Remaining Useful Life Prediction for Hall Thrusters Based on Adaptive Self-Cognizant Dynamic System and Multi-Physics Modeling

Abstract Hall thrusters, characterized by high specific impulses and extended operational durations, are increasingly recognized as promising electric propulsion devices for long-duration missions and station-keeping of cislunar satellites. However, the failure of channel wall erosion caused by sputtering remains a significant challenge, compromising the functionality and reliability of Hall thrusters. This paper proposes a novel Hall thruster remaining useful life (RUL) prediction approach based on adaptive self-cognizant dynamic system (ASDS) with multi-physics modeling. First, a low-fidelity plasma discharge model and a semi-empirical sputter model are integrated to reveal erosion mechanism and efficiently generate degradation data. Then, an ASDS state-space model, employing fully-connected neural networks (FCNNs) as system modelers, is established based on erosion mechanism and trained offline with simulation data. Upon receiving online telemetry observations, the state of health and FCNN parameters are estimated and updated through particle filter. The RUL and its distribution are finally predicted by forwarding the state of health across different particles. Case study on SPT-100 Hall thruster validates the effectiveness of the proposed ASDS approach, which not only captures the fundamental failure mechanisms and adjusts to environmental changes, but also provides the distribution of RUL as valuable prior information for thruster refueling and maintenance decision-making.