Data-driven preventive maintenance for a heterogeneous machine portfolio

Laurens Deprez; Katrien Antonio; Joachim Arts; Robert Boute

doi:10.1016/j.orl.2023.01.006

Data-driven preventive maintenance for a heterogeneous machine portfolio

Laurens Deprez^*, Katrien Antonio, Joachim Arts, Robert Boute

^*Corresponding author for this work

Managerial Economics, Decision Sciences and Operations

Research output: Contribution to journal › Article › peer-review

5 Scopus citations

Abstract

We describe a data-driven approach to optimize periodic maintenance policies for a heterogeneous portfolio with different machine profiles. When insufficient data are available per profile to assess failure intensities and costs accurately, we pool the data of all machine profiles and evaluate the effect of (observable) machine characteristics by calibrating appropriate statistical models. This reduces maintenance costs compared to a stratified approach that splits the data into subsets per profile and a uniform approach that treats all profiles the same.

Original language	English (US)
Pages (from-to)	163-170
Number of pages	8
Journal	Operations Research Letters
Volume	51
Issue number	2
DOIs	https://doi.org/10.1016/j.orl.2023.01.006
State	Published - Mar 2023

Keywords

Data pooling
Preventive maintenance
Proportional hazards
Small data

ASJC Scopus subject areas

Software
Management Science and Operations Research
Industrial and Manufacturing Engineering
Applied Mathematics

Access to Document

10.1016/j.orl.2023.01.006

Cite this

@article{a692d1fe4f2b486781bfc5b29a4f9919,

title = "Data-driven preventive maintenance for a heterogeneous machine portfolio",

abstract = "We describe a data-driven approach to optimize periodic maintenance policies for a heterogeneous portfolio with different machine profiles. When insufficient data are available per profile to assess failure intensities and costs accurately, we pool the data of all machine profiles and evaluate the effect of (observable) machine characteristics by calibrating appropriate statistical models. This reduces maintenance costs compared to a stratified approach that splits the data into subsets per profile and a uniform approach that treats all profiles the same.",

keywords = "Data pooling, Preventive maintenance, Proportional hazards, Small data",

author = "Laurens Deprez and Katrien Antonio and Joachim Arts and Robert Boute",

note = "Publisher Copyright: {\textcopyright} 2023 Elsevier B.V.",

year = "2023",

month = mar,

doi = "10.1016/j.orl.2023.01.006",

language = "English (US)",

volume = "51",

pages = "163--170",

journal = "Operations Research Letters",

issn = "0167-6377",

publisher = "Elsevier B.V.",

number = "2",

}

TY - JOUR

T1 - Data-driven preventive maintenance for a heterogeneous machine portfolio

AU - Deprez, Laurens

AU - Antonio, Katrien

AU - Arts, Joachim

AU - Boute, Robert

PY - 2023/3

Y1 - 2023/3

N2 - We describe a data-driven approach to optimize periodic maintenance policies for a heterogeneous portfolio with different machine profiles. When insufficient data are available per profile to assess failure intensities and costs accurately, we pool the data of all machine profiles and evaluate the effect of (observable) machine characteristics by calibrating appropriate statistical models. This reduces maintenance costs compared to a stratified approach that splits the data into subsets per profile and a uniform approach that treats all profiles the same.

AB - We describe a data-driven approach to optimize periodic maintenance policies for a heterogeneous portfolio with different machine profiles. When insufficient data are available per profile to assess failure intensities and costs accurately, we pool the data of all machine profiles and evaluate the effect of (observable) machine characteristics by calibrating appropriate statistical models. This reduces maintenance costs compared to a stratified approach that splits the data into subsets per profile and a uniform approach that treats all profiles the same.

KW - Data pooling

KW - Preventive maintenance

KW - Proportional hazards

KW - Small data

UR - http://www.scopus.com/inward/record.url?scp=85148686969&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85148686969&partnerID=8YFLogxK

U2 - 10.1016/j.orl.2023.01.006

DO - 10.1016/j.orl.2023.01.006

M3 - Article

AN - SCOPUS:85148686969

SN - 0167-6377

VL - 51

SP - 163

EP - 170

JO - Operations Research Letters

JF - Operations Research Letters

IS - 2

ER -

Data-driven preventive maintenance for a heterogeneous machine portfolio

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this