Data-driven predictive maintenance: a methodology primer

Tania Cerquitelli (Corresponding author), Nikolaus Nikolakis, Lia Morra, Andrea Bellagarda, Matteo Orlando, Riku Salokangas, Olli Saarela, Jani Hietala, Petri Kaarmila, Enrico Macii

Research output: Chapter in Book/Report/Conference proceedingChapter or book articleScientificpeer-review

Abstract

Predictive maintenance aims at proactively assessing the current condition of assets and performing maintenance activities if and when needed to preserve them in the optimal operational condition. This in turn may lead to a reduction of unexpected breakdowns and production stoppages as well as maintenance costs, ultimately resulting in reduced production costs. Empowered by recent advances in the fields of information and communication technologies and artificial intelligence, this chapter attempts to define the main operational blocks for predictive maintenance, building upon existing standards discusses and key data-driven methodologies for predictive maintenance. In addition, technical information related to potential data models for storing and communicating key information are provided, finally closing the chapter with different deployment strategies for predictive analytics as well as identifying open issues.
Original languageEnglish
Title of host publicationPredictive Maintenance in Smart Factories
Subtitle of host publicationArchitectures, Methodologies, and Use-cases
EditorsT. Cerquitelli, N. Nikolakis, N. O’Mahony, E. Macii, M. Ippolito, S. Makris
PublisherSpringer
Chapter8
Pages39-73
ISBN (Electronic)978-981-16-2940-2
ISBN (Print)978-981-16-2939-6
DOIs
Publication statusPublished - 2021
MoE publication typeA3 Part of a book or another research book

Publication series

SeriesInformation Fusion and Data Science
ISSN2510-1528

Fingerprint

Dive into the research topics of 'Data-driven predictive maintenance: a methodology primer'. Together they form a unique fingerprint.

Cite this