Reducing costs and eliminating non-value-adding processes are essential steps toward making airline operations leaner and more efficient, particularly in the stages leading up to a flight. An effective maintenance process plays a critical role in lowering marginal costs and enhancing commercial competitiveness. Faced with growing demand in the commercial aviation sector, operators strive to maximize aircraft availability by minimizing ground time and unscheduled maintenance. This challenge has driven engineering teams worldwide to seek innovative solutions. In this study, we developed a data-driven tool employing unsupervised machine learning techniques for classification and clustering of maintenance demand data simulated from a generic fleet support database. The proposed approach leverages unsupervised artificial intelligence to identify recurrent maintenance cases and prioritize events that generate the highest workload and man-hour costs for support teams. The ultimate goal is to proactively recommend solutions and repair procedures that reduce aircraft ground time. The tool demonstrated a significant reduction in data dispersion—approximately 70%, condensing an initial dataset comprising 9 global classes and 30 local subclasses into a clear visualization of 3 distinct clusters. This cluster-based presentation facilitates engineering teams in optimizing the structural health assessment process and effectively qualifying aircraft repair regions. The developed methodology provides a practical, visual management solution that supports the continuous improvement of structural repair manuals and fleet maintenance strategies.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Optimizing aircraft fleet maintenance: a data-driven approach using unsupervised artificial intelligence


    Additional title:

    Mach. Learn. Comput. Sci. Eng




    Publication date :

    2025-07-26




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    An Approach to Optimizing Aircraft Maintenance

    Okoro, Onyedikachi Chioma / Zaliskyi, Maksym / Dmytriiev, Serhii | Springer Verlag | 2023


    Advances in Artificial Intelligence for Aircraft Maintenance

    Husni, M. | British Library Conference Proceedings


    Maintenance of a fleet of aircraft

    MILLER ADRIENNE PAULINE / LASATER BRADLEY A / YAGER STEVEN S | European Patent Office | 2019

    Free access

    DATA-DRIVEN APPROACH TO OPTIMAL AIRCRAFT MAINTENANCE

    Okoro, O. / Zaliskyi, M. / Dmytriiev, S. et al. | British Library Conference Proceedings | 2022


    Artificial Intelligence/Robotics Applications to Navy Aircraft Maintenance

    D. R. Brown / R. H. Monahan / W. T. Park | NTIS | 1984