Orbit determination (OD) for spacecraft with unknown maneuver is always a challenging task. This paper proposes a novel framework for efficiently solving continuously maneuvering spacecraft OD problems by merging the Long Short-Term Memory (LSTM) neural network and the filter algorithms. A polynomial-representation fitted the unknown continuous maneuver is first proposed. Rather than directly output the estimated maneuver, the LSTM is trained to detect the unknown maneuver and then estimate the coefficients of the polynomial-representation. Then a fusion is designed to combine the prediction of the LSTM and the estimation of the filter for a more accurate estimation. The proposed LSTM-based framework is successfully applied to solve a Low-Earth-orbit OD problem and a Middle-Earth-orbit OD problem. The continuously maneuvering target is well tracked and the unknown maneuver is accurately estimated. Numerical simulations show that the LSTM trained based on one training dataset can also be applied to other scenarios that share some common features with the training dataset.

机动未知航天器的轨道确定（OD）始终是一项具有挑战性的任务。本文提出了一种新的框架，通过合并长短期记忆 (LSTM) 神经网络和滤波器算法，有效解决连续机动航天器 OD 问题。首次提出了拟合未知连续机动的多项式表示。不是直接输出估计的机动，而是训练 LSTM 来检测未知机动，然后估计多项式表示的系数。然后设计了一个融合，将 LSTM 的预测和滤波器的估计结合起来，以获得更准确的估计。所提出的基于 LSTM 的框架成功地应用于解决低地球轨道 OD 问题和中地球轨道 OD 问题。连续机动目标被很好地跟踪，未知机动被准确估计。数值模拟表明，基于一个训练数据集训练的 LSTM 也可以应用于与训练数据集具有一些共同特征的其他场景。