基于深层神经网络的多颗近地小行星探测太阳帆轨道设计
Solar-Sail Trajectory Design for Multiple Near Earth Asteroid Exploration Based on Deep Neural Networks
摘要：
在多目标交会问题的初步轨道设计中，一个能够快速估算变轨代价的模型是必不可少的。利用太阳帆在两个任意轨道之间转移时间的估计是困难的，通常需要求解最优控制问题。受深度神经网络在非线性回归中成功应用的启发，探讨了利用深度神经网络从轨道特征映射太阳帆转移时间的可能性和有效性。在此基础上，研究了蒙特卡罗树搜索方法，并将其应用于多小行星探测问题的最优序列搜索。将通过顺序求解最优控制问题来求解和验证从初步设计获得的序列。两个不同应用背景的实例验证了该方法的有效性。
英文摘要：
In the preliminary trajectory design of the multi-target rendezvous problem, a model that can quickly estimate the cost of the orbital transfer is essential. The estimation of the transfer time using solar sail between two arbitrary orbits is difficult and usually requires to solve an optimal control problem. Inspired by the successful applications of the deep neural network in nonlinear regression, this work explores the possibility and effectiveness of mapping the transfer time for solar sail from the orbital characteristics using the deep neural network. Furthermore, the Monte Carlo Tree Search method is investigated and used to search the optimal sequence considering a multi-asteroid exploration problem. The obtained sequences from preliminary design will be solved and verified by sequentially solving the optimal control problem. Two examples of different application backgrounds validate the effectiveness of the proposed approach.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
