Scientific Machine Learning for Engine Health Management and Remaining Useful Life Prediction

2026-05-28

AI Summary

This study addresses key challenges in aero-engine health monitoring—namely, heterogeneous and non-stationary fleet data, and the lack of uncertainty quantification in point predictions—for remaining useful life (RUL) estimation and turbine gas temperature (TGTU/DTGT) tracking. To this end, the authors propose a multi-task scientific machine learning framework featuring a shared sequence encoder (comprising a convolutional front-end, residual bidirectional LSTM, and attention-based pooling), coupled with task-specific probabilistic regression heads and an optional survival analysis head. The model jointly outputs point estimates and empirically calibrated prediction intervals for RUL, TGTU, and DTGT, innovatively integrating multi-task learning with uncertainty quantification. A tunable parameter mechanism further enables adaptation to diverse operational and maintenance strategies. Experimental results demonstrate superior performance across metrics including MAE, PICP, MPIW, and CWC, while stratified analyses reveal how flight phase and maintenance status influence prediction uncertainty, thereby supporting risk-aware operational decisions.

Abstract

Engine Health Management (EHM) depends on reliable forecasting of Remaining Useful Life (RUL) and on tracking thermal indicators such as turbine gas temperature (TGT). In practice, real-world fleet data are heterogeneous and non-stationary, and point predictions alone are insufficient for risk-aware maintenance decisions. This paper presents a multi-task scientific machine learning framework for turbine prognostics that jointly predicts turbine gas temperature untrimmed (TGTU), Delta Turbine Gas Temperature (DTGT), and RUL, with quantified uncertainty in the form of prediction intervals whose empirical coverage is evaluated. A shared sequence encoder (convolutional front-end with residual bidirectional LSTM layers and attention pooling) feeds task-specific heads, including mean--variance estimation for probabilistic regression and, optionally, a survival head for threshold-based event modeling. The framework is designed to be tunable via a small set of practitioner-facing parameters (e.g., DTGT thresholding rules and RUL target construction) so that deployment can align with in-house policies and proprietary criteria. The predictive performance of the proposed framework is evaluated using both point and interval metrics, including mean absolute error (MAE), prediction interval coverage probability (PICP), mean prediction interval width (MPIW), and the coverage--width criterion (CWC). Results are reported both in aggregate and stratified by flight phase and maintenance segment to highlight operational-context effects and to support uncertainty-aware monitoring.

Problem

• Engine Health Management
• Remaining Useful Life Prediction
• Turbine Gas Temperature
• Uncertainty Quantification
• Heterogeneous Data

Innovation

• scientific machine learning
• multi-task learning
• uncertainty quantification
• remaining useful life prediction
• turbine prognostics