Abstract
In order to solve the problem of trajectory optimization of Space Maneuver Vehicle (SMV), a dynamic neural network method is introduced. Combined with neural network and Pontryagin's maximum principle, the method is able to approximate the optimal solution by neural network. At the same time, with the dynamic process, the problem of guessing covariates' initial value in traditional indirect method has been solved fairly well. In this work, the principle of the Dynamic Neural Network (DNN) optimal algorithm has been given and the optimization process has been described in detail. The simulation results indicated that using Dynamic Neural Network optimal algorithm can avoid guessing the covariates' initial value and satisfy the real-time requirements. Moreover, it has a higher accuracy solution.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.