Automating the process of optimization in spacecraft design

Author

Fukunaga, Alex S. ; Chien, Steve ; Mutz, Darren ; Sherwood, Robert L. ; Stechert, Andre D.

Author_Institution

Jet Propulsion Lab., California Inst. of Technol., Pasadena, CA, USA

Volume

4

fYear

1997

fDate

1-8 Feb 1997

Firstpage

411

Abstract

Spacecraft design optimization is a difficult problem, due to the complexity of optimization cost surfaces and the human expertise in optimization that is necessary in order to achieve good results. In this paper, we propose the use of a set of generic, metaheuristic optimization algorithms (e.g., genetic algorithms, simulated annealing), which is configured for a particular optimization problem by an adaptive problem solver based on artificial intelligence and machine learning techniques. We describe work in progress on OASIS, a system for adaptive problem solving based on these principles

Keywords

CAD; adaptive systems; aerospace computing; genetic algorithms; learning (artificial intelligence); problem solving; Mars; Neptune Orbiter; OASIS; adaptive problem; adaptive problem solving; artificial intelligence; complexity; generic metaheuristic optimization algorithms; machine learning; optimization cost; simulated annealing; spacecraft design; Adaptive systems; Artificial intelligence; Cost function; Design optimization; Genetic algorithms; Humans; Machine learning; Machine learning algorithms; Simulated annealing; Space vehicles;

fLanguage

English

Publisher

ieee

Conference_Titel

Aerospace Conference, 1997. Proceedings., IEEE

Conference_Location

Snowmass at Aspen, CO

Print_ISBN

0-7803-3741-7

Type

conf

DOI

10.1109/AERO.1997.577524

Filename

577524