A classification-based approach to monitoring the safety of dynamic systems

Shengtong Zhong, Helge Langseth, Thomas Dyhre Nielsen

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

4 Citationer (Scopus)
915 Downloads (Pure)

Resumé

Monitoring a complex process often involves keeping an eye on hundreds or thousands of sensors to determine whether or not the process is stable. We have been working with dynamic data from an oil production facility in the North sea, where unstable situations should be identified as soon as possible. Motivated by this prob- lem setting, we propose a general model for classification in dynamic domains, and exemplify its use by showing how it can be employed for activity detection. We con- struct our model by using well known statistical techniques as building-blocks, and evaluate each step in the model-building process empirically. Exact inference in the proposed model is intractable, so in this paper we experiment with an approximate inference scheme.
OriginalsprogEngelsk
TidsskriftReliability Engineering & System Safety
Vol/bind121
Sider (fra-til)61-71
ISSN0951-8320
DOI
StatusUdgivet - jan. 2014

Fingerprint

Dynamical systems
Monitoring
Sensors
Experiments

Citer dette

@article{0a8153213e984046a6d3f4042f8e0541,
title = "A classification-based approach to monitoring the safety of dynamic systems",
abstract = "Monitoring a complex process often involves keeping an eye on hundreds or thousands of sensors to determine whether or not the process is stable. We have been working with dynamic data from an oil production facility in the North sea, where unstable situations should be identified as soon as possible. Motivated by this prob- lem setting, we propose a general model for classification in dynamic domains, and exemplify its use by showing how it can be employed for activity detection. We con- struct our model by using well known statistical techniques as building-blocks, and evaluate each step in the model-building process empirically. Exact inference in the proposed model is intractable, so in this paper we experiment with an approximate inference scheme.",
author = "Shengtong Zhong and Helge Langseth and Nielsen, {Thomas Dyhre}",
year = "2014",
month = "1",
doi = "10.1016/j.ress.2013.07.016",
language = "English",
volume = "121",
pages = "61--71",
journal = "Reliability Engineering & System Safety",
issn = "0951-8320",
publisher = "Pergamon Press",

}

A classification-based approach to monitoring the safety of dynamic systems. / Zhong, Shengtong; Langseth, Helge; Nielsen, Thomas Dyhre.

I: Reliability Engineering & System Safety, Bind 121, 01.2014, s. 61-71.

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

TY - JOUR

T1 - A classification-based approach to monitoring the safety of dynamic systems

AU - Zhong, Shengtong

AU - Langseth, Helge

AU - Nielsen, Thomas Dyhre

PY - 2014/1

Y1 - 2014/1

N2 - Monitoring a complex process often involves keeping an eye on hundreds or thousands of sensors to determine whether or not the process is stable. We have been working with dynamic data from an oil production facility in the North sea, where unstable situations should be identified as soon as possible. Motivated by this prob- lem setting, we propose a general model for classification in dynamic domains, and exemplify its use by showing how it can be employed for activity detection. We con- struct our model by using well known statistical techniques as building-blocks, and evaluate each step in the model-building process empirically. Exact inference in the proposed model is intractable, so in this paper we experiment with an approximate inference scheme.

AB - Monitoring a complex process often involves keeping an eye on hundreds or thousands of sensors to determine whether or not the process is stable. We have been working with dynamic data from an oil production facility in the North sea, where unstable situations should be identified as soon as possible. Motivated by this prob- lem setting, we propose a general model for classification in dynamic domains, and exemplify its use by showing how it can be employed for activity detection. We con- struct our model by using well known statistical techniques as building-blocks, and evaluate each step in the model-building process empirically. Exact inference in the proposed model is intractable, so in this paper we experiment with an approximate inference scheme.

U2 - 10.1016/j.ress.2013.07.016

DO - 10.1016/j.ress.2013.07.016

M3 - Journal article

VL - 121

SP - 61

EP - 71

JO - Reliability Engineering & System Safety

JF - Reliability Engineering & System Safety

SN - 0951-8320

ER -