Sequential predictive maintenance and spare parts management with data mining methods: a case study in bus fleet

dc.authoridIFRAZ, Metin/0000-0001-7161-223X
dc.contributor.authorIfraz, Metin
dc.contributor.authorErsoz, Suleyman
dc.contributor.authorAktepe, Adnan
dc.contributor.authorCetinyokus, Tahsin
dc.date.accessioned2025-01-21T16:44:22Z
dc.date.available2025-01-21T16:44:22Z
dc.date.issued2024
dc.departmentKırıkkale Üniversitesi
dc.description.abstractThe sustainability of enterprises in an increasingly competitive environment is proportional to their ability to use the resources efficiently. Maintenance departments are critical to ensure that resources are ready and operational. Increasing the efficiency of maintenance departments depends on reducing the number of failures, performing planned maintenance on time and sustaining availability of spare parts needed. Therefore, it is vital that businesses consider predictive maintenance and spare parts jointly. In this study, predictive maintenance and spare parts integration studies are carried out using gearbox failure data and spare parts consumption data of a bus fleet. This study aims to contribute to the reduction of failure costs by finding failure patterns and predicting the subsequent failures and spare parts to be used. The sequential pattern mining approach was used to determine failure patterns and the traditional frequent itemset mining approach was used to predict spare parts. As a result, 45 failure patterns were found. Rules with a reliability of up to 79% were obtained. In addition, spare part clusters with a support value of approximately 40% were created. With this valuable information, businesses are able to investigate root causes, take precautions against future failures, make predictions about the spare parts that will be needed, and develop joint maintenance planning and inventory management policies.
dc.description.sponsorshipScientific and Technological Research Council of Turkey (TUBITAK) [MAG-221M438]
dc.description.sponsorshipThis work was supported by the Scientific and Technological Research Council of Turkey (TUBITAK) within the 1001-The Scientific and Technological Research Projects Funding Program [Grant Numbers: MAG-221M438].
dc.identifier.doi10.1007/s11227-024-06297-1
dc.identifier.endpage22123
dc.identifier.issn0920-8542
dc.identifier.issn1573-0484
dc.identifier.issue15
dc.identifier.scopus2-s2.0-85196293288
dc.identifier.scopusqualityQ1
dc.identifier.startpage22099
dc.identifier.urihttps://doi.org/10.1007/s11227-024-06297-1
dc.identifier.urihttps://hdl.handle.net/20.500.12587/25439
dc.identifier.volume80
dc.identifier.wosWOS:001250189800001
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherSpringer
dc.relation.ispartofJournal of Supercomputing
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_20241229
dc.subjectSequential pattern mining; Maintenance management; Predictive maintenance; Spare parts management; Data mining
dc.titleSequential predictive maintenance and spare parts management with data mining methods: a case study in bus fleet
dc.typeArticle

Dosyalar