Title
Application of large language models in diagnostics and maintenance of aircraft propulsion systems
Authors
[ 1 ] Instytut Transportu, Wydział Inżynierii Lądowej i Transportu, Politechnika Poznańska | [ 2 ] Instytut Napędów i Lotnictwa, Wydział Inżynierii Lądowej i Transportu, Politechnika Poznańska | [ 3 ] Wydział Inżynierii Lądowej i Transportu, Politechnika Poznańska | [ P ] employee | [ SzD ] doctoral school student
Scientific discipline (Law 2.0)
Year of publication
2025
Published in
Article type
scientific article
Publication language
english
Keywords
Abstract
EN This study delves into the application of large language models (LLMs) in the diagnostics and maintenance of aircraft propulsion systems. Rapid advancements in aviation technology make there is an increasing need for sophisticated tools to assist in predicting and preventing equipment failures. LLMs, trained on extensive datasets, offer the potential to analyze telemetry and operational data, providing diagnostic insights and maintenance recommendations. This research explores the capabilities of LLMs in interpreting sensor data, identifying anomalies, and generating maintenance guidelines. The performance and limitations of LLMs are evaluated utilizing synthetic data from NASA to simulate real-world scenarios. Findings indicate that LLMs can enhance the reliability and efficiency of aircraft propulsion system maintenance significantly, despite challenges related to data quality and model limitations.
Date of online publication
01.01.2025
Pages (from - to)
304 - 320
License type
CC BY (attribution alone)
Open Access Mode
open journal
Open Access Text Version
final published version
Release date
01.01.2025
Date of Open Access to the publication
at the time of publication
Full text of article
Access level to full text
public
Ministry points / journal
100
System created by Poznań University of Technology
and Poznan Supercomputing and Networking Center
Log in through eKonto to add to SIS