Hybrid Digital Twin for Aero-Engine Bearing Prognostics: A Physics-Informed Machine Learning Approach to RUL Prediction

Unscheduled maintenance due to the failure of critical components, such as aero-engine rolling element bearings, is a leading cause of costly Aircraft-on-Ground (AOG) events; consequently, current time-based maintenance practices are inefficient and prone to risk. This paper develops a resource-efficient Hybrid Digital Twin (HDT) model for an engine bearing, focusing on the dynamic prediction of spall growth due to Rolling Contact Fatigue (RCF), thereby enabling a condition-based maintenance paradigm. The HDT architecture integrates two core models: (1) a physics-informed model that uses established life and fatigue theory to define initial degradation thresholds and constrain the failure envelope, and (2) a data-driven Recurrent Neural Network (RNN) (specifically, an LSTM) for dynamic degradation rate modeling. The methodology utilizes a Monte Carlo simulation coupled with RCF progression equations to generate a large, synthetic run-to-failure dataset under varying operational loads, accurately simulating realistic mission profiles. This synthetic time-series data, specifically the simulated vibration frequency signatures, trains the RNN to estimate the component's State-of-Health (SOH). The HDT demonstrates a significant improvement in prognostic accuracy, consistently predicting the Remaining Useful Life (RUL) of the bearing with a Mean Absolute Error (MAE) under 5% compared to the simulated failure time. The hybrid approach proves superior by effectively compensating for the non-linearity and uncertainty inherent in real-world operational data while maintaining physical grounding. This computationally efficient, laptop-based approach directly supports the Digital Engineering Transformation theme by providing a blueprint for the virtual qualification of critical mechanical components, offering a pathway to substantial MRO cost reduction and improved fleet availability.