Implementation of a Bayesian linear regression framework for nuclear prognostics

Omer Panni, Graeme West, Victoria Catterson, Stephen McArthur, Dongfeng Shi, Ieuan Mogridge

Research output: Contribution to conferencePaper

Abstract

Steam turbines are an important asset of nuclear power plants (NPPs), and are required to operate reliably and efficiently. Unplanned outages have a significant impact on the ability of the plant to generate electricity. Therefore, predictive and proactive maintenance which can avoid unplanned outages has the potential to reduce operating costs while increasing the reliability and availability of the plant.

A case study from the data of an operational steam turbine of a NPP in the UK was used for the implementation of a Bayesian Linear Regression (BLR) framework. An appropriate model for the deterioration under study is selected. The BLR framework was applied as a prognostic technique in order to calculate the remaining useful life (RUL). Results show that the accuracy of the technique varies due to the nature of the data that is utilised to estimate the model parameters.

Conference

ConferenceThird European Conference of the Prognostics and Health Management Society 2016
CountrySpain
CityBilbao
Period5/07/168/07/16

Fingerprint

Steam turbines
Linear regression
Outages
Nuclear power plants
Operating costs
Deterioration
Electricity
Availability

Keywords

  • asset management
  • prognostics and health management
  • Bayesian
  • steam turbines
  • nuclear

Cite this

Panni, O., West, G., Catterson, V., McArthur, S., Shi, D., & Mogridge, I. (Accepted/In press). Implementation of a Bayesian linear regression framework for nuclear prognostics. Paper presented at Third European Conference of the Prognostics and Health Management Society 2016, Bilbao, Spain.
Panni, Omer ; West, Graeme ; Catterson, Victoria ; McArthur, Stephen ; Shi, Dongfeng ; Mogridge, Ieuan. / Implementation of a Bayesian linear regression framework for nuclear prognostics. Paper presented at Third European Conference of the Prognostics and Health Management Society 2016, Bilbao, Spain.9 p.
@conference{3e178c31dbd14fa28d355deeeadbbca2,
title = "Implementation of a Bayesian linear regression framework for nuclear prognostics",
abstract = "Steam turbines are an important asset of nuclear power plants (NPPs), and are required to operate reliably and efficiently. Unplanned outages have a significant impact on the ability of the plant to generate electricity. Therefore, predictive and proactive maintenance which can avoid unplanned outages has the potential to reduce operating costs while increasing the reliability and availability of the plant.A case study from the data of an operational steam turbine of a NPP in the UK was used for the implementation of a Bayesian Linear Regression (BLR) framework. An appropriate model for the deterioration under study is selected. The BLR framework was applied as a prognostic technique in order to calculate the remaining useful life (RUL). Results show that the accuracy of the technique varies due to the nature of the data that is utilised to estimate the model parameters.",
keywords = "asset management, prognostics and health management, Bayesian, steam turbines , nuclear",
author = "Omer Panni and Graeme West and Victoria Catterson and Stephen McArthur and Dongfeng Shi and Ieuan Mogridge",
year = "2016",
month = "5",
day = "16",
language = "English",
note = "Third European Conference of the Prognostics and Health Management Society 2016 ; Conference date: 05-07-2016 Through 08-07-2016",

}

Panni, O, West, G, Catterson, V, McArthur, S, Shi, D & Mogridge, I 2016, 'Implementation of a Bayesian linear regression framework for nuclear prognostics' Paper presented at Third European Conference of the Prognostics and Health Management Society 2016, Bilbao, Spain, 5/07/16 - 8/07/16, .

Implementation of a Bayesian linear regression framework for nuclear prognostics. / Panni, Omer; West, Graeme; Catterson, Victoria; McArthur, Stephen; Shi, Dongfeng; Mogridge, Ieuan.

2016. Paper presented at Third European Conference of the Prognostics and Health Management Society 2016, Bilbao, Spain.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Implementation of a Bayesian linear regression framework for nuclear prognostics

AU - Panni, Omer

AU - West, Graeme

AU - Catterson, Victoria

AU - McArthur, Stephen

AU - Shi, Dongfeng

AU - Mogridge, Ieuan

PY - 2016/5/16

Y1 - 2016/5/16

N2 - Steam turbines are an important asset of nuclear power plants (NPPs), and are required to operate reliably and efficiently. Unplanned outages have a significant impact on the ability of the plant to generate electricity. Therefore, predictive and proactive maintenance which can avoid unplanned outages has the potential to reduce operating costs while increasing the reliability and availability of the plant.A case study from the data of an operational steam turbine of a NPP in the UK was used for the implementation of a Bayesian Linear Regression (BLR) framework. An appropriate model for the deterioration under study is selected. The BLR framework was applied as a prognostic technique in order to calculate the remaining useful life (RUL). Results show that the accuracy of the technique varies due to the nature of the data that is utilised to estimate the model parameters.

AB - Steam turbines are an important asset of nuclear power plants (NPPs), and are required to operate reliably and efficiently. Unplanned outages have a significant impact on the ability of the plant to generate electricity. Therefore, predictive and proactive maintenance which can avoid unplanned outages has the potential to reduce operating costs while increasing the reliability and availability of the plant.A case study from the data of an operational steam turbine of a NPP in the UK was used for the implementation of a Bayesian Linear Regression (BLR) framework. An appropriate model for the deterioration under study is selected. The BLR framework was applied as a prognostic technique in order to calculate the remaining useful life (RUL). Results show that the accuracy of the technique varies due to the nature of the data that is utilised to estimate the model parameters.

KW - asset management

KW - prognostics and health management

KW - Bayesian

KW - steam turbines

KW - nuclear

UR - http://www.phmsociety.org/events/conference/phm/europe/16

M3 - Paper

ER -

Panni O, West G, Catterson V, McArthur S, Shi D, Mogridge I. Implementation of a Bayesian linear regression framework for nuclear prognostics. 2016. Paper presented at Third European Conference of the Prognostics and Health Management Society 2016, Bilbao, Spain.