Predictive maintenance modelling for through-life engineering services

C. Okoh, R. Roy, J. Mehnen

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Predictive maintenance needs to forecast the numbers of rejections at any overhaul point before any failure occurs in order to accurately and proactively take adequate maintenance action. In healthcare, prediction has been applied to foretell when and how to administer medication to improve the health condition of the patient. The same is true for maintenance where the application of prognostics can help make better decisions. In this paper, an overview of prognostic maintenance strategies is presented. The proposed data-driven prognostics approach employs a statistical technique of (i) the parameter estimation methods of the time-to-failure data to predict the relevant statistical model parameters and (ii) prognostics modelling incorporating the reliability Weibull Cumulative Distribution Function to predict part rejection, replacement, and reuse. The analysis of the modelling uses synthetic data validated by industry domain experts. The outcome of the prediction can further proffer solution to designers, manufacturers and operators of industrial product-service systems. The novelty in this paper is the development of the through-life performance approach. The approach ascertains when the system needs to undergo maintenance, repair and overhaul before failure occurs.
LanguageEnglish
Pages196–201
Number of pages6
JournalProcedia CIRP
Volume59
Early online date2 Mar 2017
DOIs
Publication statusPublished - 2017

Fingerprint

Weibull distribution
Parameter estimation
Distribution functions
Repair
Health
Industry
Statistical Models

Keywords

  • through-life engineering services
  • maintenance strategies
  • data-driven prediction
  • predictive modelling
  • parameter estimation

Cite this

@article{cdb8c21fbdbe489e9b1c1d31c3cbff76,
title = "Predictive maintenance modelling for through-life engineering services",
abstract = "Predictive maintenance needs to forecast the numbers of rejections at any overhaul point before any failure occurs in order to accurately and proactively take adequate maintenance action. In healthcare, prediction has been applied to foretell when and how to administer medication to improve the health condition of the patient. The same is true for maintenance where the application of prognostics can help make better decisions. In this paper, an overview of prognostic maintenance strategies is presented. The proposed data-driven prognostics approach employs a statistical technique of (i) the parameter estimation methods of the time-to-failure data to predict the relevant statistical model parameters and (ii) prognostics modelling incorporating the reliability Weibull Cumulative Distribution Function to predict part rejection, replacement, and reuse. The analysis of the modelling uses synthetic data validated by industry domain experts. The outcome of the prediction can further proffer solution to designers, manufacturers and operators of industrial product-service systems. The novelty in this paper is the development of the through-life performance approach. The approach ascertains when the system needs to undergo maintenance, repair and overhaul before failure occurs.",
keywords = "through-life engineering services, maintenance strategies, data-driven prediction, predictive modelling, parameter estimation",
author = "C. Okoh and R. Roy and J. Mehnen",
year = "2017",
doi = "10.1016/j.procir.2016.09.033",
language = "English",
volume = "59",
pages = "196–201",
journal = "Procedia CIRP",
issn = "2212-8271",

}

Predictive maintenance modelling for through-life engineering services. / Okoh, C.; Roy, R.; Mehnen, J.

In: Procedia CIRP, Vol. 59, 2017, p. 196–201.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Predictive maintenance modelling for through-life engineering services

AU - Okoh, C.

AU - Roy, R.

AU - Mehnen, J.

PY - 2017

Y1 - 2017

N2 - Predictive maintenance needs to forecast the numbers of rejections at any overhaul point before any failure occurs in order to accurately and proactively take adequate maintenance action. In healthcare, prediction has been applied to foretell when and how to administer medication to improve the health condition of the patient. The same is true for maintenance where the application of prognostics can help make better decisions. In this paper, an overview of prognostic maintenance strategies is presented. The proposed data-driven prognostics approach employs a statistical technique of (i) the parameter estimation methods of the time-to-failure data to predict the relevant statistical model parameters and (ii) prognostics modelling incorporating the reliability Weibull Cumulative Distribution Function to predict part rejection, replacement, and reuse. The analysis of the modelling uses synthetic data validated by industry domain experts. The outcome of the prediction can further proffer solution to designers, manufacturers and operators of industrial product-service systems. The novelty in this paper is the development of the through-life performance approach. The approach ascertains when the system needs to undergo maintenance, repair and overhaul before failure occurs.

AB - Predictive maintenance needs to forecast the numbers of rejections at any overhaul point before any failure occurs in order to accurately and proactively take adequate maintenance action. In healthcare, prediction has been applied to foretell when and how to administer medication to improve the health condition of the patient. The same is true for maintenance where the application of prognostics can help make better decisions. In this paper, an overview of prognostic maintenance strategies is presented. The proposed data-driven prognostics approach employs a statistical technique of (i) the parameter estimation methods of the time-to-failure data to predict the relevant statistical model parameters and (ii) prognostics modelling incorporating the reliability Weibull Cumulative Distribution Function to predict part rejection, replacement, and reuse. The analysis of the modelling uses synthetic data validated by industry domain experts. The outcome of the prediction can further proffer solution to designers, manufacturers and operators of industrial product-service systems. The novelty in this paper is the development of the through-life performance approach. The approach ascertains when the system needs to undergo maintenance, repair and overhaul before failure occurs.

KW - through-life engineering services

KW - maintenance strategies

KW - data-driven prediction

KW - predictive modelling

KW - parameter estimation

U2 - 10.1016/j.procir.2016.09.033

DO - 10.1016/j.procir.2016.09.033

M3 - Article

VL - 59

SP - 196

EP - 201

JO - Procedia CIRP

T2 - Procedia CIRP

JF - Procedia CIRP

SN - 2212-8271

ER -