Failure Pattern Recognition for Predictive Maintenance with Changepoint Detection and Process Mining

Alexandros Bousdekis () and Georgia Theodoropoulou ()
Additional contact information
Alexandros Bousdekis: University of Piraeus, Department of Industrial Management and Technology
Georgia Theodoropoulou: University of West Attica, Department of Informatics and Computer Engineering

A chapter in Advanced Data Analytics, Machine Learning and AI in Business, 2026, pp 425-440 from Springer

Abstract: Abstract Predictive maintenance aims to enhance equipment availability and minimize unplanned downtime by leveraging both real-time sensor data and data-at-rest from enterprise and operational systems. While recent advances in IoT have enabled high-frequency data collection, a significant volume of legacy data, such as records from Computerized Maintenance Management Systems (CMMS), Enterprise Resource Planning (ERP), and Manufacturing Execution Systems (MES), remains underutilized. Motivated by the P–F curve, this paper proposes a failure pattern recognition approach that integrates Bayesian Online Changepoint Detection (BOCD) with process mining. The approach is validated in a real-world cold rolling process in the steel industry.

Keywords: predictive maintenance; machine learning; anomaly detection; process mining; event log (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:lnopch:978-3-032-23493-3_26

Ordering information: This item can be ordered from
http://www.springer.com/9783032234933

DOI: 10.1007/978-3-032-23493-3_26

Access Statistics for this chapter

More chapters in Lecture Notes in Operations Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().