Zhang Chengfen, Niu Yanxiong, Zhang Hao, Lu Jiazhen
Appl Opt. 2018 Feb 10;57(5):1067-1074. doi: 10.1364/AO.57.001067.
High-precision ground calibration is essential to ensure the performance of star sensors. However, the complex distortion and multi-error coupling have brought great difficulties to traditional calibration methods, especially for large field of view (FOV) star sensors. Although increasing the complexity of models is an effective way to improve the calibration accuracy, it significantly increases the demand for calibration data. In order to achieve high-precision calibration of star sensors with large FOV, a novel laboratory calibration method based on a regularization neural network is proposed. A multi-layer structure neural network is designed to represent the mapping of the star vector and the corresponding star point coordinate directly. To ensure the generalization performance of the network, regularization strategies are incorporated into the net structure and the training algorithm. Simulation and experiment results demonstrate that the proposed method can achieve high precision with less calibration data and without any other priori information. Compared with traditional methods, the calibration error of the star sensor decreased by about 30%. The proposed method can satisfy the precision requirement for large FOV star sensors.
高精度地面校准对于确保星敏感器的性能至关重要。然而，复杂的畸变和多误差耦合给传统校准方法带来了极大困难，尤其是对于大视场（FOV）星敏感器。虽然增加模型的复杂度是提高校准精度的有效方法，但这显著增加了对校准数据的需求。为了实现大视场星敏感器的高精度校准，提出了一种基于正则化神经网络的新型实验室校准方法。设计了一种多层结构神经网络来直接表示星向量与相应星点坐标的映射。为确保网络的泛化性能，将正则化策略融入网络结构和训练算法中。仿真和实验结果表明，所提方法在较少校准数据且无需任何其他先验信息的情况下即可实现高精度。与传统方法相比，星敏感器的校准误差降低了约30%。所提方法能够满足大视场星敏感器的精度要求。
