Advancing Fault Diagnosis in Aircraft Landing Gear - An Innovative Two-Tier Machine Learning Approach - with Intelligent Sensor Data Management

Aug 4, 2026

Revolutionizing aircraft safety, the study presents a two-tier machine learning framework for real-time fault diagnosis in aircraft landing gear systems. It tackles a critical limitation of traditional methods: sensor data anomalies that degrade diagnostic reliability. The approach models complex hydraulic failures using simulation-based data to train robust classifiers while a secondary tier imputes and corrects irregular sensor inputs through redundant measurements. Results show diagnostic accuracy improves from 95.88% to 98.76% after imputation, enabling uninterrupted health assessment and supporting safer, more cost-effective maintenance decisions.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Introduction

Landing gear health monitoring: safety and economic impact

Limits of model-driven vs data-driven diagnostic methods

Motivation for two-tier robust ML with sensor anomaly handling

AIAA SciTech Forum 10.2514/6 .2024-0759 8-12 January 2024, Orlando, FL AIAA SCITECH 2024 Forum Advancing Fault Diagnosis in Aircraft Landing Gear: An innovative two-tier Machine Learning Approach with intelligent sensor data management Kadripathi KN, Adolfo Perrusquia, Antonios Tsourdos, Dmitry Ignatyev School of Aerospace, Transport and Manufacturing, Cranfield University, Cranfield MK43 OAL, United Kingdom Revolutionizing aircraft safety, this study unveils a pioneering two-tier machine learning model specifically designed for advanced fault diagnosis in aircraft landing gear systems. Addressing the critical gap in traditional diagnostic methods, our approach deftly navigates the challenges of sensor data anomalies, ensuring robust and accurate real-time health assessments. This innovation not only promises to enhance the reliability and safety of aviation but also sets a new benchmark in the application of intelligent machine-learning solutions in high-stakes environments. Our method is adept at identifying and compensating for data anomalies caused by faulty or uncalibrated sensors, ensuring uninterrupted health assessment. The model employs a simulation-based dataset reflecting complex hydraulic failures to train robust machine learning classifiers for fault detection. The primary tier focuses on fault classification, whereas the secondary tier corrects sensor data irregularities, leveraging redundant sensor inputs to bolster diagnostic precision. Such integration markedly improves classification accuracy, with empirical evidence showing an increase from 95.88% to 98.76% post-imputation. Our findings also underscore the importance of specific sensors— particularly temperature and pump speed—in evaluating the health of landing gear, advocating for their prioritized usage in monitoring systems. This approach promises to revolutionize maintenance protocols, reduce operational costs, and significantly enhance the safety measures within the aviation industry, promoting a more resilient and data-informed safety infrastructure. Keywords: Fault Diagnosis, Aircraft Landing Gear Systems, Machine Learning, Sensor Data Imputation, Hydraulic Failure Simulation, Safety Enhancement in Aviation, Real-time Health Assessment, Diagnostic Accuracy Improvement. I. Nomenclature AI = Artificial Intelligence ML = Machine Learning ICAO = International Civil Aviation Organization ATA 32 = Air Transport Association Chapter 32: Landing Gear TapAir = Hydraulic fluid-to-air ratio RPM = Revolutions Per Minute EDA = Exploratory Data Analysis KNN = K-Nearest Neighbors XGBoost = Extreme Gradient Boosting 1 Copyright © 2024 by Kadripathi KN. Published by the American Institute of Aeronautics and Astronautics, Inc., with permission. Issued with: Creative Commons Attribution License (CC:BY 4.0) . The final published version (version of record) is available online at DOI:10.2514/6.2024-0759 . Please refer to any applicable publisher terms of use. II. Introduction Aircraft, epitomizing the zenith of modern engineering, comprise an intricate matrix of systems and subsystems functioning cohesively to guarantee a secure flight. At the heart of this matrix lies the landing gear system, an indispensable, non-redundant element of an aircraft's architecture. Acting as a conduit between the aircraft and the ground, it encompasses a range of dynamic components, including the landing gear, wheels, brakes, shock absorbers, retraction mechanisms, control valves, and supplementary systems. Notably, each component within an aircraft is usually complemented by a backup or redundant system to ensure continuity of operation in the event ofa malfunction. For instance, should a primary thruster fail, the aircraft can seamlessly switch to an auxiliary thruster, enabling the flight to proceed to the nearest suitable landing site. This redundancy principle applies to various subsystems, such as navigation,

FAQs

Why is landing gear health monitoring critical for aviation?

Landing gear health monitoring directly supports passenger safety and economic efficiency. The document cites a significant share of aviation accidents linked to landing gear failure.

What problem does the proposed two-tier method address in fault diagnosis?

It addresses sensor data anomalies that can mislead machine learning models, causing false alarms or missed/incorrect fault predictions.

How does the two-tier model improve diagnostic accuracy?

The primary tier focuses on fault classification, while the secondary tier corrects sensor irregularities using redundant sensor inputs, improving accuracy from 95.88% to 98.76% after imputation.

Aug 4, 2026

Upload by Emma Wilson