona
Period06/07/200508/07/2005
SeriesLecture Notes in Computer Science
Number3571

Fingerprint

Fault detection
Power plants
Coal
Oils

Cite this

Nielsen, T. D., & Jensen, F. V. (2005). Alert Systems for production Plants: A Methodology Based on Conflict Analysis. In Proceedings of the Eighth European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty (pp. 76-87). IEEE Computer Society Press. Lecture Notes in Computer Science, No. 3571
Nielsen, Thomas Dyhre ; Jensen, Finn Verner. / Alert Systems for production Plants : A Methodology Based on Conflict Analysis. Proceedings of the Eighth European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty. IEEE Computer Society Press, 2005. pp. 76-87 (Lecture Notes in Computer Science; No. 3571).
@inproceedings{76efc39031c311db8de7000ea68e967b,
title = "Alert Systems for production Plants: A Methodology Based on Conflict Analysis",
abstract = "We present a new methodology for detecting faults and abnormal behavior in production plants. The methodology stems from a joint project with a Danish energy consortium. During the course of the project we encountered several problems that we believe are common for projects of this type. Most notably, there was a lack of both knowledge and data concerning possible faults, and it therefore turned out to be infeasible to learn/construct a standard classification model for doing fault detection. As an alternative we propose a method for doing on-line fault detection using only a model of normal system operation, i.e., it does not rely on information about the possible faults. We illustrate the proposed method using real-world data from a coal driven power plant as well as simulated data from an oil production facility.",
author = "Nielsen, {Thomas Dyhre} and Jensen, {Finn Verner}",
year = "2005",
language = "English",
isbn = "3540273263",
pages = "76--87",
booktitle = "Proceedings of the Eighth European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty",
publisher = "IEEE Computer Society Press",
address = "United States",

}

Nielsen, TD & Jensen, FV 2005, Alert Systems for production Plants: A Methodology Based on Conflict Analysis. in Proceedings of the Eighth European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty. IEEE Computer Society Press, Lecture Notes in Computer Science, no. 3571, pp. 76-87, Barcelona, Spain, 06/07/2005.

Alert Systems for production Plants : A Methodology Based on Conflict Analysis. / Nielsen, Thomas Dyhre; Jensen, Finn Verner.

Proceedings of the Eighth European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty. IEEE Computer Society Press, 2005. p. 76-87.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Alert Systems for production Plants

T2 - A Methodology Based on Conflict Analysis

AU - Nielsen, Thomas Dyhre

AU - Jensen, Finn Verner

PY - 2005

Y1 - 2005

N2 - We present a new methodology for detecting faults and abnormal behavior in production plants. The methodology stems from a joint project with a Danish energy consortium. During the course of the project we encountered several problems that we believe are common for projects of this type. Most notably, there was a lack of both knowledge and data concerning possible faults, and it therefore turned out to be infeasible to learn/construct a standard classification model for doing fault detection. As an alternative we propose a method for doing on-line fault detection using only a model of normal system operation, i.e., it does not rely on information about the possible faults. We illustrate the proposed method using real-world data from a coal driven power plant as well as simulated data from an oil production facility.

AB - We present a new methodology for detecting faults and abnormal behavior in production plants. The methodology stems from a joint project with a Danish energy consortium. During the course of the project we encountered several problems that we believe are common for projects of this type. Most notably, there was a lack of both knowledge and data concerning possible faults, and it therefore turned out to be infeasible to learn/construct a standard classification model for doing fault detection. As an alternative we propose a method for doing on-line fault detection using only a model of normal system operation, i.e., it does not rely on information about the possible faults. We illustrate the proposed method using real-world data from a coal driven power plant as well as simulated data from an oil production facility.

M3 - Article in proceeding

SN - 3540273263

SP - 76

EP - 87

BT - Proceedings of the Eighth European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty

PB - IEEE Computer Society Press

ER -

Nielsen TD, Jensen FV. Alert Systems for production Plants: A Methodology Based on Conflict Analysis. In Proceedings of the Eighth European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty. IEEE Computer Society Press. 2005. p. 76-87. (Lecture Notes in Computer Science; No. 3571).