Identifying heteroclinic connections using artificial neural networks
Identifying heteroclinic connections using artificial neural networks
- New search for: De Smet, Stijn
- Further information on De Smet, Stijn:
-
https://orcid.org/0000-0003-3196-6871
- New search for: Scheeres, Daniel J.
- New search for: De Smet, Stijn
- Further information on De Smet, Stijn:
-
https://orcid.org/0000-0003-3196-6871
- New search for: Scheeres, Daniel J.
Abstract This paper demonstrates the usage of artificial neural networks (ANN) to identify heteroclinic connections in astrodynamical systems. The ANN architecture is applied to find heteroclinic connections, or lack thereof, in the Earth-Moon circular restricted three body problem from to Lyapunov orbits for Jacobi values between 3.07 and 3.17. The predicted heteroclinic connections are within 0.1–1% of the arclength along the periodic orbit from their true locations.
Highlights Artificial neural networks can be used to Model periapse Poincaré maps. Design heteroclinic connections between L1 and L2 Lyapunov orbits. Obtained accuracy was 0.1–1.7% of the arclength along the periodic orbit.
Document information
Identifying heteroclinic connections using artificial neural networks
Acta Astronautica ; 161 ; 192-199
2019-05-06
8 pages
Article (Journal)
Electronic Resource
English
Similar titles
The Genesis Trajectory and Heteroclinic Connections
| NTRS | 1999
The Genesis Trajectory and Heteroclinic Connections (AAS 99-451)
| British Library Conference Proceedings | 2000
A Survey of Heteroclinic Connections in the Earth-Moon System
| TIBKAT | 2023
Homoclinic/Heteroclinic Connections of Equilibria and Periodic Orbits of Contact Binary Asteroids
| Online Contents | 2017