TY - JOUR
T1 - Low-thrust spacecraft trajectory optimization via a DNN-based method
AU - Yin, Shanshan
AU - Li, Jian
AU - Cheng, Lin
N1 - Publisher Copyright:
© 2020 COSPAR
PY - 2020/10/1
Y1 - 2020/10/1
N2 - Initial solution guess has a significant impact on the convergence of indirect methods, especially for continuous low-thrust trajectory optimization problems. In this study, an intelligent initial solution supplying approach based on deep neural networks (DNNs) is proposed to help achieve the fast generation of optimal trajectories for low-thrust orbit transfers. Energy-optimal and fuel-optimal trajectories with three different terminal conditions are considered. Based on the training dataset obtained by an indirect method, DNNs are constructed to approximate the solutions corresponding to different flight states. Based on the trained DNNs, an intelligent trajectory optimization method named DNN-based method is developed with the help of the homotopy technique. Numerical simulations are conducted to evaluate the performance of the proposed method on success rates and time consumptions. Simulation results demonstrate that the combination of traditional techniques and the new DNN technology can achieve the fast generation of low-thrust optimal trajectories with advantages on computational efficiency and reliability.
AB - Initial solution guess has a significant impact on the convergence of indirect methods, especially for continuous low-thrust trajectory optimization problems. In this study, an intelligent initial solution supplying approach based on deep neural networks (DNNs) is proposed to help achieve the fast generation of optimal trajectories for low-thrust orbit transfers. Energy-optimal and fuel-optimal trajectories with three different terminal conditions are considered. Based on the training dataset obtained by an indirect method, DNNs are constructed to approximate the solutions corresponding to different flight states. Based on the trained DNNs, an intelligent trajectory optimization method named DNN-based method is developed with the help of the homotopy technique. Numerical simulations are conducted to evaluate the performance of the proposed method on success rates and time consumptions. Simulation results demonstrate that the combination of traditional techniques and the new DNN technology can achieve the fast generation of low-thrust optimal trajectories with advantages on computational efficiency and reliability.
KW - Continuous low-thrust spacecraft
KW - Deep neural networks
KW - Indirect method
KW - Trajectory optimization
UR - http://www.scopus.com/inward/record.url?scp=85086671395&partnerID=8YFLogxK
U2 - 10.1016/j.asr.2020.05.046
DO - 10.1016/j.asr.2020.05.046
M3 - Article
AN - SCOPUS:85086671395
SN - 0273-1177
VL - 66
SP - 1635
EP - 1646
JO - Advances in Space Research
JF - Advances in Space Research
IS - 7
ER -