Abstract This paper introduces an innovative approach for generating re-entry trajectories for a reusable winged spacecraft. This approach utilizes Fourier series parametrized control profiles. The Fourier coefficients are derived through a combination of the Improved Search Space Reduction (ISSR) technique and Sequential Quadratic Programming (SQP) optimization methods, which effectively limit the maximum heat rate experienced by the spacecraft. These re-entry trajectories and control profiles are then used to train artificial neural networks, enabling the controller to provide optimal control inputs based on the spacecraft’s current altitude and velocity. To validate this methodology, Hardware-in-loop (HIL) simulations are conducted, integrating the designed neural network-based controller with a Texas Instruments TI Delfino TMSF28335 controller and a real-time simulator, the OPAL-RT OP4510. The results of the HIL simulation demonstrate that the generated re-entry trajectory accurately adheres to heat rate and terminal constraints. Additionally, the Fourier series parametrization of control profiles is applied to a high lift-to-drag ratio CAV-H vehicle, showcasing the method’s versatility. Furthermore, resilience of proposed method to uncertainties in aerodynamic coefficients and atmospheric density is also demonstrated. The results show that the proposed method is generic and exhibits robustness to uncertainties.
Neural network-based hardware-in-the-loop implementation of fourier series parametrized control profiles for re-entry vehicles
Advances in Space Research ; 73 , 9 ; 4782-4799
2024-01-19
18 pages
Article (Journal)
Electronic Resource
English
A Closed Loop Guidance Scheme For Re-Entry Vehicles
British Library Conference Proceedings | 2003
|Taylor & Francis Verlag | 2016
|Automotive engineering | 2016
|British Library Conference Proceedings | 2019
|