Publication Date

Spring 2025

Degree Type

Master's Project

Degree Name

Master of Science in Computer Science (MSCS)

Department

Computer Science

First Advisor

Saptarshi Sengupta

Second Advisor

Navrati Saxena

Third Advisor

Amith Kamath Belman

Keywords

Remaining Useful Life (RUL), N-CMAPSS Dataset, Bi-LSTM, Residual Features, Predictive Maintenance, Asymmetric Loss Function

Abstract

Accurate prediction of Remaining Useful Life (RUL) for aircraft engines is important to enhance maintenance efficiency and flight safety. For this project, a solution to RUL prediction on NASA's N-CMAPSS data set, mimicking realistic engine degradation under simulated full-flight scenarios, is being proposed. For addressing the high-dimensional noisy sensor data challenge, a new feature engineering pipeline was utilized. Models trained on healthy data predict normal sensor behavior, and the discrepancy between these predictions—referred to as residual features—is a measure of degradation. To handle the size and computational demands of the dataset, training was conducted on Google Cloud Platform using GPU-supported virtual machines and cloud storage. The residual features were used to train a Bidirectional Long Short-Term Memory (Bi-LSTM) network to learn temporal relationships in engine behavior. The model was trained with NASA's asymmetric scoring function, which penalizes overestimation more severely to make safer, more conservative RUL predictions. Testing on unseen engine units revealed the model to be close to simulating actual RUL patterns throughout degradation periods. Accuracy during early life stages remains limited due to the absence of useful degradation signals. Overall, the approach offers a robust framework for data-driven, condition-based maintenance in aviation and comparable industries.

Download

Available for download on Monday, May 25, 2026

Share

COinS