Application of Computational Intelligence in Order to Develop Hybrid Orbit Propagation Methods

Abstract

We present a new approach in astrodynamics and celestial mechanics fields, calledhybrid perturbation theory. A hybrid perturbation theory combines anintegrating technique, general perturbation theory or special perturbation theory or semianalytical method, with aforecasting technique, statistical time series model or computational intelligence method. This combination permits an increase in the accuracy of the integrating technique, through the modeling of higher-order terms and other external forces not considered in the integrating technique. In this paper, neural networks have been used as time series forecasters in order to help two economic general perturbation theories describe the motion of an orbiter only perturbed by the Earth’s oblateness.