Abstract
In this paper, neural networks are trained to learn the optimal time, the initial costates, and the optimal control law of time-optimal low-thrust interplanetary trajectories. The aim is to overcome the difficult selection of first guess costates in indirect optimization, which limits their implementation in global optimization and prevents on-board applications. After generating a dataset, three networks that predict the optimal time, the initial costate, and the optimal control law are trained. A performance assessment shows that neural networks are able to predict the optimal time and initial costate accurately, especially a 100% success rate is achieved when neural networks are used to initialize the shooting function of indirtect methods. Moreover, learning the state-control pairs shows that neural networks can be utilized in real-time, on-board optimal control.
Highlights
Solar electric propulsion (SEP) is an ideal option for interplanetary missions, because of its high specific impulse and fuel saving capability
We show that neural networks (NNs) can predict the optimal time and initial costate accurately, so improving the efficiency in shooting convergence, and paving the way to real-time, on-board controller
The orbital distances are acceptable. These results show that NNs have excellent performance and generalization capability in predicting the optimal time and initial costates
Summary
Solar electric propulsion (SEP) is an ideal option for interplanetary missions, because of its high specific impulse and fuel saving capability. Even though indirect methods perform well in optimizing low-thrust trajectories, the optimization process is timeconsuming, which involves two issues: global mission design and real-time on-board implementation. NNs are trained to learn the optimal time and fuel of low-thrust transfers [26]–[28]. NNs are utilized as both predictors and optimal controllers in indirect optimization of low-thrust trajectories, that is, they are trained to learn the optimal time, the initial costate, as well as the optimal control of timeoptimal problems (TOP). We show that NNs can predict the optimal time and initial costate accurately, so improving the efficiency in shooting convergence, and paving the way to real-time, on-board controller. This paper is organized as follows: In Section 2, the indirect method for time-optimal low-thrust trajectory optimization as well as the dataset generation procedure are presented.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
