Integrating Survival Analysis with Bayesian Statistics to Forecast the Remaining Useful Life of a Centrifugal Pump Conditional to Multiple Fault Types

To improve the viability of nuclear power plants, there is a need to reduce their operational costs. Operational costs account for a significant portion of a plant’s yearly budget, due to their scheduled-based maintenance approach. In order to reduce these costs, proactive methods are required that...

Full description

Bibliographic Details
Main Authors: Abhimanyu Kapuria, Daniel G. Cole
Format: Article
Language:English
Published: MDPI AG 2023-04-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/16/9/3707
_version_ 1827743008934592512
author Abhimanyu Kapuria
Daniel G. Cole
author_facet Abhimanyu Kapuria
Daniel G. Cole
author_sort Abhimanyu Kapuria
collection DOAJ
description To improve the viability of nuclear power plants, there is a need to reduce their operational costs. Operational costs account for a significant portion of a plant’s yearly budget, due to their scheduled-based maintenance approach. In order to reduce these costs, proactive methods are required that estimate and forecast the state of a machine in real time to optimize maintenance schedules. In this research, we use Bayesian networks to develop a framework that can forecast the remaining useful life of a centrifugal pump. To do so, we integrate survival analysis with Bayesian statistics to forecast the health of the pump conditional to its current state. We complete our research by successfully using the Bayesian network on a case study. This solution provides an informed probabilistic viewpoint of the pumping system for the purpose of predictive maintenance.
first_indexed 2024-03-11T04:19:56Z
format Article
id doaj.art-2e78f9ad264f453b80cef9951b6fc6ba
institution Directory Open Access Journal
issn 1996-1073
language English
last_indexed 2024-03-11T04:19:56Z
publishDate 2023-04-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj.art-2e78f9ad264f453b80cef9951b6fc6ba2023-11-17T22:50:39ZengMDPI AGEnergies1996-10732023-04-01169370710.3390/en16093707Integrating Survival Analysis with Bayesian Statistics to Forecast the Remaining Useful Life of a Centrifugal Pump Conditional to Multiple Fault TypesAbhimanyu Kapuria0Daniel G. Cole1Swanson School of Engineering, University of Pittsburgh, Pittsburgh, PA 15260, USASwanson School of Engineering, University of Pittsburgh, Pittsburgh, PA 15260, USATo improve the viability of nuclear power plants, there is a need to reduce their operational costs. Operational costs account for a significant portion of a plant’s yearly budget, due to their scheduled-based maintenance approach. In order to reduce these costs, proactive methods are required that estimate and forecast the state of a machine in real time to optimize maintenance schedules. In this research, we use Bayesian networks to develop a framework that can forecast the remaining useful life of a centrifugal pump. To do so, we integrate survival analysis with Bayesian statistics to forecast the health of the pump conditional to its current state. We complete our research by successfully using the Bayesian network on a case study. This solution provides an informed probabilistic viewpoint of the pumping system for the purpose of predictive maintenance.https://www.mdpi.com/1996-1073/16/9/3707machine learningremaining useful lifecondition monitoringprobabilistic estimationBayesian networkssurvival analysis
spellingShingle Abhimanyu Kapuria
Daniel G. Cole
Integrating Survival Analysis with Bayesian Statistics to Forecast the Remaining Useful Life of a Centrifugal Pump Conditional to Multiple Fault Types
Energies
machine learning
remaining useful life
condition monitoring
probabilistic estimation
Bayesian networks
survival analysis
title Integrating Survival Analysis with Bayesian Statistics to Forecast the Remaining Useful Life of a Centrifugal Pump Conditional to Multiple Fault Types
title_full Integrating Survival Analysis with Bayesian Statistics to Forecast the Remaining Useful Life of a Centrifugal Pump Conditional to Multiple Fault Types
title_fullStr Integrating Survival Analysis with Bayesian Statistics to Forecast the Remaining Useful Life of a Centrifugal Pump Conditional to Multiple Fault Types
title_full_unstemmed Integrating Survival Analysis with Bayesian Statistics to Forecast the Remaining Useful Life of a Centrifugal Pump Conditional to Multiple Fault Types
title_short Integrating Survival Analysis with Bayesian Statistics to Forecast the Remaining Useful Life of a Centrifugal Pump Conditional to Multiple Fault Types
title_sort integrating survival analysis with bayesian statistics to forecast the remaining useful life of a centrifugal pump conditional to multiple fault types
topic machine learning
remaining useful life
condition monitoring
probabilistic estimation
Bayesian networks
survival analysis
url https://www.mdpi.com/1996-1073/16/9/3707
work_keys_str_mv AT abhimanyukapuria integratingsurvivalanalysiswithbayesianstatisticstoforecasttheremainingusefullifeofacentrifugalpumpconditionaltomultiplefaulttypes
AT danielgcole integratingsurvivalanalysiswithbayesianstatisticstoforecasttheremainingusefullifeofacentrifugalpumpconditionaltomultiplefaulttypes