Predicting Aircraft Engine Failures Using Machine Learning: A Novel Approach on NASA Turbofan Engine Degradation Data

Ramesh, Khamalesh (2025) Predicting Aircraft Engine Failures Using Machine Learning: A Novel Approach on NASA Turbofan Engine Degradation Data. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (932kB) | Preview

Abstract

Accurate prediction of the remaining useful life (RUL) of turbofan engines is essential for enhancing safety, reducing maintenance costs, and enabling predictive maintenance in aerospace operations. However, existing RUL prediction methods often face challenges such as noisy sensor data, limited generalization across varying operating conditions, and low interpretability. To address these challenges, this study proposes a hybrid deep learning framework that combines convolutional neural networks (CNNs), bidirectional long short-term memory(BiLSTM)networks, and attention mechanisms. The architecture employs multi-kernel 1D CNNs to extract local patterns from sensor data, BiLSTMs to capture temporal dynamics, and dual attention mechanisms to highlight critical sensors and time steps. Wavelet-based denoising, rolling statistics, and delta features are applied during preprocessing to improve signal quality, while automated, dataset-specific hyperparameter tuning ensures adaptability to varied operational scenarios. The proposed approach demonstrates robust performance and high interpretability across diverse operating regimes and fault modes, indicating its stability and generalizability. These characteristics make the framework a practical and deployable solution for predictive maintenance in aerospace applications. By integrating advanced signal processing techniques, deep learning and automated optimization, the framework supports early and informed decision-making in safety-critical environments.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Rifai, Hicham UNSPECIFIED
Subjects:	T Technology > TL Motor vehicles. Aeronautics. Astronautics Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	26 Aug 2026 10:36
Last Modified:	26 Aug 2026 10:36
URI:	https://norma.ncirl.ie/id/eprint/9658

Actions (login required)

View Item