The number of remote sensing satellites has increased rapidly in parallel with the advancement of space technology and the rising demand in the space industry. Consequently, the observation effectiveness evaluation of remote sensing satellites has received extensive attention. As the core content of the effectiveness evaluation, index systems are usually established and screened using qualitative or quantitative methods. They can hardly satisfy the construction principles such as completeness and independence simultaneously. To address this issue, we propose a new method for remote sensing satellite observation effectiveness evaluation that considers various principles. Firstly, a three-layer evaluation index system structure is constructed. The principle of completeness, hierarchy, and measurability of the index system is ensured by decomposition, clustering, and preliminary screening. Secondly, the principal component contribution rate is obtained through principal component analysis. Finally, we introduce a comprehensive scoring method (ICCLR) based on the combination of independence coefficient and principal component comprehensive loss rate. It realizes the screening of an index system from the index set containing correlation relationships. The validity and optimality of the proposed method are verified through experiments and analysis of three typical tasks.

An optimal real-time neural-network-based controller for an on-orbit service mission is proposed. The problem can be mathematically formulated as a complex optimal control problem due to the coupli...

Recently, remote sensing satellites have become increasingly important in the Earth observation field as their temporal, spatial, and spectral resolutions have improved. Subsequently, the quantitative evaluation of remote sensing satellites has received considerable attention. The quantitative evaluation method is conventionally based on simulation, but it has a speed-accuracy trade-off. In this paper, a real-time evaluation model architecture for remote sensing satellite clusters is proposed. Firstly, a multi-physical field coupling simulation model of the satellite cluster to observe moving targets is established. Aside from considering the repercussions of on-board resource constraints, it also considers the consequences of the imaging’s uncertainty effects on observation results. Secondly, a moving target observation indicator system is developed, which reflects the satellite cluster’s actual effectiveness in orbit. Meanwhile, an indicator screening method using correlation analysis is proposed to improve the independence of the indicator system. Thirdly, a neural network is designed and trained for stakeholders to realize a rapid evaluation. Different network structures and parameters are comprehensively studied to determine the optimized neural network model. Finally, based on the experiments carried out, the proposed neural network evaluation model can generate real-time, high-quality evaluation results. Hence, the validity of our proposed approach is substantiated.

In this paper, a real-time optimal attitude controller is designed for staring imaging, and the output command is based on future prediction. First, the mathematical model of staring imaging is established. Then, the structure of the optimal attitude controller is designed. The controller consists of a preprocessing algorithm and a neural network. Constructing the neural network requires training samples generated by optimization. The objective function in the optimization method takes the future control effect into account. The neural network is trained after sample creation to achieve real-time optimal control. Compared with the PID (proportional-integral-derivative) controller with the best combination of parameters, the neural network controller achieves better attitude pointing accuracy and pointing stability.

When approaching and removing a disabled satellite, the accuracy of the controller is imperative to the success of the mission because if the mission fails, more space debris can be produced due to satellite collision. To address this issue, a controller directly driven by discrete sample data points is proposed in this paper. First, the input vector for the controller is placed into a state space as a point. The state space also contains points constructed by the input vectors of pre-generated samples, which are created by the GPOPS planning algorithm along with control commands as sample output vectors. Then, an adjacent range is selected and the sample points within are collected. To accelerate the process, a series of data processing methods are implemented, including the dichotomy method, table look-up method, and random selection method. Finally, the control commands are computed using the iteratively reweighted least-squares algorithm with the assumption that similar inputs have similar outputs. According to the simulation results, the discrete point controller is more precise than the neural network controller.

Removing disabled satellites is essential to the efficient utilization of orbital resources. Approaching a target satellite is one of the critical stages of the whole removal process, requiring the chaser satellite to perform accurate control. In this paper, we propose a method to establish a neural network controller that utilizes an optical camera as the sole relative measurement device. To achieve this, we first create a set of optimal approach trajectories and generate a numerical dataset. We then modify this dataset to instruct the neural network controller to generate additional corrective forces when the relative velocity deviates from its optimal value due to unexpected disturbances. By making use of the modified dataset and 3D simulations, we create image sequences that are employed as training samples in deep learning. Finally, the neural network controller established based on the 3D-ResNet-18 architecture is trained and obtained. The simulation results suggest that our approach significantly improves control accuracy under thruster output uncertainty.