Refine
Year of publication
- 2005 (23) (remove)
Institute
- IfB - Institut für Bioengineering (23) (remove)
Language
- English (23) (remove)
Document Type
- Article (21)
- Conference Proceeding (2)
Keywords
Searching optimal interplanetary trajectories for low-thrust spacecraft is usually a difficult and time-consuming task that involves much experience and expert knowledge in astrodynamics and optimal control theory. This is because the convergence behavior of traditional local optimizers, which are based on numerical optimal control methods, depends on an adequate initial guess, which is often hard to find, especially for very-low-thrust trajectories that necessitate many revolutions around the sun. The obtained solutions are typically close to the initial guess that is rarely close to the (unknown) global optimum. Within this paper, trajectory optimization problems are attacked from the perspective of artificial intelligence and machine learning. Inspired by natural archetypes, a smart global method for low-thrust trajectory optimization is proposed that fuses artificial neural networks and evolutionary algorithms into so-called evolutionary neurocontrollers. This novel method runs without an initial guess and does not require the attendance of an expert in astrodynamics and optimal control theory. This paper details how evolutionary neurocontrol works and how it could be implemented. The performance of the method is assessed for three different interplanetary missions with a thrust to mass ratio <0.15mN/kg (solar sail and nuclear electric).
Multiple Near-Earth Asteroid Rendezvous and Sample Return Using First Generation Solar Sailcraft
(2005)
Limit loads can be calculated with the finite element method (FEM) for any component, defect geometry, and loading. FEM suggests that published long crack limit formulae for axial defects under-estimate the burst pressure for internal surface defects in thick pipes while limit loads are not conservative for deep cracks and for pressure loaded crack-faces. Very deep cracks have a residual strength, which is modelled by a global collapse load. These observations are combined to derive new analytical local and global collapse loads. The global collapse loads are close to FEM limit analyses for all crack dimensions.
Low-thrust space propulsion systems enable flexible high-energy deep space missions, but the design and optimization of the interplanetary transfer trajectory is usually difficult. It involves much experience and expert knowledge because the convergence behavior of traditional local trajectory optimization methods depends strongly on an adequate initial guess. Within this extended abstract, evolutionary neurocontrol, a method that fuses artificial neural networks and evolutionary algorithms, is proposed as a smart global method for low-thrust trajectory optimization. It does not require an initial guess. The implementation of evolutionary neurocontrol is detailed and its performance is shown for an exemplary mission.