Reliability prediction for aircraft fleet operators: A Bayesian network model that combines supplier estimates, maintenance data and expert judgement

Faruk Umut Küçüker and Barbaros Yet

Journal of the Operational Research Society, 2023, vol. 74, issue 10, 2187-2198

Abstract: Reliability prediction is crucial for aircraft maintenance and spare part inventory decisions. These predictions are made based on operational data collected by fleet operators or design life estimates provided by aircraft suppliers. Purely data-driven predictions have limited use especially when the fleet is young, hence the data is scarce. In this case, design life estimates are used for predicting reliability often by assuming a constant failure rate. This strong assumption is not necessarily valid for all components. This paper proposes a Bayesian Network (BN) modelling framework that systematically combines design life estimates, operational data, and expert judgement for reliability prediction of aircraft subsystems. The proposed BN adjusts the design life estimates based on expert judgement regarding supplier and manufacturing quality and revises it based on operational data. We used the BN to predict the reliability of a large aircraft fleet by using failure and maintenance data provided by a large fleet operator. We compared the predictive performance of the BN to using only data-driven approaches and to using only design life estimates provided by the aircraft supplier. The BN model provides consistently accurate reliability predictions compared to design-life estimates and purely data-driven approaches especially when the available data is scarce.

Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/01605682.2022.2129486 (text/html)
Access to full text is restricted to subscribers.

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:taf:tjorxx:v:74:y:2023:i:10:p:2187-2198

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/tjor20

DOI: 10.1080/01605682.2022.2129486

Access Statistics for this article

Journal of the Operational Research Society is currently edited by Tom Archibald

More articles in Journal of the Operational Research Society from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().