On-orbit refueling of sun-synchronous-orbit (SSO) satellite clusters requires effective deployment of fuel stations (FSs). To this end, this paper investigates the deployment optimization problem of fuel stations for SSO clusters by considering orbital geometry, satellite-to-station assignment, and refueling mission feasibility. A \(J_2\)-aware optimization framework is proposed, in which a particle swarm optimizer searches for optimal fuel-station orbital parameters and satellite assignments. For each candidate deployment, a deterministic mission evaluator is employed to estimate natural alignment opportunities, transfer requirements, and fuel consumption. The proposed approach considers th... More >

Remaining useful life (RUL) prediction is a core task in prognostics and health management. While Transformers excel at modeling long-range temporal dependencies, their performance is highly sensitive to hyperparameters, and improper splitting of sliding-window samples can introduce data leakage. We propose a Sparrow Search Algorithm (SSA)-optimized Transformer for CMAPSS RUL prediction, adopting an engine-wise split for leakage-aware model selection and using validation RMSE as the fitness function to guide SSA-based hyperparameter optimization. On the FD001 test set, the model achieves RMSE $13.79$, MAE $10.00$, $R^2=0.88$, and a NASA score of $356.26$. The prediction curves and residual d... More >