Scientific Machine Learning for Engine Health Management and Remaining Useful Life Prediction
arXiv:2605.30593v1 Announce Type: new 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 uncert
The increasing complexity and autonomy of critical infrastructure, particularly in defense and logistics, demand more reliable and precise predictive maintenance solutions, pushing advancements in scientific machine learning.
This development allows for more accurate and proactive management of high-value assets like aircraft engines, directly impacting operational efficiency, safety, and maintenance costs.
The ability to jointly predict critical thermal indicators and Remaining Useful Life with uncertainty quantification transforms engine health management from reactive to predictive, mitigating risks more effectively.
- · Aerospace & Defense Industry
- · Predictive Maintenance Software Providers
- · AI/ML Engineering Firms
- · Fleet Operators
- · Traditional Time-Based Maintenance Providers
- · Suppliers of Low-Accuracy Diagnostic Tools
Reduced unscheduled downtime and optimized maintenance schedules for complex machinery.
Increased operational readiness and lifespan of critical assets, particularly in military and commercial aviation.
Enhanced supply chain resilience through predictive component replacement, possibly leading to 'just-in-case' inventory reductions.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG