Failure prognosis provides critical decision-making support for Integrated System Health Management (ISHM), ensuring the operational safety of satellites in orbit. Temporal Convolutional Networks (TCNs), known for their capability in processing time-series data, have become an important approach for failure prognosis. The gradual performance degradation of satellites, combined with multi-physics coupling effects, gives rise to multi-scale features. However, existing TCN based failure prognosis methods remain limited in their ability to simultaneously capture both local and global features, posing challenges when processing such multi-scale features. To address this issue, a Cascaded Temporal Convolution and Transformer Network (CTCTN) framework is proposed for satellite failure prognosis and uncertainty quantification. The CTCTN first adaptively aligns the feature dimensions of the Depthwise Separable Temporal Convolution (DS-TC) block and the Transformer module through Adaptive Average Pooling (AAP), enabling both local feature extraction and global dependency modeling. A heteroscedastic Huber loss function is then designed to optimize the mean and variance of the CTCTN output. Finally, epistemic and aleatoric uncertainties are separately estimated and used to construct probabilistic prediction intervals. A satellite model is developed, and a run-to-failure dataset is constructed to validate the proposed CTCTN framework using a performance degradation scenario caused by damage to the Solar Array Paddle (SAP) of a Low Earth Orbit (LEO) satellite. Experimental results demonstrate that the proposed CTCTN method not only achieves more accurate Remaining Useful Life (RUL) predictions but also effectively quantifies uncertainty arising from multi-scale features. This work provides a reference case for failure prognosis in LEO satellites and offers decision support for ISHM.

With the increasing complexity of earth observation missions, mission planning for Low Earth Orbit (LEO) satellite cluster faces the growing contradiction between rising observation demands and limited onboard resources, which in turn intensifies environmental uncertainties and satellite system uncertainties during the observation process. To address the challenge of inefficient exploration by traditional Reinforcement Learning (RL) approaches for satellite mission planning, this paper proposes an Expert-Guided Hierarchical Reinforcement Learning (EG-HRL) method. The proposed method begins by establishing a physically-informed mission planning model that accounts for orbital perturbations from Earth’s non-spherical gravitational potential and eccentricity effects. A physics-based observation window prediction model is developed to enhance environment representation and support RL-based decision making. An integer programming model is also formulated to represent observation sequencing under task constraints and dynamic onboard resource limitations. A dual-layer EG-HRL framework is then designed. The high-level policy selects observation windows based on target priority and an expert-weighted reward function, while the low-level policy performs real-time window adjustment using a cost function derived from satellite resource states and expert-informed interval modeling. Simulation results demonstrate that the integration of expert knowledge significantly enhances planning performance in complex mission scenarios. Ablation studies confirm that both the expert guidance and the hierarchical structure are critical to this improvement. Comparative experiments further indicate that EG-HRL consistently outperforms both flat reinforcement learning and metaheuristic methods such as Improved Simulated Annealing (ISA) across various task scales. Moreover, evaluations under diverse internal and external uncertainties validate the method’s strong adaptability and robustness.

Modern warfare is increasingly dependent on logistical support. The improvement in satellite imaging technology and the increase in the number of satellites in orbit have provided a technical foundation for using satellite observations in military logistics. Due to uncertainties in the processes of production, transport, and observation, the satellite-based observation and state estimation of military logistics exhibit characteristics of uncertainty. This paper proposes an attribute-based staged method to quantify uncertainty, addressing mixed uncertainties during satellite observations of logistics. First, Bayesian estimation is used to quantify the aleatory uncertainty in the process of single-stage logistics observation. Second, evidence theory is adopted to quantify the epistemic uncertainty caused by conflicts in multi-stage logistics observation results and the lack of understanding of production principles. Through the design of the identification framework and the dynamic optimization of basic reliability, key logistics elements are identified, enabling an accurate estimation of the state of military logistics. Finally, the application case is used to validate the effectiveness and accuracy of the proposed method. Compared to conventional evidence theory, the proposed method can make fuller use of multi-source information and reduce the relative error between the estimated value and the true value to below 0.015%.

The uncertainty of the model should be statistically assessed as the foundation for model selection, as there are errors between the digital twin model and the actual system that must be reduced. However, the satellite digital twin model exhibits multi-dynamic, multi-spatial scale, and multi-physical field coupling properties. Additionally, the numerical solution will reveal the stiffness problem of ordinary differential equations and the multi-scale problem of partial differential equations. If many telemetry parameters are updated at the system level, the results will not converge. A multi-granularity and negotiation model updating framework for satellite digital twin method was proposed. The parameters were grouped by correlation analysis and frequency domain analysis. Multi-granularity digital twin models were built based on the requirements, and various granularity models of satellite subsystems and components were produced. The coupling relationship between the satellite structure of different levels was studied, and a negotiation updating method was proposed. Real on-orbit telemetry data were used to verify the framework. According to the research findings, the proposed method updating approach outperforms the unused one by over 50% in terms of accuracy, and the updating results are more thorough and methodical.