Exploration of Production Data for Predictive Maintenance of Industrial Equipment: A Case Study

Nanna Burmeister*, Rasmus Dovnborg Frederiksen, Esben Hog, Peter Nielsen

*Kontaktforfatter

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

3 Citationer (Scopus)
59 Downloads (Pure)

Abstract

Data-driven predictive maintenance is typically based on collected data from multiple sensors
or industrial systems through time, where historical and real-time data are combined as input to blackbox
machine learning models. In this article, we provide a case study of a major manufacturing company
of large industrial equipment. We investigate the opportunity to utilize the manufacturing state of the
equipment alone to predict future conditions. The production data contains information about the errors
in the equipment found in production, which are potentially repaired before the equipment is installed.
We present a proactive approach based on interpretable machine learning models, where the production
data are used to predict maintenance, which creates the opportunity to prevent future maintenance. The
solution is easily translated into a simple set of rules that can be used to separate critical production errors
from non-critical production errors. Identifying critical production errors potentially prevents future and
more expensive repairs of errors detected in inspections after the equipment has been installed. Our paper
makes two contributions to the literature on predictive maintenance. Firstly, we show the viability of a more
proactive approach utilizing production data to prevent future maintenance. Secondly, we demonstrate the
applicability of interpretable machine learning models to understand the relationship between the features
of the production errors and the later inspection errors.
OriginalsprogEngelsk
TidsskriftIEEE Access
Vol/bind11
Sider (fra-til)102025-102037
Antal sider13
ISSN2169-3536
DOI
StatusUdgivet - 2023

Bibliografisk note

Publisher Copyright:
© 2013 IEEE.

Fingeraftryk

Dyk ned i forskningsemnerne om 'Exploration of Production Data for Predictive Maintenance of Industrial Equipment: A Case Study'. Sammen danner de et unikt fingeraftryk.

Citationsformater