Integrating explainable AI into two-tier ML models for trustworthy aircraft landing gear fault diagnosis

Simple item page
dc.contributor.authorKN, Kadripathi
dc.contributor.authorPerrusquia, Adolfo
dc.contributor.authorTsourdos, Antonios
dc.contributor.authorIgnatyev, Dmitry
dc.date.accessioned2025-03-07T12:11:52Z
dc.date.available2025-03-07T12:11:52Z
dc.date.freetoread2025-03-07
dc.date.issued2025-01-06
dc.date.pubOnline2025-01-31
dc.descriptionCorrection Notice: Title of the research is changed from “Comprehensive Exploration and Development of Explainable AI for Robust Aircraft Landing Gear Fault Diagnosis” to “Integrating Explainable AI into Two-Tier ML Models for Trustworthy Aircraft Landing Gear Fault Diagnosis”, because the present research paper is more research oriented than the just exploration as submitted during abstract submission. Authors list is updated, Antonios Tsourdos name is included. And Figure 1 has to replaced with this HD images [sic], the one in the published paper is of very low quality.
dc.description.abstractAs the aviation industry increasingly relies on data-driven intelligence to enhance safety and operational efficiency, the demand for AI solutions that are both technically robust and readily interpretable continues to intensify. This research presents a pioneering methodology for advanced fault diagnosis in aircraft landing gear systems that not only achieves high predictive accuracy but also provides transparent, actionable insights. Building upon a twotier machine learning framework—integrating fault classification with intelligent sensor data imputation—we demonstrate how state-of-the-art explainability techniques, notably LIME and SHAP, can elucidate the underlying logic of complex models. By exposing the critical features and sensor parameters driving each decision, this approach empowers maintenance engineers and operations personnel to understand, validate, and trust the model’s outputs rather than relying on opaque “black-box” predictions. Our results indicate that interpretable fault diagnoses facilitate more confident decisionmaking, streamline maintenance interventions, and reduce the likelihood of unforeseen component failures. Beyond mere compliance with emerging regulatory standards for AI transparency, this method establishes a blueprint for deploying machine learning solutions that are not only accurate and robust, but also inherently comprehensible. In an era where aerospace systems must seamlessly integrate precision, reliability, and human oversight, our work sets a precedent for creating intelligent tools that foster trust, enhance collaboration between technical experts and AI models, and ultimately contribute to safer and more efficient aviation operations.
dc.description.conferencenameAIAA SCITECH 2025 Forum
dc.identifier.citationKadripathi KN, Perrusquia A, Tsourdos A, Ignatyev D. (2025) Integrating explainable AI into two-tier ML models for trustworthy aircraft landing gear fault diagnosis. In: AIAA SCITECH 2025 Forum, 6-10 January 2025, Orlando, FL, USA. Paper number AIAA 2025-1928.c1
dc.identifier.elementsID564468
dc.identifier.urihttps://doi.org/10.2514/6.2025-1928
dc.identifier.urihttps://doi.org/10.2514/6.2025-1928.c1
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/23563
dc.language.isoen
dc.publisherAIAA
dc.publisher.urihttps://arc.aiaa.org/doi/10.2514/6.2025-1928
dc.rightsAttribution 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subject40 Engineering
dc.subject4001 Aerospace Engineering
dc.subject40 Engineering
dc.subject4001 Aerospace Engineering
dc.titleIntegrating explainable AI into two-tier ML models for trustworthy aircraft landing gear fault diagnosis
dc.typeConference paper
dcterms.coverageOrlando, FL
dcterms.dateAccepted2024-08-31
dcterms.temporal.endDate10-Jan-2025
dcterms.temporal.startDate6-Jan-2025

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Integrating_explainable_AI_into_two-tier_ML_models-2025.pdf
Size:
596.58 KB
Format:
Adobe Portable Document Format
Description:
Accepted version with correction
Download

Collections

Staff publications (SATM)