Scientific Machine Learning for Engine Health Management and Remaining Useful Life Prediction
Summary
This paper presents a multi-task scientific machine learning framework for turbine prognostics that jointly predicts engine health metrics and remaining useful life with quantified uncertainty, using a shared sequence encoder and task-specific heads.
View Cached Full Text
Cached at: 06/01/26, 09:28 AM
# Scientific Machine Learning for Engine Health Management and Remaining Useful Life Prediction Source: [https://arxiv.org/abs/2605.30593](https://arxiv.org/abs/2605.30593) [View PDF](https://arxiv.org/pdf/2605.30593) > 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\. ## Submission history From: Jostein Barry\-Straume \[[view email](https://arxiv.org/show-email/25a4c5b3/2605.30593)\] **\[v1\]**Thu, 28 May 2026 21:39:53 UTC \(3,443 KB\)
Similar Articles
Benchmarking Machine Learning Uncertainty Quantification Methodologies for Predicting Turbine Gas Temperature Degradation
This paper benchmarks five uncertainty quantification methods for neural network predictions of turbine gas temperature, evaluating trade-offs in coverage, width, and stability to guide prognostics and health management in engines.
Leakage-Robust Evaluation and Data-Scale Sensitivity of Attention-Enhanced Multi-Task Learning for Joint Fault Diagnosis and Remaining Useful Life Estimation
This paper demonstrates that naive train/test splitting on sliding-window sequences can severely inflate or deflate performance metrics in multi-task learning for predictive maintenance, and proposes a leakage-robust evaluation protocol.
Robust and Personalized Federated Learning for Aircraft-Engine Prognostics under Benign and Adversarial Client Heterogeneity
This paper presents a controlled study of federated learning for aircraft-engine remaining-useful-life prediction under both benign and adversarial client heterogeneity, evaluating personalization and Byzantine-robust aggregation methods. It finds that shared-representation personalization closes much of the local-central accuracy gap, robust aggregation with Krum effectively mitigates backdoor attacks, and combining both yields a composed defense with low attack success at a modest accuracy cost.
Time-Series Foundation Model Embeddings for Remaining Useful Life Estimation
This paper introduces a lightweight approach for remaining useful life estimation using frozen embeddings from the Chronos-2 time-series foundation model combined with a simple regression head, achieving superior performance on industrial sensor data compared to baseline methods.
Semantic Feature Segmentation for Interpretable Predictive Maintenance in Complex Systems
This paper proposes a semantic feature segmentation framework for predictive maintenance that decomposes monitoring signals into canonical and residual components to improve interpretability while maintaining predictive performance.