Automation of Predictive Maintenance: An Experimental Framework for Aircraft Landing Gear
ABSTRACT Terabytes of data are recorded per flight by modern aircraft, providing a goldmine for predictive maintenance modeling, however, the required domain knowledge to build ML tools limits the number developed by airline manufacturers each year. Automated machine learning (AutoML) libraries can...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-06-01
|
| Series: | Engineering Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/eng2.70214 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849432839307657216 |
|---|---|
| author | Izaak Stanton Kamran Munir Ahsan Ikram Murad El‐Bakry |
| author_facet | Izaak Stanton Kamran Munir Ahsan Ikram Murad El‐Bakry |
| author_sort | Izaak Stanton |
| collection | DOAJ |
| description | ABSTRACT Terabytes of data are recorded per flight by modern aircraft, providing a goldmine for predictive maintenance modeling, however, the required domain knowledge to build ML tools limits the number developed by airline manufacturers each year. Automated machine learning (AutoML) libraries can simplify model development, providing features such as automated preprocessing, model selection, and hyperparameter tuning to improve the efficiency and accessibility of the development workflow. This research presents an experimental analysis comparing industry‐selected machine learning models and a hand‐picked selection of automated machine‐learning tools. The selected models were evaluated against real and synthetic time series datasets for different Airbus landing gear components across six datasets. The traditional and automated models obtained comparable MAE and F1 scores on regression and classification problems, accordingly, demonstrating the effectiveness of their use in this field. Based on these findings, a robust framework is proposed to utilize automated ML to optimize predictive maintenance tool development. This research is a stepping stone towards greater use of automation for predictive maintenance and presents insights into the field and AutoML. By integrating greater automation, AutoML can exploit more of the available data and deskill the development process to enable non‐data scientists to produce health monitoring models for a more diverse pool of aircraft components. |
| format | Article |
| id | doaj-art-f7cbca97fca44bef881f96a5afd7d498 |
| institution | Kabale University |
| issn | 2577-8196 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | Engineering Reports |
| spelling | doaj-art-f7cbca97fca44bef881f96a5afd7d4982025-08-20T03:27:15ZengWileyEngineering Reports2577-81962025-06-0176n/an/a10.1002/eng2.70214Automation of Predictive Maintenance: An Experimental Framework for Aircraft Landing GearIzaak Stanton0Kamran Munir1Ahsan Ikram2Murad El‐Bakry3Centre for Machine Vision, Bristol Robotics Laboratory (BRL) University of the West of England (UWE) Bristol UKComputer Science Research Centre (CSRC), School of Computing and Creative Technologies (SCC), College of Arts, Technology and Environment (CATE) University of the West of England (UWE) Bristol UKComputer Science Research Centre (CSRC), School of Computing and Creative Technologies (SCC), College of Arts, Technology and Environment (CATE) University of the West of England (UWE) Bristol UKAirbus Operations Ltd. Filton Bristol UKABSTRACT Terabytes of data are recorded per flight by modern aircraft, providing a goldmine for predictive maintenance modeling, however, the required domain knowledge to build ML tools limits the number developed by airline manufacturers each year. Automated machine learning (AutoML) libraries can simplify model development, providing features such as automated preprocessing, model selection, and hyperparameter tuning to improve the efficiency and accessibility of the development workflow. This research presents an experimental analysis comparing industry‐selected machine learning models and a hand‐picked selection of automated machine‐learning tools. The selected models were evaluated against real and synthetic time series datasets for different Airbus landing gear components across six datasets. The traditional and automated models obtained comparable MAE and F1 scores on regression and classification problems, accordingly, demonstrating the effectiveness of their use in this field. Based on these findings, a robust framework is proposed to utilize automated ML to optimize predictive maintenance tool development. This research is a stepping stone towards greater use of automation for predictive maintenance and presents insights into the field and AutoML. By integrating greater automation, AutoML can exploit more of the available data and deskill the development process to enable non‐data scientists to produce health monitoring models for a more diverse pool of aircraft components.https://doi.org/10.1002/eng2.70214aircraft maintenanceautomated machine learningmachine learningpredictive maintenance |
| spellingShingle | Izaak Stanton Kamran Munir Ahsan Ikram Murad El‐Bakry Automation of Predictive Maintenance: An Experimental Framework for Aircraft Landing Gear Engineering Reports aircraft maintenance automated machine learning machine learning predictive maintenance |
| title | Automation of Predictive Maintenance: An Experimental Framework for Aircraft Landing Gear |
| title_full | Automation of Predictive Maintenance: An Experimental Framework for Aircraft Landing Gear |
| title_fullStr | Automation of Predictive Maintenance: An Experimental Framework for Aircraft Landing Gear |
| title_full_unstemmed | Automation of Predictive Maintenance: An Experimental Framework for Aircraft Landing Gear |
| title_short | Automation of Predictive Maintenance: An Experimental Framework for Aircraft Landing Gear |
| title_sort | automation of predictive maintenance an experimental framework for aircraft landing gear |
| topic | aircraft maintenance automated machine learning machine learning predictive maintenance |
| url | https://doi.org/10.1002/eng2.70214 |
| work_keys_str_mv | AT izaakstanton automationofpredictivemaintenanceanexperimentalframeworkforaircraftlandinggear AT kamranmunir automationofpredictivemaintenanceanexperimentalframeworkforaircraftlandinggear AT ahsanikram automationofpredictivemaintenanceanexperimentalframeworkforaircraftlandinggear AT muradelbakry automationofpredictivemaintenanceanexperimentalframeworkforaircraftlandinggear |