Teknik & Rekayasa editorial
Open AccessOA2023
Data-driven maintenance priority recommendations for civil aircraft engine fleets using reliability-based bivariate cluster analysis
This study applies data-driven cluster analysis to real-life aircraft engine fleet operation data to provide module maintenance priority recommendations, aiming to increase operational efficiency and maximize engine value.
Hang Zhou; A. Parlikad; A. Brintrupยท Quality Engineeringยท 2023ยท DOI 10.1080/08982112.2022.2163179
The core problem
Modern civil aircraft engines are highly complex engineering systems that operate under extreme and critical conditions, where high reliability and safety are paramount. To ensure top performance and efficiency, engines are designed modularly. The article addresses the need for efficient maintenance prioritization across engine modules using real-world operational data. The authors propose a data-driven cluster analysis approach to generate maintenance priority recommendations for aircraft engine fleets, with the goal of improving operational efficiency and optimizing engine value.
Innovation
The authors apply a reliability-based bivariate cluster analysis to real-life operation data from aircraft engine fleets. The method clusters engine modules based on reliability-related metrics to identify maintenance priorities. While the abstract does not detail the specific variables or clustering algorithm, the approach is data-driven and focuses on bivariate analysis of reliability indicators. The methodology is designed to be applicable to real operational data, enabling practical maintenance prioritization.
Introduction
Modern civil aircraft engines are highly complex engineering systems that operate under extreme and critical conditions, where high reliability and safety are paramount. To ensure top performance and efficiency, engines are designed modularly. The article addresses the need for efficient maintenance prioritization across engine modules using real-world operational data. The authors propose a data-driven cluster analysis approach to generate maintenance priority recommendations for aircraft engine fleets, with the goal of improving operational efficiency and optimizing engine value.
Why it matters
The study discusses the implications of the proposed approach for civil aviation maintenance operations. By prioritizing maintenance based on reliability-based clustering, operators can allocate resources more effectively, reduce downtime, and enhance safety. The authors highlight the potential of data-driven methods to support decision-making in complex engineering systems. The abstract does not include detailed discussion of limitations or comparisons with existing methods.
Who should read this
Pembaca Research Digest dan praktisi rumpun ini.
Opening member contentโฆ